Used

List of free educational ML resources I used to become a FAANG ML Engineer

Full commentary and notes here ➡️: https://www.trybackprop.com/blog/top\ml\learning\resources Used these to brush up on math and teach myself AI/ML over the course of two years. I'm now a staff ML engineer at FAANG. Hope these help. Fundamentals Linear Algebra – 3Blue1Brown's Essence of Linear Algebra series, binged all these videos on a one hour train ride visiting my parents Multivariable Calculus – Khan Academy's Multivariable Calculus lessons were a great refresher of what I had learned in college. Looking back, I just needed to have reviewed Unit 1 – intro and Unit 2 – derivatives. Calculus for ML – this amazing animated video explains calculus and backpropagation Information Theory – easy-to-understand book on information theory called Information Theory: A Tutorial Introduction. Statistics and Probability – the StatQuest YouTube channel Machine Learning Stanford Intro to Machine Learning by Andrew Ng – Stanford's CS229, the intro to machine learning course, published their lectures on YouTube for free. I watched lectures 1, 2, 3, 4, 8, 9, 11, 12, and 13, and I skipped the rest since I was eager to move onto deep learning. The course also offers a free set of course notes, which are very well written. Caltech Machine Learning – Caltech's machine learning lectures on YouTube, less mathematical and more intuition based Deep Learning Andrej Karpathy's Zero to Hero Series – Andrej Karpathy, an AI researcher who graduated with a Stanford PhD and led Tesla AI for several years, released an amazing series of hands on lectures on YouTube. highly highly recommend Neural networks – Stanford's CS231n course notes and lecture videos were my gateway drug*, so to speak, into the world of deep learning. Transformers and LLMs Transformers – watched these two lectures: lecture from the University of Waterloo and lecture from the University of Michigan. I have also heard good things about Jay Alammar's The Illustrated Transformer guide ChatGPT Explainer – Wolfram's YouTube explainer video on ChatGPT Interactive LLM Visualization – This LLM visualization that you can play with in your browser is hands down the best interactive experience with an LLM. Financial Times' Transformer Explainer – The Financial Times released a lovely interactive article that explains the transformer very well. Residual Learning – 2023 Future Science Prize Laureates Lecture on residual learning. Efficient ML and GPUs How are Microchips Made? – This YouTube video by Branch Education is one of the best free educational videos on the internet, regardless of subject, but also, it's the best video on understanding microchips. CUDA – My L8 and L9 FAANG coworkers acquired their CUDA knowledge from this series of lectures. TinyML and Efficient Deep Learning Computing – 2023 lectures on efficient ML techniques online. Chip War – Chip War is a bestselling book published in 2022 about microchip technology whose beginning chapters on the invention of the microchip actually explain CPUs very well

Have You Used AI Tools for Your Research? Which Ones Are Your Favorite and Why?

Over a decade ago, I wrote two articles: "A B\ginner’s Guide to Computer Science Research" and "How to Start a Research Work in Computer Science"*. These articles were widely used in universities worldwide to help students and early-career researchers navigate academic research in Computer Science (CS). Fast forward to 2025, the research landscape has evolved significantly, especially in AI and CS, with the advent of AI-powered research tools, open-access repositories, and real-time collaboration platforms. These tools have made research more accessible, enabling students and professionals to work more efficiently while focusing on real innovation. I recently published an updated article in The Times of India, presenting an Eight-Step Approach to Research framework designed for modern AI and CS research. This framework integrates AI-powered literature review tools, reference management systems, open science platforms, and collaborative research methods to enhance the research workflow. 🚀 Would love to hear from the ML research community: 1️⃣ Have you used any AI-powered tools or automation techniques in your research? Which ones do you find most useful? 2️⃣ Do you have recommendations for other AI tools that weren’t covered in the article but could benefit researchers? 3️⃣ How do you think AI will shape the future of academic research and discovery? 📖 Read the article here: How to Start Research in Computer Science & AI in 2025 – An Updated Framework Block Diagram of “Eight-Step Approach to Research” in 2025 Let’s discuss! What are your go-to tools for making research more efficient in 2025?

Watched 8 hours of MrBeast's content. Here are 7 psychological strategies he's used to get 34 billion views

MrBeast can fill giant stadiums and launch 8-figure candy companies on demand. He’s unbelievably popular. Recently, I listened to the brilliant marketer Phill Agnew (from The Nudge podcast) being interviewed on the Creator Science podcast. The episode focused on how MrBeast’s near-academic understanding of audience psychology is the key to his success. Better than anyone, MrBeast knows how to get you: \- Click on his content (increase his click-through rate) \- Get you to stick around (increase his retention rate) He gets you to click by using irresistible thumbnails and headlines. I watched 8 hours of his content. To build upon Phil Agnew’s work, I made a list of 7 psychological effects and biases he’s consistently used to write headlines that get clicked into oblivion. Even the most aggressively “anti-clickbait” purists out there would benefit from learning the psychology of why people choose to click on some content over others. Ultimately, if you don’t get the click, it really doesn’t matter how good your content is. Novelty Effect MrBeast Headline: “I Put 100 Million Orbeez In My Friend's Backyard” MrBeast often presents something so out of the ordinary that they have no choice but to click and find out more. That’s the “novelty effect” at play. Our brain’s reward system is engaged when we encounter something new. You’ll notice that the headline examples you see in this list are extreme. MrBeast takes things to the extreme. You don’t have to. Here’s your takeaway: Consider breaking the reader/viewer’s scrolling pattern by adding some novelty to your headlines. How? Here are two ways: Find the unique angle in your content Find an unusual character in your content Examples: “How Moonlight Walks Skyrocketed My Productivity”. “Meet the Artist Who Paints With Wine and Chocolate.” Headlines like these catch the eye without requiring 100 million Orbeez. Costly Signaling MrBeast Headline: "Last To Leave $800,000 Island Keeps It" Here’s the 3-step click-through process at play here: MrBeast lets you know he’s invested a very significant amount of time and money into his content. This signals to whoever reads the headline that it's probably valuable and worth their time. They click to find out more. Costly signaling is all amount showcasing what you’ve invested into the content. The higher the stakes, the more valuable the content will seem. In this example, the $800,000 island he’s giving away just screams “This is worth your time!” Again, they don’t need to be this extreme. Here are two examples with a little more subtlety: “I built a full-scale botanical garden in my backyard”. “I used only vintage cookware from the 1800s for a week”. Not too extreme, but not too subtle either. Numerical Precision MrBeast knows that using precise numbers in headlines just work. Almost all of his most popular videos use headlines that contain a specific number. “Going Through The Same Drive Thru 1,000 Times" “$456,000 Squid Game In Real Life!” Yes, these headlines also use costly signaling. But there’s more to it than that. Precise numbers are tangible. They catch our eye, pique our curiosity, and add a sense of authenticity. “The concreteness effect”: Specific, concrete information is more likely to be remembered than abstract, intangible information. “I went through the same drive thru 1000 times” is more impactful than “I went through the same drive thru countless times”. Contrast MrBeast Headline: "$1 vs $1,000,000 Hotel Room!" Our brains are drawn to stark contrasts and MrBeast knows it. His headlines often pit two extremes against each other. It instantly creates a mental image of both scenarios. You’re not just curious about what a $1,000,000 hotel room looks like. You’re also wondering how it could possibly compare to a $1 room. Was the difference wildly significant? Was it actually not as significant as you’d think? It increases the audience’s \curiosity gap\ enough to get them to click and find out more. Here are a few ways you could use contrast in your headlines effectively: Transformational Content: "From $200 to a $100M Empire - How A Small Town Accountant Took On Silicon Valley" Here you’re contrasting different states or conditions of a single subject. Transformation stories and before-and-after scenarios. You’ve got the added benefit of people being drawn to aspirational/inspirational stories. Direct Comparison “Local Diner Vs Gourmet Bistro - Where Does The Best Comfort Food Lie?” Nostalgia MrBeast Headline: "I Built Willy Wonka's Chocolate Factory!" Nostalgia is a longing for the past. It’s often triggered by sensory stimuli - smells, songs, images, etc. It can feel comforting and positive, but sometimes bittersweet. Nostalgia can provide emotional comfort, identity reinforcement, and even social connection. People are drawn to it and MrBeast has it down to a tee. He created a fantasy world most people on this planet came across at some point in their childhood. While the headline does play on costly signaling here as well, nostalgia does help to clinch the click and get the view. Subtle examples of nostalgia at play: “How this \[old school cartoon\] is shaping new age animation”. “\[Your favorite childhood books\] are getting major movie deals”. Morbid Curiosity MrBeast Headline: "Surviving 24 Hours Straight In The Bermuda Triangle" People are drawn to the macabre and the dangerous. Morbid curiosity explains why you’re drawn to situations that are disturbing, frightening, or gruesome. It’s that tension between wanting to avoid harm and the irresistible desire to know about it. It’s a peculiar aspect of human psychology and viral content marketers take full advantage of it. The Bermuda Triangle is practically synonymous with danger. The headline suggests a pretty extreme encounter with it, so we click to find out more. FOMO And Urgency MrBeast Headline: "Last To Leave $800,000 Island Keeps It" “FOMO”: the worry that others may be having fulfilling experiences that you’re absent from. Marketers leverage FOMO to drive immediate action - clicking, subscribing, purchasing, etc. The action is driven by the notion that delay could result in missing out on an exciting opportunity or event. You could argue that MrBeast uses FOMO and urgency in all of his headlines. They work under the notion that a delay in clicking could result in missing out on an exciting opportunity or event. MrBeast’s time-sensitive challenge, exclusive opportunities, and high-stakes competitions all generate a sense of urgency. People feel compelled to watch immediately for fear of missing out on the outcome or being left behind in conversations about the content. Creators, writers, and marketers can tap into FOMO with their headlines without being so extreme. “The Hidden Parisian Cafe To Visit Before The Crowds Do” “How \[Tech Innovation\] Will Soon Change \[Industry\] For Good” (Yep, FOMO and urgency are primarily responsible for the proliferation of AI-related headlines these days). Why This All Matters If you don’t have content you need people to consume, it probably doesn’t! But if any aspect of your online business would benefit from people clicking on things more, it probably does. “Yes, because we all need more clickbait in this world - \eye-roll emoji\” - Disgruntled Redditor I never really understood this comment but I seem to get it pretty often. My stance is this: If the content delivers what the headline promises, it shouldn’t be labeled clickbait. I wouldn’t call MrBeast’s content clickbait. The fact is that linguistic techniques can be used to drive people to consume some content over others. You don’t need to take things to the extremes that MrBeast does to make use of his headline techniques. If content doesn’t get clicked, it won’t be read, viewed, or listened to - no matter how brilliant the content might be. While “clickbait” content isn’t a good thing, we can all learn a thing or two from how they generate attention in an increasingly noisy digital world.

Has anybody used AI calling agents for your business?

Has anybody used tools like synthflow to create a an assistant and call your clients? I created one for my business, and I tweaked it a little bit to not sound like a robot and so far is doing great but not perfect. It answers all questions and objections on point, but I'm still looking to make it more human even though it won't ever be "perfect." Are there any prompts that you guys are using? Like telling it to use certain Voice intonations? Has any of your clients hung up or found out it was an AI? I'm about to test this for my real estate business and any insight or tips are appreciated!

Starting a new consultancy focused on helping small companies become more digital with their recruitment practices.

I am based in the UK. Approaching 20 years' recruitment experience in agency and in house. I know what good looks like. Currently I am head of talent and have helped my company increase headcount by over 200% in 3 years in a very cost effective way. I am considering starting my own consultancy business focused on small companies who may have no in-house recruitment teams. The objective is to create the infrastructure for them to be able to grow and be self sufficient thus reducing agency spend and enabling them to become more digital. For example: Building online presence/careers page Implementing a new ATS Developing an EVP Introducing more data driven decision making Competitor mapping Standardising process Question banks Glassdoor elevation Streamlining ED&I Interview training Using AI practically GDPR The list goes on... Do you think there is an appetite for this sort of thing with companies less than 100? By digitilising the process, it will enhance compliance processes, save time and money.

What Are The AI Tools You Used For Your Startup Business?

I'm starting a new ecommerce brand with Shopify, but I don't have much budget, which is why I decided to go for SEO marketing and Facebook Ads for early stage promotion business. I'm limited to resources, and can't afford too much for copywriters or content creators, I learnt from a few more experienced sellers, and they recommend me to use AI for copywriting and AI Video Ads Creation, Any tools you will recommend? Your help is highly appreciated!

Has anyone here used AI tools for due diligence when buying a business?

I am considering to buy a small business and want to do the evaluation of the business by using a systematic process, to minimize the potential risk of failure. I’ve heard about using AI-powered due diligence tools to automate financial analysis and spot potential risks. I just want to know that if anyone has experience using such tools How these tools work in practice, and how do they compare to traditional methods? I’m trying to make sure I’m making the best decision without missing anything important. Any advice or experiences would be helpful!

Has anyone here used AI tools for due diligence when buying a business?

I am considering to buy a small business and want to do the evaluation of the business by using a systematic process, to minimize the potential risk of failure. I’ve heard about using AI-powered due diligence tools to automate financial analysis and spot potential risks. I just want to know that if anyone has experience using such tools How these tools work in practice, and how do they compare to traditional methods? I’m trying to make sure I’m making the best decision without missing anything important. Any advice or experiences would be helpful!

[D] Next big thing in IT is ML/AI. It used to be the Internet. Do you think this would make it harder for amateurs to start a business in IT or would be much the same?

The Internet changed the world and although web development is not an easy task, the Internet helped many young developers without a degree in computer science to make a fortune, for example, Mark Zuckerberg and Elon Musk. But ML/AI seems definitely harder to enter compared to web development. Frankly, I don't know much about ML/AI (and that's why I am asking you guys). But do you think starting a business with ML as a core product would be hard for an amateur several years later when ML starts to deliver the hype?

Most effective, and very latest AI and Automation based tools used in lead generation, prospecting and cold outreach on linked and email?

Top 3

Just Used AI to Create My First Video Ad for Automating Businesses—What Do You Think?

How Is AI Used in Business

AI can help teams and organizations analyze patterns from large data sets streamline processes improve decision making prevent fraud and maintain compliance among other benefits

How AI Is Used in Business

Artificial intelligence AI refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions

This AI powered logo generator is used by over 20 million startups

Fast and easy way to create your business logo with this powerful AI tool. Will you try it? -- FREE SHOPIFY TRIAL -- Build your business using a FREE trial of Shopify , one platform with all the ecommerce features you need to start, run, and grow your business. ► https://bit.ly/3C5Zf10 -- FREE SHOPIFY COURSE -- First Day to First Sale https://bit.ly/3MJg7iR #shorts

UI Automation and Selectors

The UI Automation and Selectors course provides a deep understanding of the different methods used while interacting with the User Interface of different applications like Excel, Word, CRM, Websites while building automation projects.

Learning How to Learn: Powerful mental tools to help you master tough subjects

This course gives you easy access to the invaluable learning techniques used by experts in art, music, literature, math, science, sports, and many other disciplines. We’ll learn about how the brain uses two very different learning modes and how it encapsulates (“chunks”) information. We’ll also cover illusions of learning, memory techniques, dealing with procrastination, and best practices shown by research to be most effective in helping you master tough subjects.

Introduction to Data Analytics

Ready to start a career in Data Analysis but don’t know where to begin? This course presents you with a gentle introduction to Data Analysis, the role of a Data Analyst, and the tools used in this job. You will learn about the skills and responsibilities of a data analyst and hear from several data experts sharing their tips & advice to start a career. This course will help you to differentiate between the roles of Data Analysts, Data Scientists, and Data Engineers.

Fundamentals of Machine Learning and Artificial Intelligence

In this course, you will learn about the foundations of machine learning (ML) and artificial intelligence (AI). You will explore the connections between AI, ML, deep learning, and the emerging field of generative artificial intelligence (generative AI), which has captured the attention of businesses and individuals alike. You will gain a solid understanding of foundational AI terms, laying the groundwork for a deeper dive into these concepts. Additionally, you will learn about a selection of Amazon Web Services (AWS) services that use AI and ML capabilities. You will gain practical insights into how these tools can be used to solve real-world problems and drive innovation across various industries.

Getting Started with Automation 360

Automation 360(tm) is the leading cloud-native end-to-end intelligent automation platform used by the world's top enterprises to automate business processes across systems and applications.

OMG - I'm a tech founder trying to promote my SAAS product and I'm like a deer in headlights!

I've been building a tool for agile project management for the past year or two and I think it is looking pretty good. I've got good feedback from agile leads and such and have adjusted the product accordingly and I think now it is solving the problem it is focused on. It isn't perfect technically and as I am a tech head and I love all the challenges of solving and building tricky software solutions it is very tempting to program and program and program. But I have to bite the bullet and get out of my comfort zone and get some customers! But I have no budget for marketing, and no acumen for it and I don't know where to start. I have researched forums, blogs, AI, etc. and there is a lot of advice, too much in fact. Every intro email or announcement text I write, I review it and rewrite it over and over as I am constantly wondering if it is too wordy, or doesn't focus on benefits, or whatever advice I read last. How do people just get on with it without doubting whether this wording is the most compelling, or the website design doesn't look clunky, or I'm not getting to the right people? The sales and marketing world is so much harder than coding, and at the same time much more squishy and ill defined :-) Can anyone out there relate, offer some advice, help?

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

Anyone finding that they just don't NEED to add more Employees anymore? (I will not promote)

A friend of mine who was looking for work asked me if we were hiring and I responded "You know, it's weird but all of our growth goals don't seem to map back to hiring people anymore." This isn't about the economy or growth goals. It's a really fascinating shift in focus and costs for startups. My gut reaction is that I HATE the idea of not creating more jobs. In my career I've hired thousands of people, and I've always prided myself on job creation. We just sold a company that employed 200 people last year, and I'm proud of the work we were able to create. What's interesting is that I simply don't feel like we NEED to like we used to. As we're looking at all of our growth goals, for the first time I'm not assigning FTEs to them. Nearly everything we're doing is actually reducing the need for more humans, not adding them - and we're not even trying to reduce the need. Obviously the timing of AI has had a major impact. Product - Our team is shipping more code than ever before, and even our designers who have never touched code are shipping final code. If we doubled the size of the team, it would make no difference (this is a big deal considering the historical cost here). Marketing - So many aspects of our marketing are getting automated and streamlined, to the point where even a single FTE can create a massive amount of reach across channels. Support - Our Success team is able to effectively respond to tickets in a fraction of the time, which essentially doubles their capacity without adding any more staff. Management - With less staff we need less managers, which are a big expense, but it also means reporting and decisions are more streamlined, which is a positive. But it also means those positions simply don't get created like they used to. I think this is a big deal for the younger startups because it translates into needing less capital (or none!) which provides for more ownership and agency. Clearly we still need some folks to build out the core team, but that's very different than a massive staffing line item. Anyone else here finding the same trend? Opposite? I don't have a strong opinion either way, but I'd love to hear how other Founders are processing this.

How I made a high tech salary in my first selling month

For over 7 years I worked as a full-stack developer, helping other companies bring their ideas to life. But one day, I thought “Why not try making my own dream come true?”. That’s when I decided to quit my job and start my own journey to becoming an entrepreneur. At first, it wasn’t easy. I didn’t make any money for months and had no idea where to start. I felt lost. Then, I decided to focus on something popular and trending. AI was everywhere, and ChatGPT was the most used AI platform. So I looked into it and I found the OpenAI community forum where people had been asking for features that weren’t being added. That gave me an idea. Why not build those features myself? I created a Chrome extension and I worked on some of the most requested features, like: Downloading the advanced voice mode and messages as MP3 Adding folders to organize chats Saving and reusing prompts Pinning important chats Exporting chats to TXT/JSON files Deleting or archiving multiple chats at once Making chat history searches faster and better It took me about a week to build the first version, and when I published it, the response was incredible. People loved it! Some even said things like, “You’re a lifesaver!” That’s when I realized I had something that could not only help people but also turn into a real business. I kept the first version free to see how people would respond. Many users have been downloading my extension, which prompted Chrome to review it to determine if it qualified for the featured badge. I received the badge, and it has significantly boosted traffic to my extension ever since. After all the positive feedback, I launched a paid version one month ago. A few minutes after publishing it, I made my first sale! That moment was so exciting, and it motivated me to keep going. I already have over 4,000 users and have made more than $4,500 in my first selling month. I’ve decided to release 1-2 new features every month to keep improving the extension based on what users ask for. I also created the same extension for Firefox and Edge users because many people have been asking for it! I also started a Reddit community, where I share updates, sales, discount codes, and ideas for new features. It’s been awesome to connect with users directly and get their feedback. Additionally, I’ve started working on another extension for Claude, which I’m hoping will be as successful as this one. My message to you is this: never give up on your dreams. It might feel impossible at first, but with patience, hard work, and some creativity, you can make it happen. I hope this inspires you to go after what you want. Good luck to all of us!

Zero To One [Book Review]

If you don't feel like reading - check out the video here ##Introduction The more I read into Peter Thiel's background, the more ridiculous it seems.. He’s been involved in controversies over: Racism, Sexism, and, [Radical Right wing libertarianism.] (https://www.bloomberg.com/news/articles/2016-07-21/the-strange-politics-of-peter-thiel-trump-s-most-unlikely-supporter) He’s built a tech company that helps the NSA spy on the world. He supported Donald Trumps presidential campaign. He’s funding research on immortality And to top it off, he helped bankrupt online media company and blog network Gawker by funding Hulk Hogan’s sex tape lawsuit - after a report of his rumoured Homosexuality rattled his chain… Zero to One clearly reflects his unique attitude and doesn't pull any punches with a genuinely interesting point of view, that has clearly worked in the past, to the tune of almost 3 billion USD. But at times, his infatuation with the All American attitude is a little much…and, quite frankly, he’s not the kind of guy I could sit and have a pint with…without grinding my teeth anyway. The content is adapted from Blake Masters' lecture notes from Thiel's 2012 Stanford Course. This definitely helped keep the book concise and fast paced, at least compared to other books I’ve reviewed. The type of content is also quite varied, with a good spread from completely abstract theories — like the Technology vs. Globalisation concept, where the book get's it's title — to practical examples such as the analysis of personalities in chapter 14, "The Founders Paradox" covering Elvis Presley, Sean Parker, Lady Gaga and Bill Gates to name a few. ###Pros Monopolies To most people a monopoly is a negative thing. But while perfect competition can drive down costs and benefit the consumer - competition is bad for business. In fact, in Thiel's opinion, every startup should aim to be a monopoly or, as he puts it: Monopoly is the condition of every successful business. I like his honesty about it. While I’m not sure about the morality of encouraging monopolies at a large scale, I can see the benefit of thinking that way when developing a startup. When you're small, you can’t afford to compete. The best way to avoid competition is to build something nobody can compete with. The concept is summed up nicely at the end of chapter 3: Tolstoy opens Anna Karenina by observing: ‘All happy families are alike; each unhappy family is unhappy in its own way.’ Business is the opposite. All happy companies are different: each one earns a monopoly by solving a unique problem. All failed companies are the same: they failed to escape competition. Pareto The Pareto Law, which you might remember as the 80/20 rule in Tim Ferris’ The Four Hour Work Week, is often used synonymously with the power law of distribution, and shows up everywhere. Thiel refers to it in his section on The Power Law of Venture Capital. If Tim Ferris recommends identifying and removing the 20% of things that take 80% of your effort - Thiel recommends finding the 20% of investments that make 80% of your return. Anything else is a waste. Soberingly, he also suggests that the Pareto Law means: ...you should not necessarily start your own company, even if you are extraordinarily talented. But to me this seems more like a venture capitalists problem, than an entrepreneurs problem - Personally, I believe there’s far more benefit in starting up your own company that purely profit. ###Cons Man and machine? Content-wise, there is very little to dislike in this book. As long as you accept that the book is written specifically for startups - where anything short of exponential growth is considered a failure - it’s exceptionally on point. However, there are a couple sections dotted throughout the book where opinion and wild speculation began to creep in. Chapter 12 is a good example of this entitled: Man and Machine. It’s a short chapter, 12 pages in total, and Thiel essentially preaches and speculates about the impact of better technology and strong AI. I like to dog ear pages with interesting or useful content so I can come back later, but this entire chapter remains untouched. America, fuck yeah! It would be really difficult for a personality as pungent as Theil's to go entirely unnoticed in a book like this, and indeed it breaks through every now and then. I only had a feint idea of Thiel's personality before I read the book, but having read up on his background, I’m actually surprised the book achieves such a neutral, if pragmatic, tone. Pretty early on in the book however, we are introduced to Thiel's concept of Economic Optimism and quite frankly the whole of chapter 6 should have been printed on star spangled, red white and blue pages. I’m not necessarily against the egotistic American spirit but when Thiel writes, in relation to European Pessimism: the US treasury prints ‘in god we trust’ on the dollar; the ECB might as well print ‘kick the can down the road’ on the euro I can smell the bacon double cheese burgers, with those tiny little American flags from here. Ooh Rah! ###TL;DR (a.k.a: Conclusion) Overall, however, I really did enjoy this book and I can see myself coming back to it. Peter Thiel IS controversial, but he has also been undeniably successful with a career punctuated by bold business decisions. The ideas in the book reflect this mind set well. Yes, he backed Trump, be he also (sadly) backed the winner.

For anyone working on LLM / AI startups

My company (which I will not promote) wrote this blog post in compliance with rule #7 :) Introduction to fine-tuning Large Language Models, or LLMs, have become commonplace in the tech world. The number of applications that LLMs are revolutionizing is multiplying by the day — extraction use cases, chatbots, tools for creatives and engineers. In spite of this, at its core, the LLM is a multi-purpose neural network, dozens of layers deep, designed to simply predict one word after the next. It predicts words by performing billions of matrix multiplication steps based on so-called parameter weights, which are discovered during the model training process. Almost all open-source, open-weight models are trained on a massive amount of text from every conceivable genre and topic. How, then, do researchers and engineers create novel specialized applications? The answer is fine-tuning. In this post, we will demystify the process of fine-tuning and discuss the tradeoffs of other approaches to customizing an LLM. The history of fine-tuning In the ancient days of LLMs, by which we mean five years ago, the primary approaches to customizing an LLM was identical to the approaches to customizing any other deep learning model. A machine learning engineer would have two options: Retrain the entire LLM. This would mean discarding the trained weights and instead only using the open source model’s architecture to train it on a specialized dataset. As long as the amount and diversity of the specialized data is comparable to what the original model was trained on, this can be the ideal method of customizing a model. However, of course, this is a massive waste of resources due to the computational power required and the difficulty of collecting such a massive dataset. Even if an organization could provision enough GPUs, the cost of training modern-day models could cost up to $190 million. Retrain the last few layers of the LLM while keeping the rest of the weights frozen. This is a more efficient method in terms of time and computational power required because it significantly cuts down the number of parameters that need to be trained. However, for most tasks, this leads to subpar quality. Of course, almost everyone chooses to retrain the last few layers. And where there is only one option, the research community saw an opportunity to step in. Soon, the LLM space saw an enormous amount of activity in fine-tuning, which leads us to today. Modern approaches to fine-tuning Most fine-tuning approaches today are parameter-efficient. Deep neural networks are composed of matrices and vectors (generally called tensors), which are at their core arrays of floating point numbers. By training a small subset of these tensors, while the rest of the LLM’s weights are kept frozen, practitioners achieve good enough results without having to retrain the entire model. Generally, this method requires at least a hundred or so handcrafted examples of input-output pairs for fine-tuning. This is called supervised learning. The modern fine-tuning landscape involves an unsupervised learning step afterwards. Given a set of inputs, a practitioner gathers the various possible outputs from the LLM and casts votes among them. This preference data is then used to further train the LLM’s weights. Usually, this approach is used for LLM alignment and safety, which defends the application from malicious uses, outputs embarrassing to the organization, and prompt injection attacks. Fine-tuning’s relationship to prompt engineering A natural question arises: why fine-tune instead of crafting a well-considered system prompt? Wouldn’t that be easier and more efficient? The answer is no, it wouldn’t. Here’s why: Advanced techniques make prompt engineering obsolete: \[redacted\]'s product uses soft-prompting and other techniques to train the input layer itself. This obviates the need for prompt engineering entirely, which lets organizations avoid the time-consuming trial-and-error process to get the prompt just right. Prompt engineering has been a stopgap measure in the early days of LLM applications to convey the practitioner’s intent to the LLM. It is not the long-term solution for LLM application development. The system prompt is precious: the limited budget for system prompt length is better used for up-to-date information, e.g., Retrieval-Augmented Generation (RAG). Even as context windows increase in size with each new open-source model, the system prompt is the least efficient place to provide the LLM model with verbose instructions and examples. The longer the prompt, the slower the application: an LLM must attend to the entire system prompt for each token generated. This pain becomes more acute in the chatbot case, where the length of the conversation so far is also counted toward the system context. The longer the conversation, and the longer your beautifully-crafted system prompt, the slower the bot becomes. Even in cases where the model allows for system prompts that are millions of tokens long, doubling the size of the context will quadruple the latency. This means adding a few hundred words to the system prompt may result in several seconds of additional latency in production, making a chatbot impossible to use. Edge case handling: the number of edge cases that the system prompt would need to consider and emphasize to the LLM is too large. The instructions would have to be too nuanced and long to cover them all. However, fine-tuning on a dataset that considers these edge cases would be more straightforward. Do I need to fine-tune the LLM in my production application? Every LLM application in production must be fine-tuned often, not just once at the beginning. Why fine-tune? The world in which the application exists is constantly evolving. New prompt injection attacks are being discovered every day, new ways of embarrassing a chatbot are emerging constantly. This data can be used to further train an LLM model, which protects the application from new failure modes and reputational risk. Like any software, LLM models are constantly improving. Smarter and faster models are open-sourced all the time. For a new model to get deployed to production, it must first be finetuned on the specific dataset of the organization building the application. Fine-tuning does not add latency to LLM applications. Rather than a solution that sits in the middle of the LLM and the rest of the application, fine-tuning leverages the power of the LLM itself to increase the quality of the output. In fact, fine-tuning allows for shorter system prompts, which speeds up the average response generation time.

160 of Y Combinators 229 Startup Cohort are AI Startups with and 75% of the Cohort has 0 revenue

Y Combinator (YC), one of the most prestigious startup accelerators in the world, has just unveiled its latest batch of innovative startups, providing key insights into what the future might hold. Y Combinators Summer 2023 Batch In a recent post by Garry Tan, YC's president, Tan offers a nostalgic look back at his first YC Demo Day in 2008, where he, as a budding entrepreneur, pitched his startup. Now, fifteen years later, he's at the helm, proudly launching the 37th Demo Day, this time for the Summer 2023 batch. Tan proudly declares this batch as one of YC's most impressive yet, emphasizing the deep technical talent of the participants. From a staggering pool of over 24,000 applications, only 229 startups were chosen, making this one of the most competitive batches to date. This batch marks a number of firsts and solidifies several rising trends within the startups landscape. 75% of these companies began their YC journey with zero revenue, and 81% hadn't raised any funding before joining the accelerator. YC's decision to focus on early-stage startups this round signals their commitment to nurturing raw, untapped potential. A Return to Face-to-Face Interaction After three years, YC has brought back the in-person Demo Day format, allowing startups, investors, and mentors to connect directly. While the virtual format has its merits, there's an unmistakable magic in the YC Demo Day room, filled with anticipation, hope, and innovation. AI Takes Center Stage Artificial Intelligence is the standout sector in the Summer 2023 batch. With recent advancements making waves across various industries, there's arguably no better time to launch an AI-focused startup, and no better platform than YC to foster its growth. This signals a clear trend in the startup investing and venture capital space: AI is just getting started. Of the entire Summer 2023 batch, 160 out of the entire 229 Summer 2023 batch that are utilizing or implementing artificial intelligence in some capacity. This means over 2 out of every 3 startups accepted is focused on artificial intelligence in some capacity. Some of the startups include: Quill AI: Automating the job of a financial analyst Fiber AI: Automating prospecting and outbound marketing Reworkd AI: Open Source Zapier of AI Agents Watto AI: AI-powered McKinsey-quality reports in seconds Agentive: AI-powered auditing platform Humanlike: Replace your call center with voice bots that sound human Greenlite: AI compliance team for fintech and banking atla: AI assistants to help in-house lawyers answer legal questions Studdy: An AI Match tutor Glade: League of Legends with AI-generated maps and gameplay and literally over 100 others. As you can see, there's a startup covering nearly every sector of AI in the new batch. YC By The Numbers YC continues to grow as a community. The accelerator now boasts over 10,000 founders spanning more than 4,500 startups. The success stories are impressive: over 350 startups valued at over $150 million and 90 valued at more than $1 billion. The unicorn creation rate of 5% is truly unparalleled in the industry. To cater to the ever-growing community, YC has added more full-time Group Partners than ever. This includes industry veterans such as Tom Blomfield, co-founder of billion-dollar startups GoCardless and Monzo, and YC alumni like Wayne Crosby (Zenter) and Emmett Shear (Twitch). YC Core Values YC's commitment to diversity is evident in the demographics of the S23 batch. They've also spotlighted the industries these startups operate in, with 70% in B2B SaaS/Enterprise, followed by fintech, healthcare, consumer, and proptech/industrials. Garry Tan emphasizes three core tenets for YC investors: to act ethically, to make decisions swiftly, and to commit long-term. He underlines the importance of the YC community, urging investors to provide valuable introductions and guidance to founders. The Road Ahead With YC's track record and the promise shown by the Summer 2023 batch, the future of the startup ecosystem looks promising. As always, YC remains at the forefront, championing innovation and shaping the next generation of global startups. Original Post: https://www.democratizing.finance/post/take-a-peek-into-the-future-with-y-combinators-finalized-summer-2023-batch

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies) (I will not promote)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. (I will not promote) About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

So, you want to be a CEO?

I used to post here occasionally with business advice. But it turns out most of you in this sub have a dream, but seemingly no execution. You want to be rich sure, but without understanding what it takes to be a founder, run a startup, create a team around an idea and a strategy, and push them to their limits without burning them out, to win in a market that's never heard of you - not to mention the pressures on your personal life. So, I'm going to post a new game called, "So, You Want to Be A CEO?" The game: Each week I will post a reasonably complex challenge that a startup founder has to overcome, between inception of the company until it goes bust or series A. You respond with your best course of action - that is, what would you do in the situation provided? YOU DON’T HAVE TO DO THE WORK! The rules: One response per person Your upvotes are your score for the week I will track them in the OP Scores are calculated on the Friday of that week You must answer the prompt completely, if you don't you lose half your points earned that week. ChatGPT is allowed, but it may not provide sufficient advice to win the game Prompt 1: "Boomerang" You are an HR executive turned entrepreneur. You have identified a significant issue: professionals over the age of 55 are struggling to re-enter the workforce and you also believe corporations are missing out on a wealth of institutional knowledge in retirement. You believe you can help solve this problem by creating Boomerang, a platform dedicated to empowering these individuals and corporate partners by connecting them with the best candidates aged 55 and older. Objective: Your goal is to validate your concept, develop a Minimum Viable Product (MVP), and balance your personal responsibilities while laying the foundation for Boomerang’s success. This Week's Key Challenges and Decisions: Market Research Challenge 1: You need to validate the market need for Boomerang. This involves understanding the pain points of older job seekers and potential employers. This will take 4 days (non-sequential) How do you get started? Developing an MVP Challenge 2: With limited resources, you need to create an MVP that effectively demonstrates Boomerang’s value. This will take 2 days. Can be combined with other challenges. How do you get started? Dealing with Personal Health Issues Challenge 3: Your doctor mentioned your bloodwork is irregular, but can't pinpoint the cause. They recommend you see a specialist before Friday. This will take 1 day. Give it a shot! There's no right answer, just answer what your plan to do and try to optimize the use of your time to the best of your ability. EDIT: Scoreboard (I realize now the top post generally gets the most upvotes, so I may change the points system): u/conscious_border3019 - 22 u/inBoulderForSummer - 4 u/that_whey-or-the-lee - 3 u/AgencySaas - 3 u/Gold-Ad-8211 - 2 u/93024662 - 2 u/DeusExBam - 2 u/njm19920 - 2 u/SilentEconomist9265 - 2 u/ai_servant - 2 u/Background-Term2759 - 2 u/Insane_squirrel - 2 u/kiss_thechef - 2 u/codeyman2 - 2 u/Xentoxus - 2 u/LongComplex4395 - 2

Joined an AI Startup with Ex-ShipStation Team - Need Tips on Finding Early Users

Hey Reddit, My name’s Welcome (Yes, that’s really my name), and I’ve been in tech for most of my career, mostly at bigger companies with established brands and resources. But recently, I decided to join a small startup called BotDojo. It’s my first time being part of a small team, and it’s been a pretty eye-opening experience so far. But, like with anything new, I’ve hit a few bumps along the way, and I’m hoping you all might have some advice. A little backstory: BotDojo was started by some of the engineers who used to work together at ShipStation. After ShipStation sold, they spent some time experimenting with AI but kept running into the same problems—having to patch together tools, getting inconsistent results, handling data ingestion, and struggling to track performance. So, they decided to build a platform to help developers build, test, and deploy AI solutions. Since I came on board, my focus has been on finding early users, and it’s been a mixed bag of wins and frustrations. We’ve got a solid group of people using the free version (which is great), but only a few have upgraded to the paid plan so far (ranging from startups to large enterprises). The cool thing is that those who have become paying customers absolutely love the product. It’s just been hard getting more people to that point. We’ve tried a bunch of things: Attending industry events, doing cold email outreach, running social ads (the usual stuff). And while we’ve seen some interest, we’re running into a few challenges:   Learning curve: The software is really powerful, but it takes a week or two for users to really see what it can do. Without a dedicated sales team to walk them through it, it’s been tough getting people to stick around long enough to see the value. Standing out is hard: The AI space is super crowded right now. I think a lot of people see “AI tool” and assume it’s just like everything else out there (even though BotDojo has some awesome features that really set it apart).  Sign-ups, but limited engagement: We’re on a freemium model to make it easy for people to try it out, but that also means we get a lot of bots and people who sign up but don’t really dive in. So, I thought I’d reach out here and see if anyone has been through this early stage before. How did you manage to break through and find those first paying users who really saw the value in what you were building?  Are there any strategies, communities, or tactics that worked particularly well for you? And if you had to do it all over again, what would you focus on? I figure I’m not the only one trying to navigate these waters, so I’m hoping this can be a helpful thread for others too. Thanks so much for reading, and I’d be super grateful for any advice or insights you can share! 🙏

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

No revenue for 6 months, then signed $10k MRR in 2 weeks with a new strategy. Here’s what I changed.

This is my first company so I made A LOT of mistakes when starting out. I'll explain everything I did that worked so you don't have to waste your time either. For context, I built a SaaS tool that helps companies scale their new client outreach 10x (at human quality with AI) so they can secure more sales meetings. Pricing I started out pricing it way too low (1/10 as much as competitors) so that it'd be easier to get customers in the beginning. This is a HUGE mistake and wasted me a bunch of time. First, this low pricing meant that I was unable to pay for the tools I needed to make sure my product could be great. I was forced to use low-quality databases, AI models, sending infrastructure -- you name it. Second, my customers were less invested in the product, and I received less input from them to make the product better. None ended up converting from my free trial because my product sucked, and I couldn't even get good feedback from them. I decided to price my product much higher, which allowed me to use best-in class tools to make my product actually work well. Outreach Approach The only issue is that it's a lot harder to get people to pay $500/month than $50/month. I watched every single video on the internet about cold email for getting B2B clients and built up an outbound MACHINE for sending thousands of emails a day. I tried all the top recommended sales email formats and tricks (intro, painpoint, testimonial, CTA, etc). Nothing. I could send 1k emails and get a few out of office responses and a handful of 'F off' responses. I felt bad and decided I couldn't just spam the entire world and expect to make any progress. I decided I needed to take a step back and learn from people who'd succeeded before in sales. I started manually emailing CEOs/founders that fit my customer profile with personal messages asking for feedback on my product -- not even trying to sell them anything. Suddenly I was getting 4-6 meetings a day and just trying to learn from them (turns out people love helping others). And without even prompting, many of them said 'hey, I actually could use this for my own sales' and asked how they could start trying it out. That week I signed 5 clients between $500-$4k/month (depending how many contacts they want to reach). I then taught my product to do outreach the same way I did that worked (include company signals, make sure the person is a great match with web research, and DONT TALK SALESY). Now, 6 of my first 10 clients (still figuring out who it works for, lol) have converted from the free trial and successfully used it to book sales meetings. I'm definitely still learning, but this one change in my sales approach changed everything for me, so I wanted to share. If anyone has any other tips/advice that changed their business's sales, would love to hear!

Getting datasets to train AI to find a business opportunity and develop growth strategy

Listened to a podcast about training AI on competitive, consumer and market datasets to find the right segments for business opportunities. One example they used was feeding it case studies of companies that have become unicorns - building out their marketing and sales strategies so the AI can find 'rules'. I'm launching a telehealth clinic but I want to develop the optimal strategy for the right first customer segment, how we evolve as a platform (e.g. become more like gymshark or more health orientated) and what the marketing strategy should be. Therefore, I need a bunch of datasets such as consumer demographics and awareness, competitive offering and performance and growth lessons from benchmark companies and their strategies. How could I find such data sets? How could I put this together? Is there a scrappy version I could put together through scraping? I'm wary of feeding it shit data and getting shit back so would love some guidance.

For the Herd-Investor(Formerly Me)

Hey guys. my friend and I developed a model that looks over SEC filings and instead of just summarizing what they say like the existing “AI” solutions do(which are really just read-write programs), it infers and reads between the lines and analyzes what type of strategy the company is using(revenue recognition timing, the company's history,etc.) and many other factors. We used a different approach. Instead of basically making a GPT wrapper, we trained it from scratch based on not only summarizing filings but inferring on key information that is glossed over a lot. We plan to scale this into a model that accounts for not only filings, but recent news, public sentiment, and other factors. And instead of people having to upload files to get analyzed, we plan to automatically aggregate files on all public companies on the US markets and train the model on those to provide a one- stop shop financial search engine platform for retail investors to access digestable financial information(like an AlphaSense but for retail investors) because right now, the average retail investor has to access on average 5 services to get this info and then has to interpret the info as well. Obviously, the retail investor these days is also tied to a sense of community so plan to implement a moderated almost newletter like platform where verified creators can publish posts regarding their interests to further serve the retail investor. The gist is basically simplifying high-level finance to the point where the beginner investor can understand while preserving the technical value. Do you guys have any extra thoughts on this? I am trying to ask if you guys would actually pay for a service like this, and what it should additionally offer to make it more valuable to the average retail investor. Thanks again!

Content aggregation that acts as a middleman for content discovery via third-party marketplace & revenue sharing (i will not promote but I'm looking for fellow researchers)

High level I’m considering a content aggregation business model, but one that acts as an open marketplace where third party devs and where world class data scientists compete to build the best recommenders for different use cases. (E.g. the incentives can be ad revenue sharing or subscription based for niche professional markets.) The idea is to facilitate more bottom up innovation from third party data scientists. The platform itself just acts as the middleman. (Also something that strips out original ads and makes it easy to skip paid sponsorship sections would be great.)  I’ve seen startups building web crawlers and content aggregation systems for other AI startups. My proposal is better in the sense that third party devs are instead responsible for implementing whatever questionable hacks are necessarily to scrape platforms that don’t necessarily want to be scraped.  Personally, I’m more concerned about getting the right information than ever before, to this end I can’t rely on platform specific recommenders. The solution is more bottom up innovation in content promotion. More generally, if you’re also concerned about consuming game changing information that’s too easily missed: we need a platform that incentivizes bottom up innovation of content promotion. What we need is a platform that functions like a marketplace where third party devs and where world class data scientists compete to build the best recommenders for different use cases. Here’s some elevator pitches I’m considering:  Did you know that the magic behind YouTube is its recommendation engine? Now, imagine an open platform where independent engines compete to deliver the most personalized content feed—from news to local events—directly to you. Interested in rethinking how we find content? “In today’s fragmented digital landscape, a single platform no longer holds sway over content discovery. The Network Effect is dead: audiences are more mobile than ever; and big tech killed it. In such a fragmented landscape we’re building a bottom-up, decentralized marketplace for recommendation engines—a solution that taps into diverse revenue streams through subscriptions, ad revenue, and affiliate partnerships. Invest in the future of personalized content aggregation.” “Are you a developer passionate about algorithms and content discovery? Our open marketplace lets you build and monetize your own recommendation engine, competing to deliver the most engaging, personalized feeds. Join a revolution where your innovation can directly shape how the world finds content.” “Are you tired of being told what to watch or read by one mysterious algorithm? Imagine taking control—choosing from a marketplace of smart recommendation engines that curate content just for you. It’s a revolution in content discovery where you hold the power.” (As a Utahn this one is interesting because even mormons are talking about the dangers of “doom scrolling” though it’s seldom discussed in society at large.) As far as simple hooks I’m considering:  One platform to rule them all and in the darkness bind them.  Choose how you discover—content recommenders that work for you.  The area where recommender engines battle to win your feed. Request I would love to start prototyping this idea and see what else I can uncover from such preliminary research. But I want to get a couple other likeminded individuals onboard.  I'm the best when it comes to iOS/macOS development, but there's tons of backend work that needs to be done which I wouldn’t have the time for if i'm focused on the native clients. Who am I 'ideally' looking for?  I’ve heard of weird stats to the effect that if you scale up a population to billions of people, the number of life overlaps starts skyrocketing. Not just physical lookalikes, but people with eerily similar life paths, personalities, habits, and even thoughts — without ever knowing each other. Where are my clones? Such is whom I’m looking for in an ideal world.  Take a hunch  People nowadays have no concept of going out on a limb, taking a ‘hunch’, and backing their instincts. Everything has to be calculated, proven, and guaranteed before they make a move. In contrast consider the success of the Chinese DeepSeek project: According to Asianometry’s YouTube video on DeepSeek, their “memory-saving multi-head latent architecture” (whatever that means, just quoting the name) came about from a researchers ‘hunch’, which the company bet big on and the result was drastically improved performance on low end hardware…  Here in the west the idea of betting on a hunch is inconceivable. We have no balls to chase long term insights. My own instincts when it comes to software is such because I’ve wasted too much of my life on small scale projects. All I’m trying to do is attempt a more scaled up experiment based on some hunches with me and a few other likeminded individuals.  Just as the early oil prospectors didn’t have precise maps—just intuition and test drills. They had to drill, analyze the pressure, and adjust. The best oil fields weren’t found by foresight alone, but by adaptive exploration. The startup space itself is liken to the first prospectors who got the gold nuggets lying in the riverbed. In such an environment moving first has its advantages but nowadays I wish I could have all those shitty ‘engineers’ sent to their maker.  Today the reality is such that you’ve got to dig deep—where vast stores of wealth can be found—or go home, and those who dig into the depths cannot use mere forethought, for what lies beneath cannot be seen by the mind’s eye.  I will not promote but I'm looking for fellow research oriented minds.

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I'm technical looking for non-technical co-founder with a good idea and good background.

Hi all! So things have fell through with my co-founder and I have decided to start looking for new opportunities. I'm a senior software engineer looking to work with someone who already has an idea. I've primarily worked on fintech during my career.  I've build payment systems, fraud prevention mechanisms, and arrear collections infrastructure. The products I've had a key role in developing have helped UK governments and banks save millions of pounds. I've built beautiful front end systems (web, android, and IOS) that are being used by thousands of people and have developed back end infrastructure that is currently servicing millions of requests per day. I'm open to working in most domains if the idea and the founder behind are great. I'm looking for a co-founder who is ideally an expert in there space and has a good idea. I'll try to get back to everyone who pings me. All the best!

Technical Co-Founder Seeking Commercial/Marketing Partner for Micro SaaS Projects

Hi everyone, I’m looking for a commercial or marketing co-founder to join me in developing some Micro SaaS (MSaaS) apps. Here’s a bit about where I’m coming from and what I’m hoping to find: About Me: I’m a full-stack developer with over 15 years of experience, including some work in AI. I’m currently working part-time, which gives me the time to focus on developing MVPs quickly. I’m passionate about creating SaaS solutions and would love to find someone who can help bring these ideas to life. Based in french alps. What I’m Looking For: Role: Non-Technical Co-Founder (Commercial/Marketing) Location: Remote Equity: 50% co-founder stake What I’m Hoping You’ll Bring: Experience: Background in business development, marketing, or similar fields. Vision: An eye for potential in new SaaS ideas and a drive to help make them successful. Commitment: Enthusiasm for building and growing a business together. What’s In It For You: Revenue Potential: Share in the financial rewards of successful products with a 50% equity stake, giving you a direct share of the profits. Fast ROI: Benefit from rapid MVP development, which allows for quicker validation and faster revenue generation. Dynamic Approach: We move quickly—if an app doesn’t gain traction in a few weeks, we pivot to the next idea, keeping our efforts focused on what works. Financial Growth: As we iterate and scale, there are opportunities for significant financial upside based on the success of our products. Shared Success: Be an integral part of a partnership where both of us share equally in the risks and rewards, creating a strong incentive for mutual success. What’s In It For You: Partnership: Equal share in the business (50/50). Opportunity: Work on interesting MSaaS projects with room for creativity. Flexibility: A remote role that fits around your schedule. If you’re interested or would like to learn more, please reach out. I’d be thrilled to discuss how we might work together. Thank you for considering this!

Lessons from 139 YC AI startups (S23)

YC's Demo Day was last week, and with it comes another deluge of AI companies. A record-breaking 139 startups were in some way related to AI or ML - up from 112 in the last batch. Here are 5 of my biggest takeaways: AI is (still) eating the world. It's remarkable how diverse the industries are - over two dozen verticals were represented, from materials science to social media to security. However, the top four categories were: AI Ops: Tooling and platforms to help companies deploy working AI models. We'll discuss more below, but AI Ops has become a huge category, primarily focused on LLMs and taming them for production use cases. Developer Tools: Apps, plugins, and SDKs making it easier to write code. There were plenty of examples of integrating third-party data, auto-generating code/tests, and working with agents/chatbots to build and debug code. Healthcare + Biotech: It seems like healthcare has a lot of room for automation, with companies working on note-taking, billing, training, and prescribing. And on the biotech side, there are some seriously cool companies building autonomous surgery robots and at-home cancer detection. Finance + Payments: Startups targeting banks, fintechs, and compliance departments. This was a wide range of companies, from automated collections to AI due diligence to "Copilot for bankers." Those four areas covered over half of the startups. The first two make sense: YC has always filtered for technical founders, and many are using AI to do what they know - improve the software developer workflow. But it's interesting to see healthcare and finance not far behind. Previously, I wrote: Large enterprises, healthcare, and government are not going to send sensitive data to OpenAI. This leaves a gap for startups to build on-premise, compliant \[LLMs\] for these verticals. And we're now seeing exactly that - LLMs focused on healthcare and finance and AI Ops companies targeting on-prem use cases. It also helps that one of the major selling points of generative AI right now is cost-cutting - an enticing use case for healthcare and finance. Copilots are king. In the last batch, a lot of startups positioned themselves as "ChatGPT for X," with a consumer focus. It seems the current trend, though, is "Copilot for X" - B2B AI assistants to help you do everything from KYC checks to corporate event planning to chip design to negotiate contracts. Nearly two dozen companies were working on some sort of artificial companion for businesses - and a couple for consumers. It's more evidence for the argument that AI will not outright replace workers - instead, existing workers will collaborate with AI to be more productive. And as AI becomes more mainstream, this trend of making specialized tools for specific industries or tasks will only grow. That being said - a Bing-style AI that lives in a sidebar and is only accessible via chat probably isn't the most useful form factor for AI. But until OpenAI, Microsoft, and Google change their approach (or until another company steps up), we'll probably see many more Copilots. AI Ops is becoming a key sector. "AI Ops" has been a term for only a few years. "LLM Ops" has existed for barely a year. And yet, so many companies are focused on training, fine-tuning, deploying, hosting, and post-processing LLMs it's quickly becoming a critical piece of the AI space. It's a vast industry that's sprung up seemingly overnight, and it was pretty interesting to see some of the problems being solved at the bleeding edge. For example: Adding context to language models with as few as ten samples. Pausing and moving training runs in real-time. Managing training data ownership and permissions. Faster vector databases. Fine-tuning models with synthetic data. But as much ~~hype~~ enthusiasm and opportunity as there might be, the size of the AI Ops space also shows how much work is needed to really productionalize LLMs and other models. There are still many open questions about reliability, privacy, observability, usability, and safety when it comes to using LLMs in the wild. Who owns the model? Does it matter? Nine months ago, anyone building an LLM company was doing one of three things: Training their own model from scratch. Fine-tuning a version of GPT-3. Building a wrapper around ChatGPT. Thanks to Meta, the open-source community, and the legions of competitors trying to catch up to OpenAI, there are now dozens of ways to integrate LLMs. However, I found it interesting how few B2B companies mentioned whether or not they trained their own model. If I had to guess, I'd say many are using ChatGPT or a fine-tuned version of Llama 2. But it raises an interesting question - if the AI provides value, does it matter if it's "just" ChatGPT behind the scenes? And once ChatGPT becomes fine-tuneable, when (if ever) will startups decide to ditch OpenAI and use their own model instead? "AI" isn't a silver bullet. At the end of the day, perhaps the biggest lesson is that "AI" isn't a magical cure-all - you still need to build a defensible company. At the beginning of the post-ChatGPT hype wave, it seemed like you just had to say "we're adding AI" to raise your next round or boost your stock price. But competition is extremely fierce. Even within this batch, there were multiple companies with nearly identical pitches, including: Solving customer support tickets. Negotiating sales contracts. Writing drafts of legal documents. Building no-code LLM workflows. On-prem LLM deployment. Automating trust and safety moderation. As it turns out, AI can be a competitive advantage, but it can't make up for a bad business. The most interesting (and likely valuable) companies are the ones that take boring industries and find non-obvious use cases for AI. In those cases, the key is having a team that can effectively distribute a product to users, with or without AI. Where we’re headed I'll be honest - 139 companies is a lot. In reviewing them all, there were points where it just felt completely overwhelming. But after taking a step back, seeing them all together paints an incredibly vivid picture of the current AI landscape: one that is diverse, rapidly evolving, and increasingly integrated into professional and personal tasks. These startups aren't just building AI for the sake of technology or academic research, but are trying to address real-world problems. Technology is always a double-edged sword - and some of the startups felt a little too dystopian for my taste - but I'm still hopeful about AI's ability to improve productivity and the human experience.

Is my idea + progress good enough to raise pre-seed round? CRM for construction niches. Non-tech founder.

Is my startup idea and progress good enough to raise a pre-seed round? It’s a CRM with meaningful AI integrations for specific type of B2B construction companies. I only want to continue at my current pace if it’s realistic to start raising within the next 2 weeks. At first, I thought it was fine because simple companies still get on Y-comb such as hammr and Relate CRM , but now I’m not sure. Would love to get the community’s thoughts on this. I’ve been working on this for about a week. &#x200B; Key Highlights (You can skip to longer section below) Product is CRM for B2B construction companies. The previous tech company I worked at used an in-house built CRM for their workflow, and I’m creating that solution and applying it to B2B construction companies that have similar workflows. No competitors I’ve found. I’m uniquely positioned to spearhead: B2B SaaS/tech sales + expertise in construction I’m a non-tech sales founder with experience in UI/UX. Will bring on CTO co-founder once I start raising as that would entice better talent Progress + Traction $400 MRR in pre-sales, can get to \~$800-1000 EOM Validated through customer interviews Created some Figma frames, product overview, user journeys, business plan Made a simple but meaningful AI tool that will be available to those that sign up for waitlist. Did this with GitHub + ChatGPT Landing page website going up this week followed by PPC campaign, email marketing, and outreach. My GF works in enterprise sales and she’ll help me generate more leads. &#x200B; Long Version Background B2B SaaS/Tech sales. I worked at enterprise company as an Account Executive where I worked with funded startups and their development, UI/UX, and Product management teams. I have a general knowledge in all these - my best being UI/UX design as I can work with Figma well Domain expertise: my family has had a construction company since I was young. I have a large network because of this. Problem At my previous company, we had a custom in-house built CRM for our workflow. It worked okay, despite being maintained by multiple engineers costing hundreds of thousands a year. I’m creating a CRM that solves that, and applying it to construction industries that can make use of it. I have a great network here which makes it easy for me get sales quickly. Vision Building this CRM for construction niche will allow us to generate MRR fast. We will be first movers in bringing meaningful AI tools to construction, which is generating significant interest. This gives us the opportunity to build the foundational technology that can be adapted to a wider audience such as my previous company and others - think researchers, consultants, etc. Traction + Current Progress (1 week) Validated idea through user interviews and pre-sales. Currently have $400 MRR in pre-sales. I expect $800-1000 in a month if I continue at my pace. This is from doing typical B2B sales. I’ve set up a CRM for this. Created product overview, user journeys, wireframes and some Figma frames, business plan Created a simple but meaningful AI tool for the niche which will be available to those that sign up for the waitlist. Created with GitHub + ChatGPT Completing landing page website this week. Will start PPC ads (I’m experienced in this) after that to generate sign-ups. I’ll also start email marketing from lists I’ve scraped. Team Solo-founder, will bring on CTO co-founder once I start raising funds. I have promising candidates, but feel that I need to raise funds to really entice a good co-founder. I’m uniquely positioned to head this product; B2B sales having worked with many CRMs + construction expertise and network. That said, I’ve never actually done anything that* impressive besides being an AE at a known enterprise techy company (but not FAANG level). &#x200B; I want to acknowledge that my progress might sound more impressive than it is - it's still just a CRM after all, and I'm non-technical. Should I keep going? Advice? I also have a great offer to lead sales at a profitable startup, but I could always do both if it was worth it. I’m feeling really uncertain for some reason :/ maybe it’s just burnout.

Looking for a non-technical co-founder (I will not promote)

Hey everyone, I've launched an AI networking agent designed to connect people based on specific prompts. You describe the type of person you're looking for, and it provides a relevant contact. This tool can be used for hiring, procuring services, selling services, and more. I'm currently seeking a highly motivated, high-energy non-technical co-founder to handle sales and marketing, conduct customer interviews to grow our user base. No experience is required, only a strong willingness to succeed. We're completely bootstrapped but plan to start fundraising after securing our first paying users. If you're interested, shoot me a DM. i will not promote

Startup founders, tell me what's the job you would like to get done in your startup but you are too busy to repeat or start it?

I've been focusing on LLM-based agent development for the past two years and am now building a related startup. I want to validate my startup ideas and would especially like to hear feedback from entrepreneurs. What are the repetitive tasks in your startup journey that need to be completed but you're too busy to handle or initiate? I can develop specialized intelligent agents to solve these issues for you. Whether it's workflow automation or more advanced agent AI applications, whatever problems you want to solve, I'm willing to try and help. For just a small fee (provided it's truly an important problem worth solving), I can customize solutions for you. Following the principle of "do things that don't scale," I'm more focused on helping entrepreneurs quickly and effectively address their pain points. Through this approach, we can explore together the practical value of AI agents in startup scenarios and gradually improve product functionality. Feel free to share any specific business scenarios or needs you have. Let's discuss how AI agents can truly help entrepreneurs improve their work efficiency.

So, you want to be a CEO?

I used to post here occasionally with business advice. But it turns out most of you in this sub have a dream, but seemingly no execution. You want to be rich sure, but without understanding what it takes to be a founder, run a startup, create a team around an idea and a strategy, and push them to their limits without burning them out, to win in a market that's never heard of you - not to mention the pressures on your personal life. So, I'm going to post a new game called, "So, You Want to Be A CEO?" The game: Each week I will post a reasonably complex challenge that a startup founder has to overcome, between inception of the company until it goes bust or series A. You respond with your best course of action - that is, what would you do in the situation provided? YOU DON’T HAVE TO DO THE WORK! The rules: One response per person Your upvotes are your score for the week I will track them in the OP Scores are calculated on the Friday of that week You must answer the prompt completely, if you don't you lose half your points earned that week. ChatGPT is allowed, but it may not provide sufficient advice to win the game Prompt 1: "Boomerang" You are an HR executive turned entrepreneur. You have identified a significant issue: professionals over the age of 55 are struggling to re-enter the workforce and you also believe corporations are missing out on a wealth of institutional knowledge in retirement. You believe you can help solve this problem by creating Boomerang, a platform dedicated to empowering these individuals and corporate partners by connecting them with the best candidates aged 55 and older. Objective: Your goal is to validate your concept, develop a Minimum Viable Product (MVP), and balance your personal responsibilities while laying the foundation for Boomerang’s success. This Week's Key Challenges and Decisions: Market Research Challenge 1: You need to validate the market need for Boomerang. This involves understanding the pain points of older job seekers and potential employers. This will take 4 days (non-sequential) How do you get started? Developing an MVP Challenge 2: With limited resources, you need to create an MVP that effectively demonstrates Boomerang’s value. This will take 2 days. Can be combined with other challenges. How do you get started? Dealing with Personal Health Issues Challenge 3: Your doctor mentioned your bloodwork is irregular, but can't pinpoint the cause. They recommend you see a specialist before Friday. This will take 1 day. Give it a shot! There's no right answer, just answer what your plan to do and try to optimize the use of your time to the best of your ability. EDIT: Scoreboard (I realize now the top post generally gets the most upvotes, so I may change the points system): u/conscious_border3019 - 22 u/inBoulderForSummer - 4 u/that_whey-or-the-lee - 3 u/AgencySaas - 3 u/Gold-Ad-8211 - 2 u/93024662 - 2 u/DeusExBam - 2 u/njm19920 - 2 u/SilentEconomist9265 - 2 u/ai_servant - 2 u/Background-Term2759 - 2 u/Insane_squirrel - 2 u/kiss_thechef - 2 u/codeyman2 - 2 u/Xentoxus - 2 u/LongComplex4395 - 2

Competing with much bigger companies that have lame products? How do I market and carve out a niche? (I will not promote)

I've been working on a product for the last few months that competes with CapCut, Adobe Premier, Veed, Descript, DaVinci Resolve, etc. Basically, it's a fancy video editor. (no link and I will not promote but just some background context) I'm very technical and started creating videos for TikTok but really wanted to take my game to the next level. My channel sort of blew up on me in the first month and I was able to get 2M views and 10k followers. My initial thinking was that I was going to use AI to make video editing fancy/faster and sort of have this as a "script" that I used personally. Basically, give myself a serious competitive advantage. However, it sort of spiraled out of control! What started off as a weekend project, turned into 2 weekends, which turned into about 2 months of continuous hacking. If I'm going to spend a significant amount of time on this, I might as well try to productize it and try to at least make enough money that I break even on my time. The thing I'm worried about, in the back of my mind, is that if I shop this, that my competitors, with their signifiant resources, could clone what I'm doing quickly. However, at the same time, why haven't they done so already? I mean maybe I have a better understanding of the market than they do because they don't actually use their products. I know that sounds like a bit of a cop out in a way but there are plenty of entrepreneurs who have started companies and crushed it just because they were heads down and focused. Another problem I face, is that I think VCs may not be super excited about this because it's B2C-ish and it's not in a super exciting space. Maybe you could say it's in the AI video space, and they're excited about AI video, but it's just an AI video editor, not fully creating AI videos from scratch like SORA. I think since I blew up my TikTok feed before, that I could do it again, and if I get 2M views, and I have a outro on my video, that I could start to convert some of these as customers. Especially, if I started to create videos for creators which is more focused on the target market. So without funding, can I really tackle these existing competitors? PS. "I will not promote" but I have to talk about this somewhat abstractly but I won't link to anything.

Why raise in 2025? - I will not promote

I will not promote Lately, I've been thinking about how AI tools are completely reshaping what it means to bootstrap a startup. It honestly feels like we're living through a golden age for entrepreneurs where you don't necessarily need venture capital to build something big or meaningful. At my company, we're a small team of just four people, bootstrapping our AI-focused startup. Thanks to AI-powered tools, we're able to keep our burn rate ridiculously low, quickly test new ideas, and scale our operations way faster than we ever expected. It’s honestly pretty incredible how accessible advanced technology has become, even compared to just a few years ago. Of course, bootstrapping definitely comes with its own share of headaches. For example, we've noticed that funded startups get significantly better access to cloud credits, advertising budgets, and enterprise-level tools. We do have access to some discounts and free resources, but it rarely compares to what funded startups enjoy. This can feel frustrating, especially when you know you're competing directly with businesses that have those extra advantages. Visibility is another major challenge we've noticed. Without big funding announcements or a well-connected investor backing us, getting attention from media or even early adopters can be tough. It's just harder to make a splash without someone else's endorsement. We've had to accept and work around creatively. That said, there's something genuinely empowering about staying bootstrapped, prioritizing profitability, and maintaining control over our vision. After speaking with several investors, we've become aware of how investors can significantly influence or even redirect the trajectory of a business. We've heard stories where investors gained enough leverage to replace the original founders or have killed perfectly profitable businesses that were not growing "fast enough", which certainly gave us pause. They can definitely be helpful but giving the control over the future of my business to someone else would definitely make me feel anxious. At this time, we simply don't feel raising external capital aligns with our current goals, but we're also aware that this could change in the future. For now, maintaining autonomy and staying close to our original vision remains a priority. I'm curious to hear from others here who've been through this. Have you successfully bootstrapped an AI a tech business? What obstacles did you encounter, and how did you overcome them? EDIT: To give you a bit of perspective, my company is a B2B SaaS in the finance industry based in Europe. We have received VC funding in the past but it was an exceptionally good deal and we don't plan to raise in the near future even-thought it may change if we see the need to help us scale. We have also raised a significant amount in soft funding. Right now, we are growing on our revenues, and we plan to continue this trajectory. Recently, one of our developers left, and although we are a small team, we noticed that it had little to no impact on our productivity.

We built a tool to help you find relevant grants. Would you pay for it?

Hi everyone, About a year ago, I asked you guys whether it would make sense to develop a tool to help entrepreneurs find relevant grants. Many of you provided incredibly valuable feedback, which we used to refine the concept. With this concept, we went through Techstars and finally launched a beta version of our grant scan tool last week! Along the way, we realized something interesting: when you ask a grant advisor which grants might be a great fit for you, they almost always recommend the ones they know well. This makes sense since most work on a success fee basis, and referring you to lesser-known grants (which take more time to write and have lower success rates) isn’t worth it for them. Plus, memorizing the details of 20,000+ grants is, understandably, pretty tough. Our platform uses AI to scan and analyze thousands of grants. It identifies the best matches, estimates your chances of success, and calculates how much time you might need for the application and reporting phases. We can then match you with a grant advisor with relevant expertise—whether to write the application for you or provide feedback on your draft. We’re considering launching both a free and a paid version. The free version would provide basic insights, while the paid version would include more comprehensive results, expert comments (such as explaining why certain grants are a good fit), and updates when new relevant grants become available. Both versions will allow you to connect with relevant experts. Would you pay for the paid version? And if so, which features should it include? Also, any general feedback is much appreciated! Thanks!

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

How I made a high tech salary in my first selling month

For over 7 years I worked as a full-stack developer, helping other companies bring their ideas to life. But one day, I thought “Why not try making my own dream come true?”. That’s when I decided to quit my job and start my own journey to becoming an entrepreneur. At first, it wasn’t easy. I didn’t make any money for months and had no idea where to start. I felt lost. Then, I decided to focus on something popular and trending. AI was everywhere, and ChatGPT was the most used AI platform. So I looked into it and I found the OpenAI community forum where people had been asking for features that weren’t being added. That gave me an idea. Why not build those features myself? I created a Chrome extension and I worked on some of the most requested features, like: Downloading the advanced voice mode and messages as MP3 Adding folders to organize chats Saving and reusing prompts Pinning important chats Exporting chats to TXT/JSON files Deleting or archiving multiple chats at once Making chat history searches faster and better It took me about a week to build the first version, and when I published it, the response was incredible. People loved it! Some even said things like, “You’re a lifesaver!” That’s when I realized I had something that could not only help people but also turn into a real business. I kept the first version free to see how people would respond. Many users have been downloading my extension, which prompted Chrome to review it to determine if it qualified for the featured badge. I received the badge, and it has significantly boosted traffic to my extension ever since. After all the positive feedback, I launched a paid version one month ago. A few minutes after publishing it, I made my first sale! That moment was so exciting, and it motivated me to keep going. I already have over 4,000 users and have made more than $4,500 in my first selling month. I’ve decided to release 1-2 new features every month to keep improving the extension based on what users ask for. I also created the same extension for Firefox and Edge users because many people have been asking for it! I also started a Reddit community, where I share updates, sales, discount codes, and ideas for new features. It’s been awesome to connect with users directly and get their feedback. Additionally, I’ve started working on another extension for Claude, which I’m hoping will be as successful as this one. My message to you is this: never give up on your dreams. It might feel impossible at first, but with patience, hard work, and some creativity, you can make it happen. I hope this inspires you to go after what you want. Good luck to all of us!

10y of product development, 2 bankruptcies, and 1 Exit — what next? [Extended Story]

10 years of obsessive pursuit from the bottom to impressive product-market fit and exit. Bootstrapping tech products as Software Developer and 3x Startup Founder (2 bankruptcies and 1 exit). Hi everyone, your motivation has inspired me to delve deeper into my story. So, as promised to some of you, I've expanded on it a bit more, along with my brief reflections. There are many founders, product creators, and proactive individuals, I’ve read many of your crazy stories and lessons so I decided to share mine and the lessons I learned from the bottom to impressive product-market fit and exit. I've spent almost the past 10 years building tech products as a Corporate Team Leader, Senior Software Developer, Online Course Creator, Programming Tutor, Head of Development/CTO, and 3x Startup Founder (2 bankruptcies, and 1 exit). And what next? good question... A brief summary of my journey: Chapter 1: Software Developer / Team Leader / Senior Software Developer I’ve always wanted to create products that win over users’ hearts, carry value, and influence users. Ever since my school days, I’ve loved the tech part of building digital products. At the beginning of school, I started hosting servers for games, blogs and internet forums, and other things that did not require much programming knowledge. My classmates and later even over 100 people played on servers that I hosted on my home PC. Later, as the only person in school, I passed the final exam in computer science. During my computer science studies, I started my first job as a software developer. It was crazy, I was spending 200–300 hours a month in the office attending also to daily classes. Yes, I didn’t have a life, but it truly was the fulfillment of my dreams. I was able to earn good money doing what I love, and I devoted fully myself to it. My key to effectively studying IT and growing my knowledge at rocket speed was learning day by day reading guides, building products to the portfolio, watching youtube channels and attending conferences, and even watching them online, even if I didn’t understand everything at the beginning. In one year we’ve been to every possible event within 400km. We were building healthcare products that were actually used in hospitals and medical facilities. It was a beautiful adventure and tons of knowledge I took from this place. That time I built my first product teams, hired many great people, and over the years became a senior developer and team leader. Even I convinced my study mates to apply to this company and we studied together and worked as well. Finally, there were 4 of us, when I left a friend of mine took over my position and still works there. If you’re reading this, I’m sending you a flood of love and appreciation. I joined as the 8th person, and after around 4 years, when I left hungry for change, there were already over 30 of us, now around 100. It was a good time, greetings to everyone. I finished my Master’s and Engineering degrees in Computer Science, and it was time for changes. Chapter 2: 1st time as a Co-founder — Marketplace In the meantime, there was also my first startup (a marketplace) with four of my friends. We all worked on the product, each of us spent thousands of hours, after hours, entire weekends… and I think finally over a year of work. As you might guess, we lacked the most important things: sales, marketing, and product-market fit. We thought users think like us. We all also worked commercially, so the work went very smoothly, but we didn’t know what we should do next with it… Finally, we didn’t have any customers, but you know what, I don’t regret it, a lot of learning things which I used many times later. The first attempts at validating the idea with the market and business activities. In the end, the product was Airbnb-sized. Landing pages, listings, user panels, customer panels, admin site, notifications, caches, queues, load balancing, and much more. We wanted to publish the fully ready product to the market. It was a marketplace, so if you can guess, we had to attract both sides to be valuable. “Marketplace” — You can imagine something like Uber, if you don’t have passengers it was difficult to convince taxi drivers, if you don’t have a large number of taxi drivers you cannot attract passengers. After a year of development, we were overloaded, and without business, marketing, sales knowledge, and budget. Chapter 3: Corp Team Lead / Programming Tutor / Programming Architecture Workshop Leader Working in a corporation, a totally different environment, an international fintech, another learning experience, large products, and workmates who were waiting for 5 pm to finish — it wasn’t for me. Very slow product development, huge hierarchy, being an ant at the bottom, and low impact on the final product. At that time I understood that being a software developer is not anything special and I compared my work to factory worker. Sorry for that. High rates have been pumped only by high demand. Friends of mine from another industry do more difficult things and have a bigger responsibility for lower rates. That’s how the market works. This lower responsibility time allowed for building the first online course after hours, my own course platform, individual teaching newbies programming, and my first huge success — my first B2C customers, and B2B clients for workshops. I pivoted to full focus on sales, marketing, funnels, advertisements, demand, understanding the market, etc. It was 10x easier than startups but allowed me to learn and validate my conceptions and ideas on an easier market and showed me that it’s much easier to locate their problem/need/want and create a service/product that responds to it than to convince people of your innovative ideas. It’s just supply and demand, such a simple and basic statement, in reality, is very deep and difficult to understand without personal experience. If you’re inexperienced and you think you understand, you don’t. To this day, I love to analyze this catchword in relation to various industries / services / products and rediscover it again and again... While writing this sentence, I’m wondering if I’m not obsessed. Chapter 4: Next try — 2nd time as a founder — Edtech Drawing upon my experiences in selling services, offering trainings, and teaching programming, I wanted to broaden my horizons, delve into various fields of knowledge, involve more teachers, and so on. We started with simple services in different fields of knowledge, mainly relying on teaching in the local area (without online lessons). As I had already gathered some knowledge and experience in marketing and sales, things were going well and were moving in the right direction. The number of teachers in various fields was growing, as was the number of students. I don’t remember the exact statistics anymore, but it was another significant achievement that brought me a lot of satisfaction and new experiences. As you know, I’m a technology lover and couldn’t bear to look at manual processes — I wanted to automate everything: lessons, payments, invoices, customer service, etc. That’s when I hired our first developers (if you’re reading this, I’m sending you a flood of love — we spent a lot of time together and I remember it as a very fruitful and great year) and we began the process of tool and automation development. After a year we had really extended tools for students, teachers, franchise owners, etc. We had really big goals, we wanted to climb higher and higher. Maybe I wouldn’t even fully call it Startup, as the client was paying for the lessons, not for the software. But it gave us positive income, bootstrap financing, and tool development for services provided. Scaling this model was not as costless as SaaS because customer satisfaction was mainly on the side of the teacher, not the quality of the product (software). Finally, we grew to nearly 10 people and dozens of teachers, with zero external funding, and almost $50k monthly revenue. We worked very hard, day and night, and by November 2019, we were packed with clients to the brim. And as you know, that’s when the pandemic hit. It turned everything upside down by 180 degrees. Probably no one was ready for it. With a drastic drop in revenues, society started to save. Tired from the previous months, we had to work even harder. We had to reduce the team, change the model, and save what we had built. We stopped the tool’s development and sales, and with the developers, we started supporting other product teams to not fire them in difficult times. The tool worked passively for the next two years, reducing incomes month by month. With a smaller team providing programming services, we had full stability and earned more than relying only on educational services. At the peak of the pandemic, I promised myself that it was the last digital product I built… Never say never… Chapter 5: Time for fintech — Senior Software Developer / Team Lead / Head of Development I worked for small startups and companies. Building products from scratch, having a significant impact on the product, and complete fulfillment. Thousands of hours and sacrifices. This article mainly talks about startups that I built, so I don’t want to list all the companies, products, and applications that I supported as a technology consultant. These were mainly start-ups with a couple of people up to around 100 people on board. Some of the products were just a rescue mission, others were building an entire tech team. I was fully involved in all of them with the hope that we would work together for a long time, but I wasn’t the only one who made mistakes when looking for a product-market fit. One thing I fully understood: You can’t spend 8–15 hours a day writing code, managing a tech team, and still be able to help build an audience. In marketing and sales, you need to be rested and very creative to bring results and achieve further results and goals. If you have too many responsibilities related to technology, it becomes ineffective. I noticed that when I have more free time, more time to think, and more time to bounce the ball against the wall, I come up with really working marketing/sales strategies and solutions. It’s impossible when you are focused on code all day. You must know that this chapter of my life was long and has continued until now. Chapter 6: 3rd time as a founder — sold Never say never… right?\\ It was a time when the crypto market was really high and it was really trending topic. You know that I love technology right? So I cannot miss the blockchain world. I had experience in blockchain topics by learning on my own and from startups where I worked before. I was involved in crypto communities and I noticed a “starving crowd”. People who did things manually and earned money(crypto) on it.I found potential for building a small product that solves a technological problem. I said a few years before that I don’t want to start from scratch. I decided to share my observations and possibilities with my good friend. He said, “If you gonna built it, I’m in”. I couldn’t stop thinking about it. I had thought and planned every aspect of marketing and sales. And you know what. On this huge mindmap “product” was only one block. 90% of the mindmap was focused on marketing and sales. Now, writing this article, I understood what path I went from my first startup to this one. In the first (described earlier) 90% was the product, but in the last one 90% was sales and marketing. Many years later, I did this approach automatically. What has changed in my head over the years and so many mistakes? At that time, the company for which I provided services was acquired. The next day I got a thank you for my hard work and all my accounts were blocked. Life… I was shocked. We were simply replaced by their trusted technology managers. They wanted to get full control. They acted a bit unkindly, but I knew that they had all my knowledge about the product in the documentation, because I’m used to drawing everything so that in the moment of my weakness (illness, whatever) the team could handle it. That’s what solid leaders do, right? After a time, I know that these are normal procedures in financial companies, the point is that under the influence of emotions, do not do anything inappropriate. I quickly forgot about it, that I was brutally fired. All that mattered was to bring my plan to life. And it has been started, 15–20 hours a day every day. You have to believe me, getting back into the game was incredibly satisfying for me. I didn’t even know that I would be so excited. Then we also noticed that someone was starting to think about the same product as me. So the race began a game against time and the market. I assume that if you have reached this point, you are interested in product-market fit, marketing, and sales, so let me explain my assumptions to you: Product: A very very small tool that allowed you to automate proper tracking and creation of on-chain transactions. Literally, the whole app for the user was located on only three subpages. Starving Crowd: We tapped into an underserved market. The crypto market primarily operates via communities on platforms like Discord, Reddit, Twitter, Telegram, and so on. Therefore, our main strategy was directly communicating with users and demonstrating our tool. This was essentially “free marketing” (excluding the time we invested), as we did not need to invest in ads, promotional materials, or convince people about the efficacy of our tool. The community could directly observe on-chain transactions executed by our algorithms, which were processed at an exceptionally fast rate. This was something they couldn’t accomplish manually, so whenever someone conducted transactions using our algorithm, it was immediately noticeable and stirred a curiosity within the community (how did they do that!). Tests: I conducted the initial tests of the application on myself — we had already invested significantly in developing the product, but I preferred risking my own resources over that of the users. I provided the tool access to my wallet, containing 0.3ETH, and went to sleep. Upon waking up, I discovered that the transactions were successful and my wallet had grown to 0.99ETH. My excitement knew no bounds, it felt like a windfall. But, of course, there was a fair chance I could have lost it too. It worked. As we progressed, some users achieved higher results, but it largely hinged on the parameters set by them. As you can surmise, the strategy was simple — buy low, sell high. There was considerable risk involved. Churn: For those versed in marketing, the significance of repeat visitors cannot be overstated. Access to our tool was granted only after email verification and a special technique that I’d prefer to keep confidential. And this was all provided for free. While we had zero followers on social media, we saw an explosion in our email subscriber base and amassed a substantial number of users and advocates. Revenue Generation: Our product quickly gained popularity as we were effectively helping users earn — an undeniable value proposition. Now, it was time to capitalize on our efforts. We introduced a subscription model charging $300 per week or $1,000 per month — seemingly high rates, but the demand was so intense that it wasn’t an issue. Being a subscriber meant you were prioritized in the queue, ensuring you were among the first to reap benefits — thus adding more “value”. Marketing: The quality of our product and its ability to continually engage users contributed to it achieving what can best be described as viral. It was both a source of pride and astonishment to witness users sharing charts and analyses derived from our tool in forum discussions. They weren’t actively promoting our product but rather using screenshots from our application to illustrate certain aspects of the crypto world. By that stage, we had already assembled a team to assist with marketing, and programming, and to provide round-the-clock helpdesk support. Unforgettable Time: Despite the hype, my focus remained steadfast on monitoring our servers, their capacity, and speed. Considering we had only been on the market for a few weeks, we were yet to implement alerts, server scaling, etc. Our active user base spanned from Japan to the West Coast of the United States. Primarily, our application was used daily during the evenings, but considering the variety of time zones, the only time I could afford to sleep was during the evening hours in Far Eastern Europe, where we had the least users. However, someone always needed to be on guard, and as such, my phone was constantly by my side. After all, we couldn’t afford to let our users down. We found ourselves working 20 hours a day, catering to thousands of users, enduring physical fatigue, engaging in talks with VCs, and participating in conferences. Sudden Downturn: Our pinnacle was abruptly interrupted by the war in Ukraine (next macroeconomic shot straight in the face, lucky guy), a precipitous drop in cryptocurrency value, and swiftly emerging competition. By this time, there were 5–8 comparable tools had infiltrated the market. It was a challenging period as we continually stumbled upon new rivals. They immediately embarked on swift fundraising endeavors — a strategy we overlooked, which in retrospect was a mistake. Although our product was superior, the competitors’ rapid advancement and our insufficient funds for expeditious scaling posed significant challenges. Nonetheless, we made a good decision. We sold the product (exit) to competitors. The revenue from “exit” compensated for all the losses, leaving us with enough rest. We were a small team without substantial budgets for rapid development, and the risk of forming new teams without money to survive for more than 1–2 months was irresponsible. You have to believe me that this decision consumed us sleepless nights. Finally, we sold it. They turned off our app but took algorithms and users. Whether you believe it or not, after several months of toiling day and night, experiencing burnout, growing weary of the topic, and gaining an extra 15 kg in weight, we finally found our freedom… The exit wasn’t incredibly profitable, but we knew they had outdone us. The exit covered all our expenses and granted us a well-deserved rest for the subsequent quarter. It was an insane ride. Despite the uncertainty, stress, struggles, and sleepless nights, the story and experience will remain etched in my memory for the rest of my life. Swift Takeaways: Comprehending User Needs: Do you fully understand the product-market fit? Is your offering just an accessory or does it truly satisfy the user’s needs? The Power of Viral Marketing: Take inspiration from giants like Snapchat, ChatGPT, and Clubhouse. While your product might not attain the same scale (but remember, never say never…), the closer your concept is to theirs, the easier your journey will be. If your user is motivated to text a friend saying, “Hey, check out how cool this is” (like sharing ChatGPT), then you’re on the best track. Really. Even if it doesn’t seem immediately evident, there could be a way to incorporate this into your product. Keep looking until you find it. Niche targeting — the more specific and tailored your product is to a certain audience, the easier your journey will be People love buying from people — establishing a personal brand and associating yourself with the product can make things easier. Value: Seek to understand why users engage with your product and keep returning. The more specific and critical the issue you’re aiming to solve, the easier your path will be. Consider your offerings in terms of products and services and focus on sales and marketing, regardless of personal sentiments. These are just a few points, I plan to elaborate on all of them in a separate article. Many products undergo years of development in search of market fit, refining the user experience, and more. And guess what? There’s absolutely nothing wrong with that. Each product and market follows its own rules. Many startups have extensive histories before they finally make their mark (for instance, OpenAI). This entire journey spanned maybe 6–8 months. I grasped and capitalized on the opportunity, but we understood from the start that establishing a startup carried a significant risk, and our crypto product was 10 times riskier. Was it worth it? Given my passion for product development — absolutely. Was it profitable? — No, considering the hours spent — we lose. Did it provide a stable, problem-free life — nope. Did this entire adventure offer a wealth of happiness, joy, and unforgettable experiences — definitely yes. One thing is certain — we’ve amassed substantial experience and it’s not over yet :) So, what lies ahead? Chapter 7: Reverting to the contractor, developing a product for a crypto StartupReturning to the past, we continue our journey… I had invested substantial time and passion into the tech rescue mission product. I came on board as the technical Team Leader of a startup that had garnered over $20M in seed round funding, affiliated with the realm of cryptocurrencies. The investors were individuals with extensive backgrounds in the crypto world. My role was primarily technical, and there was an abundance of work to tackle. I was fully immersed, and genuinely devoted to the role. I was striving for excellence, knowing that if we secured another round of financing, the startup would accelerate rapidly. As for the product and marketing, I was more of an observer. After all, there were marketing professionals with decades of experience on board. These were individuals recruited from large crypto-related firms. I had faith in them, kept an eye on their actions, and focused on my own responsibilities. However, the reality was far from satisfactory. On the last day, the principal investor for the Series A round withdrew. The board made the tough decision to shut down. It was a period of intense observation and gaining experience in product management. This was a very brief summary of the last 10 years. And what next? (Last) Chapter 8: To be announced — Product Owner / Product Consultant / Strategist / CTO After spending countless hours and days deliberating my next steps, one thing is clear: My aspiration is to continue traversing the path of software product development, with the hopeful anticipation that one day, I might ride the crest of the next big wave and ascend to the prestigious status of a unicorn company. I find myself drawn to the process of building products, exploring product-market fit, strategizing, engaging in software development, seeking out new opportunities, networking, attending conferences, and continuously challenging myself by understanding the market and its competitive landscape. Product Owner / Product Consultant / CTO / COO: I’m not entirely sure how to categorize this role, as I anticipate that it will largely depend on the product to which I will commit myself fully. My idea is to find one startup/company that wants to build a product / or already has a product, want to speed up, or simply doesn’t know what’s next. Alternatively, I could be a part of an established company with a rich business history, which intends to invest in digitization and technological advancements. The goal would be to enrich their customer experience by offering complementary digital products Rather than initiating a new venture from ground zero with the same team, I am receptive to new challenges. I am confident that my past experiences will prove highly beneficial for the founders of promising, burgeoning startups that already possess a product, or are in the initial phases of development. ‘Consultant’ — I reckon we interpret this term differently. My aim is to be completely absorbed in a single product, crafting funnels, niches, strategies, and all that is necessary to repeatedly achieve the ‘product-market fit’ and significant revenue. To me, ‘consultant’ resonates more akin to freelancing than being an employee. My current goal is to kickstart as a consultant and aide, dealing with facilitating startups in their journey from point A to B. Here are two theoretical scenarios to illustrate my approach: Scenario 1: (Starting from point A) You have a product but struggle with marketing, adoption, software, strategy, sales, fundraising, or something else. I conduct an analysis and develop a strategy to reach point B. I take on the “dirty work” and implement necessary changes, including potential pivots or shifts (going all-in) to guide the product to point B. The goal is to reach point B, which could involve achieving a higher valuation, expanding the user base, increasing sales, or generating monthly revenue, among other metrics. Scenario 2: (Starting from point A) You have a plan or idea but face challenges with marketing, adoption, strategy, software, sales, fundraising, or something else. I analyze the situation and devise a strategy to reach point B. I tackle the necessary tasks, build the team, and overcome obstacles to propel the product to point B. I have come across the view that finding the elusive product-market fit is the job of the founder, and it’s hard for me to disagree. However, I believe that my support and experiences can help save money, many failures, and most importantly, time. I have spent a great deal of time learning from my mistakes, enduring failure after failure, and even had no one to ask for support or opinion, which is why I offer my help. Saving even a couple of years, realistically speaking, seems like a value I’m eager to provide… I invite you to share your thoughts and insights on these scenarios :) Closing Remarks: I appreciate your time and effort in reaching this point. This has been my journey, and I wouldn’t change it for the world. I had an extraordinary adventure, and now I’m ready for the next exciting battle with the market and new software products. While my entire narrative is centered around startups, especially the ones I personally built, I’m planning to share more insights drawn from all of my experiences, not just those as a co-founder. If you’re currently developing your product or even just considering the idea, I urge you to reach out to me. Perhaps together, we can create something monumental :) Thank you for your time and insights. I eagerly look forward to engaging in discussions and hearing your viewpoints. Please remember to like and subscribe. Nothing motivates to write more than positive feedback :) Matt.

36 startup ideas found by analyzing podcasts (problem, solution & source episode)

Hey, I've been a bit of a podcast nerd for a long time. Around a year ago I began experimenting with transcription of podcasts for a SaaS I was running. I realized pretty quickly that there's a lot of knowledge and value in podcast discussions that is for all intents and purposes entirely unsearchable or discoverable to most people. I ended up stopping work on that SaaS product (party for lack of product/market fit, and partly because podcasting was far more interesting), and focusing on the podcast technology full-time instead. I'm a long-time lurker and poster of r/startups and thought this would make for some interesting content and inspiration for folks. Given I'm in this space, have millions of transcripts, and transcribe thousands daily... I've been exploring fun ways to expose some of the interesting knowledge and conversations taking place that utilize our own data/API. I'm a big fan of the usual startup podcasts (My First Million, Greg Isenberg, etc. etc.) and so I built an automation that turns all of the startup ideas discussed into a weekly email digest. I always struggle to listen to as many episodes as I'd actually like to, so I thought I'd summarise the stuff I care about instead (startup opportunities being discussed). I thought it would be interesting to post some of the ideas extracted so far. They range from being completely whacky and blue sky, to pretty boring but realistic. A word of warning before anyone complains – this is a big mixture of tech, ai, non-tech, local services, etc. ideas: Some of the ideas are completely mundane, but realistic (e.g. local window cleaning service) Some of the ideas are completely insane, blue sky, but sound super interesting Here's the latest 36 ideas: |Idea Name|Problem|Solution|Source| |:-|:-|:-|:-| |SalesForce-as-a-Service - White Label Enterprise Sales Teams|White-label enterprise sales teams for B2B SaaS. Companies need sales but can't hire/train. Recruit retail sellers, train for tech, charge 30% of deals closed.|Create a white-label enterprise sales team by recruiting natural salespeople from retail and direct sales backgrounds (e.g. mall kiosks, cutco knives). Train them specifically in B2B SaaS sales techniques and processes. Offer this trained sales force to tech companies on a contract basis.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |TechButler - Mobile Device Maintenance Service|Mobile tech maintenance service. Clean/optimize devices, improve WiFi, basic support. $100/visit to homes. Target affluent neighborhoods.|Mobile tech support service providing in-home device cleaning, optimization, and setup. Focus on common issues like WiFi improvement, device maintenance, and basic tech support.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |MemoryBox - At-Home Video Digitization Service|Door-to-door VHS conversion service. Parents have boxes of old tapes. Pick up, digitize, deliver. $30/tape with minimum order. Going extinct.|Door-to-door VHS to digital conversion service that handles everything from pickup to digital delivery. Make it extremely convenient for customers to preserve their memories.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |Elite Match Ventures - Success-Based Luxury Matchmaking|High-end matchmaking for 50M+ net worth individuals. Only charge $1M+ when they get married. No upfront fees. Extensive vetting process.|Premium matchmaking service exclusively for ultra-high net worth individuals with a pure contingency fee model - only get paid ($1M+) upon successful marriage. Focus on quality over quantity with extensive vetting and personalized matching.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |LocalHost - Simple Small Business Websites|Simple WordPress sites for local businesses. $50/month includes hosting, updates, security. Target restaurants and shops. Recurring revenue play.|Simplified web hosting and WordPress management service targeting local small businesses. Focus on basic sites with standard templates, ongoing maintenance, and reliable support for a fixed monthly fee.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |VoiceJournal AI - Voice-First Smart Journaling|Voice-to-text journaling app with AI insights. 8,100 monthly searches. $15/month subscription. Partners with journaling YouTubers.|AI-powered journaling app that combines voice recording, transcription, and intelligent insights. Users can speak their thoughts, which are automatically transcribed and analyzed for patterns, emotions, and actionable insights.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |AIGenAds - AI-Generated UGC Content Platform|AI platform turning product briefs into UGC-style video ads. Brands spending $500/video for human creators. Generate 100 variations for $99/month.|AI platform that generates UGC-style video ads using AI avatars and scripting. System would allow rapid generation of multiple ad variations at a fraction of the cost. Platform would use existing AI avatar technology combined with script generation to create authentic-looking testimonial-style content.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |InfographAI - Automated Infographic Generation Platform|AI turning blog posts into branded infographics. Marketers spending hours on design. $99/month unlimited generation.|AI-powered platform that automatically converts blog posts and articles into visually appealing infographics. System would analyze content, extract key points, and generate professional designs using predefined templates and brand colors.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |KidFinance - Children's Financial Education Entertainment|Children's media franchise teaching financial literacy. Former preschool teacher creating 'Dora for money'. Books, videos, merchandise potential.|Character-driven financial education content for kids, including books, videos, and potentially TV show. Focus on making money concepts fun and memorable.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |FinanceTasker - Daily Financial Task Challenge|Free 30-day financial challenge with daily action items. People overwhelmed by money management. Makes $500k/year through books, speaking, and premium membership.|A free 30-day financial challenge delivering one simple, actionable task per day via email. Each task includes detailed scripts and instructions. Participants join a Facebook community for support and accountability. The program focuses on quick wins to build momentum. Automated delivery allows scaling.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |FinanceAcademy - Expert Financial Training Platform|Premium financial education platform. $13/month for expert-led courses and live Q&As. 4000+ members generating $40k+/month.|Premium membership site with expert-led courses, live Q&As, and community support. Focus on specific topics like real estate investing, business creation, and advanced money management.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |SecurityFirst Compliance - Real Security + Compliance Platform|Security-first compliance platform built by hackers. Companies spending $50k+ on fake security. Making $7M/year showing why current solutions don't work.|A compliance platform built by security experts that combines mandatory compliance requirements with real security measures. The solution includes hands-on security testing, expert guidance, and a focus on actual threat prevention rather than just documentation. It merges traditional compliance workflows with practical security implementations.|In the Pit with Cody Schneider| |LinkedInbound - Automated Professional Visibility Engine|LinkedIn automation for inbound job offers. Professionals spending hours on manual outreach. $99/month per job seeker.|Automated system for creating visibility and generating inbound interest on LinkedIn through coordinated profile viewing and engagement. Uses multiple accounts to create visibility patterns that trigger curiosity and inbound messages.|In the Pit with Cody Schneider| |ConvoTracker - Community Discussion Monitoring Platform|Community discussion monitoring across Reddit, Twitter, HN. Companies missing sales opportunities. $499/month per brand tracked.|Comprehensive monitoring system that tracks competitor mentions and industry discussions across multiple platforms (Reddit, Twitter, Hacker News, etc.) with automated alerts and engagement suggestions.|In the Pit with Cody Schneider| |ContentAds Pro - Smart Display Ad Implementation|Display ad implementation service for content creators. Bloggers losing thousands in ad revenue monthly. Makes $3-5k per site setup plus ongoing optimization fees.|Implementation of professional display advertising through networks like Mediavine that specialize in optimizing ad placement and revenue while maintaining user experience. Include features like turning off ads for email subscribers and careful placement to minimize impact on core metrics.|The Side Hustle Show - "636: Is Business Coaching Worth It? A Look Inside the last 12 months of Side Hustle Nation"| |MoneyAppReviews - Professional Side Hustle App Testing|Professional testing service for money-making apps. People wasting time on low-paying apps. Makes $20k/month from affiliate commissions and ads.|Professional app testing service that systematically reviews money-making apps and creates detailed, honest reviews including actual earnings data, time investment, and practical tips.|The Side Hustle Show - "636: Is Business Coaching Worth It? A Look Inside the last 12 months of Side Hustle Nation"| |LightPro - Holiday Light Installation Service|Professional Christmas light installation service. Homeowners afraid of ladders. $500-2000 per house plus storage.|Professional Christmas light installation service targeting residential and commercial properties. Full-service offering including design, installation, maintenance, removal and storage. Focus on safety and premium aesthetic results.|The Side Hustle Show - "639: 30 Ways to Make Extra Money for the Holidays"| |FocusMatch - Research Participant Marketplace|Marketplace connecting companies to paid research participants. Companies spending weeks finding people. $50-150/hour per study.|Online platform connecting companies directly with paid research participants. Participants create detailed profiles and get matched to relevant studies. Companies get faster access to their target demographic while participants earn money sharing opinions.|The Side Hustle Show - "639: 30 Ways to Make Extra Money for the Holidays"| |SolarShine Pro - Specialized Solar Panel Cleaning Service|Solar panel cleaning service using specialized equipment. Panels lose 50% efficiency when dirty. $650 per job, automated scheduling generates $18k/month from repeat customers.|Professional solar panel cleaning service using specialized deionized water system and European cleaning equipment. Includes automated 6-month scheduling, professional liability coverage, and warranty-safe cleaning processes. Service is bundled with inspection and performance monitoring.|The UpFlip Podcast - "156. $18K/Month with This ONE Service — Niche Business Idea"| |ExteriorCare Complete - One-Stop Exterior Maintenance Service|One-stop exterior home cleaning service (solar, windows, gutters, bird proofing). Automated scheduling. $650 average ticket. 60% repeat customers on 6-month contracts.|All-in-one exterior cleaning service offering comprehensive maintenance packages including solar, windows, gutters, roof cleaning and bird proofing. Single point of contact, consistent quality, and automated scheduling for all services.|The UpFlip Podcast - "156. $18K/Month with This ONE Service — Niche Business Idea"| |ContentMorph - Automated Cross-Platform Content Adaptation|AI platform converting blog posts into platform-optimized social content. Marketing teams spending 5hrs/post on manual adaptation. $199/mo per brand with 50% margins.|An AI-powered platform that automatically transforms long-form content (blog posts, podcasts, videos) into platform-specific formats (Instagram reels, TikToks, tweets). The system would preserve brand voice while optimizing for each platform's unique requirements and best practices.|Entrepreneurs on Fire - "Digital Threads: The Entrepreneur Playbook for Digital-First Marketing with Neal Schaffer"| |MarketerMatch - Verified Digital Marketing Talent Marketplace|Marketplace for pre-vetted digital marketing specialists. Entrepreneurs spending 15hrs/week on marketing tasks. Platform takes 15% commission averaging $900/month per active client.|A specialized marketplace exclusively for digital marketing professionals, pre-vetted for specific skills (video editing, social media, SEO, etc.). Platform includes skill verification, portfolio review, and specialization matching.|Entrepreneurs on Fire - "Digital Threads: The Entrepreneur Playbook for Digital-First Marketing with Neal Schaffer"| |Tiger Window Cleaning - Premium Local Window Service|Local window cleaning service targeting homeowners. Traditional companies charging 2x market rate. Making $10k/month from $200 initial investment.|Local window cleaning service combining competitive pricing ($5/pane), excellent customer service, and quality guarantees. Uses modern tools like water-fed poles for efficiency. Implements systematic approach to customer communication and follow-up.|The Side Hustle Show - "630: How this College Student’s Side Hustle Brings in $10k a Month"| |RealViz3D - Real Estate Visualization Platform|3D visualization service turning architectural plans into photorealistic renderings for real estate agents. Agents struggling with unbuilt property sales. Making $30-40k/year per operator.|Professional 3D modeling and rendering service that creates photorealistic visualizations of properties before they're built or renovated. The service transforms architectural plans into immersive 3D representations that show lighting, textures, and realistic details. This helps potential buyers fully understand and connect with the space before it physically exists.|Side Hustle School - "#2861 - TBT: An Architect’s Side Hustle in 3D Real Estate Modeling"| |Somewhere - Global Talent Marketplace|Platform connecting US companies with vetted overseas talent. Tech roles costing $150k locally filled for 50% less. Grew from $15M to $52M valuation in 9 months.|Platform connecting US companies with pre-vetted overseas talent at significantly lower rates while maintaining high quality. Handles payments, contracts, and quality assurance to remove friction from global hiring.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |GymLaunch - Rapid Gym Turnaround Service|Consultants flying to struggling gyms to implement proven member acquisition systems. Gym owners lacking sales expertise. Made $100k in first 21 days.|Expert consultants fly in to implement proven member acquisition systems, train staff, and rapidly fill gyms with new members. The service combines sales training, marketing automation, and proven conversion tactics to transform struggling gyms into profitable businesses within weeks.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |PublishPlus - Publishing Backend Monetization|Backend monetization system for publishing companies. One-time customers becoming recurring revenue. Grew business from $2M to $110M revenue.|Add complementary backend products and services to increase customer lifetime value. Develop software tools and additional services that natural extend from initial publishing product. Focus on high-margin recurring revenue streams.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |WelcomeBot - Automated Employee Onboarding Platform|Automated employee welcome platform. HR teams struggling with consistent onboarding. $99/month per 100 employees.|An automated onboarding platform that creates personalized welcome experiences through pre-recorded video messages, scheduled check-ins, and automated swag delivery. The platform would ensure consistent high-quality onboarding regardless of timing or location.|Entrepreneurs on Fire - "Free Training on Building Systems and Processes to Scale Your Business with Chris Ronzio: An EOFire Classic from 2021"| |ProcessBrain - Business Knowledge Documentation Platform|SaaS platform turning tribal knowledge into documented processes. Business owners spending hours training new hires. $199/month per company.|A software platform that makes it easy to document and delegate business processes and procedures. The platform would include templates, guided documentation flows, and tools to easily share and update procedures. It would help businesses create a comprehensive playbook of their operations.|Entrepreneurs on Fire - "Free Training on Building Systems and Processes to Scale Your Business with Chris Ronzio: An EOFire Classic from 2021"| |TradeMatch - Modern Manufacturing Job Marketplace|Modern job board making manufacturing sexy again. Factory jobs paying $40/hr but can't recruit. $500 per successful referral.|A specialized job marketplace and recruitment platform focused exclusively on modern manufacturing and trade jobs. The platform would combine TikTok-style content marketing, referral programs, and modern UX to make manufacturing jobs appealing to Gen Z and young workers. Would leverage existing $500 referral fees and industry demand.|My First Million - "He Sold His Company For $15M, Then Got A Job At McDonald’s"| |GroundLevel - Executive Immersion Program|Structured program putting CEOs in front-line jobs. Executives disconnected from workers. $25k per placement.|A structured program that places executives and founders in front-line jobs (retail, warehouse, service) for 2-4 weeks with documentation and learning framework. Similar to Scott Heiferman's McDonald's experience but productized.|My First Million - "He Sold His Company For $15M, Then Got A Job At McDonald’s"| |OneStepAhead - Micro-Mentorship Marketplace|Marketplace for 30-min mentorship calls with people one step ahead. Professionals seeking specific guidance. Takes 15% of session fees.|MicroMentor Marketplace - Platform connecting people with mentors who are just one step ahead in their journey for focused, affordable micro-mentorship sessions.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |VulnerableLeader - Leadership Authenticity Training Platform|Leadership vulnerability training platform. Leaders struggling with authentic communication. $2k/month per company subscription.|Leadership Vulnerability Platform - A digital training platform combining assessment tools, guided exercises, and peer support to help leaders develop authentic communication skills. The platform would include real-world scenarios, video coaching, and measurable metrics for tracking leadership growth through vulnerability.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |NetworkAI - Smart Network Intelligence Platform|AI analyzing your network to find hidden valuable connections. Professionals missing opportunities in existing contacts. $49/month per user.|AI Network Navigator - Smart tool that analyzes your professional network across platforms, identifies valuable hidden connections, and suggests specific actionable ways to leverage relationships for mutual benefit.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |Porch Pumpkins - Seasonal Decoration Service|Full-service porch pumpkin decoration. Homeowners spend $300-1350 per season. One operator making $1M in 8 weeks seasonal revenue.|Full-service seasonal porch decoration service focused on autumn/Halloween, including design, installation, maintenance, and removal. Offering premium curated pumpkin arrangements with various package tiers.|My First Million - "The guy who gets paid $80K/yr to do nothing"| |Silent Companion - Professional Presence Service|Professional silent companions for lonely people. Huge problem in Japan/globally. $68/session, $80k/year per companion. Non-sexual, just presence.|A professional companion service where individuals can rent a non-judgmental, quiet presence for various activities. The companion provides silent company without the pressure of conversation or social performance. They accompany clients to events, meals, or just sit quietly together.|My First Million - "The guy who gets paid $80K/yr to do nothing"| Hope this is useful. If anyone would like to ensure I include any particular podcasts or episodes etc. in future posts, very happy to do so. I'll generally send \~5 ideas per week in a short weekly digest format (you can see the format I'd usually use in here: podcastmarketwatch.beehiiv.com). I find it mindblowing that the latest models with large context windows make it even possible to analyze full transcripts at such scale. It's a very exciting time we're living through! Would love some feedback on this stuff, happy to iterate and improve the analysis/ideas... or create a new newsletter on a different topic if anyone would like. Cheers!

A Structured Approach to Ideation and Validation (I will not promote)

Hi all, I used to work in VC and wanted to share some startup knowledge and insights from startup founders I know. Recently, I interviewed a friend of mine who built an AI Robotics startup ("Hivebotics") that creates automated toilet-cleaning robots. I can't post the full article because of Reddit's word limit, so I'll be posting it in sections here instead. This first section of the transcript goes through his approach to ideation and validation. Enjoy and let me know what you think! (I will not promote) \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ (1) Ideation and Validation Problem-Market-Solution Framework I like to think of startup ideation and validation using this framework: Problem– What exactly are you solving? Observation– How you identify a problem to work on User Research– How you further understand that problem Market– Is there a large enough market for solving this problem? Size– How many people experience this same problem? Demand– How many of those people are willing to pay for the solution? Solution– Your answer to the problem Desirability– Whether people actually want your solution Feasibility– Whether building the solution is practical and realistic Viability– Whether your solution can generate revenue Problem You always need to start problem-first, which is something that was really drilled into me during my time at Stanford. Too often, founders rush to build solutions first—apps or products they find exciting—without confirming whether there's any real demand for it. The first step is always to identify a specific problem, then further understand its scale, urgency and further details by talking to potential users. Observation– To find problems, observation is key. People may not even realise the inefficiencies in their processes until you point them out. That’s why interviews and field research are so important. There are problems all around us, so it's simply a matter of going out, paying attention and being attuned to them as they occur. User Research– To further understand the problem, conducting user research by interviewing potential customers is essential. Personally, I like to use the "Mom Test" when I conduct interviews to avoid biased and generic feedback. Don’t just ask theoretical questions and avoid being too specific—observe how your potential users work, ask about pain points, and use broad, open-ended questions to ensure you aren't leading them to a specific answer. Market Once you've found an actual problem and talked to enough potential users to really understand its specific pain points, the next step is to determine the market size and demand for a solution. Size– Determining the market size is essential because it determines whether or not it's commercially worthwhile to pursue the problem and develop a solution for it. You need to determine if there are enough potential customers out there experiencing this problem to gauge the market size. There's no secret strategy for this; you have to interview as many potential users as possible to confirm that it's a widespread problem in the industry. Demand– Make sure that you're working on a problem that people will gladly pay to have solved. Even if the problem is large enough, you have to make sure it's painful enough to warrant a paid solution. If many people experience the same problem, but aren't willing to pay for a solution, then you don't have a market and should look for a different problem to validate. Another way of looking at it is that your true market size is the number of potential customers actually willing to pay* for the solution to the problem, not the number of people simply experiencing the same problem. Solution When validating a potential solution to the problem, I would look at the 3 factors of desirability, feasibility and viability. Desirability– the degree to which a solution appeals to people and fulfills their wants and needs. Without strong desirability, even the most technically advanced or economically practical product is unlikely to succeed. The best way to test this is to secure financial commitments early on during the proof-of-concept stage. Most people are polite, so they may simply tell you that your startup's product is good even if it's not. However, if they're actually willing to pay for the solution, this is actual evidence of your product's desirability. Don't just ask people if they would pay for it; actually see whether they will pay for it. Feasibility– whether a product can be built using existing technical capabilities. A lack of feasibility makes it challenging or impossible to develop the product, no matter how appealing it might be to users or how promising its financial prospects are. This is just a matter of conducting initial research and actually trying to build a prototype, which will inform you whether the fully-realised product is truly feasible. Viability– the product's ability to generate sustainable financial returns. Without financial viability, the business supporting the product cannot endure, even if the product is highly appealing to users and technically achievable. Here, you need to look at your unit economics, development costs and other expenses to determine the viability of your solution. \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ Hope you enjoyed reading this; let me know your honest thoughts in the comments and I'll try to improve how I interview founders based on those!

Voice AI Isn’t Just for Big Brands – Here’s How Startups Can Use It (I will not promote)

When you think about Voice AI, it’s easy to picture massive companies like Amazon or Google pouring millions into complex systems. But it isn’t just for the big guys anymore. Startups can use it too, and it doesn’t have to cost a fortune. Why Startups Should Care About Voice AI Voice AI used to be expensive and complicated, but that’s changed a lot. Today, even small startups can use it to save time, cut costs, and make customers happier—all without needing a massive budget. If you think that repetitive tasks are eating up your team’s time, or if customers are getting frustrated by slow responses, Voice AI can help. And it’s not just for call centers or tech giants. Startups can benefit from it just as much, if not more. 3 Practical Ways Startups Can Use Voice AI Automated Scheduling and Appointment Setting Whether it’s booking meetings, setting reminders, or rescheduling, Voice AI can handle it all. This is especially useful for service-based startups, like healthcare clinics, legal firms, or consulting agencies. Answering Frequently Asked Questions (FAQs) Every startup gets repetitive questions—“What are your hours?” “What’s your refund policy?” Instead of answering the same things over and over, Voice AI can automate it. Order Tracking and Status Updates For e-commerce startups, Voice AI can provide real-time order updates without involving a human. Customers get quick answers, and your team can focus on more important tasks. Simple Workflow: How It Works Customer Initiates Call Customer calls the business for scheduling, FAQs, or order updates. Voice AI Answers AI responds with a natural, human-like voice. AI Handles the Request Schedules appointments, answers FAQs, or provides order updates. Integration and Confirmation Syncs with calendars or order management systems. Confirms booking or provides tracking info. Call Ends Customer gets what they need without waiting. Team stays focused on higher-priority tasks. If the fear is that Voice AI will sound robotic or annoy customers, it’s worth reconsidering. Today’s tech is way more natural and human-like than it used to be. You can use free trial of platforms like Retell AI or Play AI or Bland AI (I will not promote) Would it make sense for your startup to try Voice AI?

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies) (I will not promote)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. (I will not promote) About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

Online Reputation AI - Startup got stuck

Hi, I‘m one of 3 co-founders of a startup that built an AI-driven SaaS and App product this year. We‘re coming from an SaaS background, two of us senior developers (in the 3% of highest earning freelancers in Germany) and expert in our fields. The third is a seasoned sales strategist. We have a minor 4th co-founder (legal advisor). The company is self-funded, no investors. Our tech is owned by us, built by us and the product was already operational after a few months. We basically solve three data science/NLP issues in a generalized way: understand customer feedback to improve your business. Analyzes online review with context and explains it with a drill down, aggregation, charts (AI insights, timeframe reports); evidence driven, agentic LLM and ETL processes drive this. respond to customer feedback, half-automated, human in the loop, but AI supported. In the tone of your brand, any language. And context-aware, with your customer support signature etc. competitor analysis. Because we do 1 for you, we can do 1. for all of your competitors and compare the results, yielding insights like „oh, this happens to everyone in November to December, so I should focus on something else“ — etc. Now, after a huge sales effort we got only one paying customer. This customer is petty happy with the product. They tell us that they use our product daily, it‘s better than all the other solutions out there (better than TrustYou, etc.) However, after cold calling/emailing hundreds of leads, we almost always hear that „what we have is good enough“. Or that they don‘t have budget. I‘m the introverted tech part of the startup. I‘m good with algorithms. Give me any tech issue and I will solve it for you quickly and efficiently. I make stuff work. But with my startups I never had commercial luck. People always tell me about my stellar potential, because I can build things almost nobody else can. I come from a poor families background, worked my way up the very hard way. I just love tech and programming. I wrote a book for O’Reilly once. I‘m not doing bad economically, but I‘m probably not the best sales person. After founding a few startups with amazing tech, people using the products and loving them, but no commercial success, I truly question myself and if I‘m just unlucky with the fact that I‘m located in Europe, targeting the wrong industries, or are just unlucky somehow? I won‘t blame my co-founders here. They definitely did the best they could. I‘m just a bit resignated. I recently thought about valuing my own lifetime more and only building software for myself anymore. Basically not focusing on what problems other people face and trying to solve them, but solely focusing on what I enjoy doing most — e.g. coding algorithms for a music visualizer. Because in the end, my time is my most valuable resource. If I waste any second on something that isn‘t contributing to „my life“ and how I define success, then it would be a rather stupid deed? I don‘t want to derail too much here. I‘m confused and seeking for advice. Burn me if you like, but please be aware that you are talking to a broadly educated nerd.

AI Might Be the Best Industry for Ambitious Lazy People i will not promote

Not here to promote, just talk about my experience with starting a new business. I'm not new to the game, so I was able to speed-run my new AI automation agency. I currently run a software company with a co-founder, and I recently decided to start a new AI and automation agency. I just had a private launch this week, and I already have a $2K client lined up, ready to buy, along with some other interested parties, as I have sales calls with them coming up. I found all of my leads after choosing a niche to focus on and using this tool I built that automatically scrapes IG data. My tool is “unique” because it automagically qualifies the leads with AI. It even has a custom frontend, and I used this tool as a case study to secure the client I have now, and I accomplished all of this in the span of about a week. Granted, I have a background in engineering, so picking up AI was easier for me, but anyone can do it. You can even use AI to learn AI. If you haven’t used AI in your business yet, I would strongly suggest getting into AI and automation. If you've been considering starting a business but don't know what business to start, take this as a sign to turn AI into a business. i will not promote

After building an AI Co-founder to solve my startup struggles, I realized we might be onto something bigger. What problems would you want YOUR AI Co-founder to solve?

A few days ago, I shared my entrepreneurial journey and the endless loop of startup struggles I was facing. The response from the community was overwhelming, and it validated something I had stumbled upon while trying to solve my own problems. In just a matter of days, we've built out the core modules I initially used for myself, deep market research capabilities, automated outreach systems, and competitor analysis. It's surreal to see something born out of personal frustration turning into a tool that others might actually find valuable. But here's where it gets interesting (and where I need your help). While we're actively onboarding users for our alpha test, I can't shake the feeling that we're just scratching the surface. We've built what helped me, but what would help YOU? When you're lying awake at 3 AM, stressed about your startup, what tasks do you wish you could delegate to an AI co-founder who actually understands context and can take meaningful action? Of course, it's not a replacement for an actual AI cofounder, but using our prior entrepreneurial experience and conversations with other folks, we understand that OUTREACH and SALES might actually be a big problem statement we can go deeper on as it naturally helps with the following: Idea Validation - Testing your assumptions with real customers before building Pricing strategy - Understanding what the market is willing to pay Product strategy - Getting feedback on features and roadmap Actually revenue - Converting conversations into real paying customers I'm not asking you to imagine some sci-fi scenario, we've already built modules that can: Generate comprehensive 20+ page market analysis reports with actionable insights Handle customer outreach Monitor competitors and target accounts, tracking changes in their strategy Take supervised actions based on the insights gathered (Manual effort is required currently) But what else should it do? What would make you trust an AI co-founder with parts of your business? Or do you think this whole concept is fundamentally flawed? I'm committed to building this the right way, not just another AI tool or an LLM Wrapper, but an agentic system that can understand your unique challenges and work towards overcoming them. Whether you think this is revolutionary or ridiculous, I want to hear your honest thoughts. But more importantly, I want to hear your unfiltered feedback in the comments. What would make this truly valuable for YOU? Edit 1: The AI cofounder will take no equity in your startup.

Startup founders, tell me what's the job you would like to get done in your startup but you are too busy to repeat or start it?

I've been focusing on LLM-based agent development for the past two years and am now building a related startup. I want to validate my startup ideas and would especially like to hear feedback from entrepreneurs. What are the repetitive tasks in your startup journey that need to be completed but you're too busy to handle or initiate? I can develop specialized intelligent agents to solve these issues for you. Whether it's workflow automation or more advanced agent AI applications, whatever problems you want to solve, I'm willing to try and help. For just a small fee (provided it's truly an important problem worth solving), I can customize solutions for you. Following the principle of "do things that don't scale," I'm more focused on helping entrepreneurs quickly and effectively address their pain points. Through this approach, we can explore together the practical value of AI agents in startup scenarios and gradually improve product functionality. Feel free to share any specific business scenarios or needs you have. Let's discuss how AI agents can truly help entrepreneurs improve their work efficiency.

Looking for an accountability partner as a solo founder. [I will not promote]

Hello! I am a technical founder focused on using AI solutions to drive automation. Recently had a co-founder split after working together for a couple month. We had a very good traction but I made a decision to leave because I believed we didn't have a solid foundational relationship that can be sustained for a long time. Had more of a co-worker style relationship. Took on the short-term pain to set myself up for a long term success. He was the one leading the sales and relation with the businesses, so we decided he will be leading the company moving forward and we split on very good terms. Back in the gulag now and starting from scratch. Took three days to reset and recover. When I tried to get back at things yesterday, my brain wasn't just having it. My stress activation got so high, i did like 4 wim hof breathing sessions and a 10 mile run to relieve the stress buildup. There is something about uncertainty and working without a lack of clear path that is super hard to process especially when you are solo. Currently I am working through my previous idea backlogs that I have built up and re-starting previous conversations. But my brain isn't giving me the dopamine hit from driving toward action as much as I used to. So any work that i do feels like a slogging through mud. I am looking to experiment with having an accountability partner, to make the initial ramp up easier. Thinking of doing the elon musk style "What have you done this week?" report that we can do to drive accountability and give that extra motivation. If you're navigating similar challenges as a solo founder and believe mutual accountability could accelerate our progress and growth, I'd love to connect. Let's help each other build momentum and stay motivated—drop a comment or DM if interested! I will not promote

Feeling stuck—built a startup, got rejected from YC & IVI, met smarter people, and now I don’t know what to do. ( i will not promote ) I will not promote

I will not promote I don’t even know where to start, but I just feel completely stuck right now. I’m 20 years oldI don’t even know where to start, but I just feel completely stuck right now. I’m 20 years old, have been grinding non-stop for months, and it feels like I have nothing to show for it. I built an AI agent that automates workflows for businesses. I can build tech, but I can’t sell. That’s been my biggest realization recently—I thought building would be enough, but it’s not. I need customers, I need a co-founder, I need to figure out the business side… and I have no idea how. I applied to YC, IVI at ISB, and EF, met a lot of insanely smart people—some were impressed with me and my work, but they were wiser, more experienced, and honestly, just better at all of this than I am. It made me realize how much I don’t know. I got rejected from YC & IVI. 💔 YC didn’t even give much feedback—just a standard rejection. 💔 IVI told me: “You're too young, you need more experience, and you should work with a team before trying to start something.” That hit me hard. I had already been struggling to find a co-founder, and this just made me wonder if I even belong in this space yet. The Frustrating Part? I KNOW my tool Has a Unique Edge. I’m not just another AI automation tool—I know my tool has a strong USP that competitors lack. It has the potential to be an AI employee for businesses, not just another workflow tool. But I still haven’t built the “perfect product” I originally envisioned. And that’s what’s eating at me. I see what it COULD be, but I haven’t made it happen yet. At the same time, the competition in the AI agent space is exploding. YC-backed companies are working on AI agent startups. OpenAI is making huge progress with Operator. Competitors are moving fast, while I feel stuck. I’ve delayed development because I’m unsure whether to double down, pivot, or just move on entirely. Where I’m Stuck Right Now 🔹 Do I keep pushing and try to crack sales somehow? 🔹 Do I join a startup as a founding engineer to get experience, make connections, and learn sales before trying again? 🔹 Do I move to Bangalore, meet founders, and figure out what’s next? 🔹 Do I pivot to something nicher instead of competing in the AI agent race? If so, how do I even find a niche worth pursuing? 🔹 Do I even belong in startups? Or am I just forcing something that’s not working? I feel stuck in a weird middle zone where I’m not a beginner, but I’m also not successful. I’ve done enough to see what’s possible, but not enough to make it real. Every rejection makes me question if I’m even on the right path. I don’t know if I’m posting this for advice or just to get it out of my system. Maybe both. Has anyone else felt like this before? If you’ve been in this situation—how did you figure out whether to keep going or move on? TL;DR: I’m 20, built an AI agent for automating workflows, got rejected from YC & IVI, met insanely smart and experienced people, realized I can build tech but can’t sell, struggling to find a co-founder, AI agent competition is growing, delaying development, confused about the future—don’t know whether to double down, pivot, or move on. The frustrating part? I\ know I have a unique edge that others lack, but I still haven’t built the perfect product I originally envisioned.* edit: removed the tool's name

What I Learned from a Failed Startup: Seeking Advice on Engineering, Co-Founder Agreements & Execution (i will not promote)

Hey everyone! Long-time lurker, first-time founder here. I’m reaching out to get feedback on a recent startup experience—what went wrong, what I could have done better, and how I should approach future opportunities. The Background There were three founders in this venture: • Founder A (CEO, 50%) – The product/growth guy who identified the problem space. • Founder B (Me, CTO, 37.5%) – A software engineer with a software dev shop and multiple clients. I wanted to diversify into building my own products but am not inherently a “product person.” • Founder C (COO, 12.5%) – Brought into the mix by Founder A, with the goal of leveraging his network for traction once the product was built. The idea was to create Product X, a solution targeting the SMB space while competitors were moving upmarket. It wasn’t revolutionary—more of a strategic market play. The Initial Plan & My Role • Founder A would define and prioritize product specs, guiding what needed to be built. • I (Founder B) didn’t have time to code myself, so I allocated engineers from my dev shop (which I personally paid for). My stake was adjusted from 32.5% to 37.5% to reflect this contribution. • Founder C was more of an observer early on, planning to help with traction once we had a product ready. We agreed on a 1-year cliff and a 4-year vesting schedule for equity. Where Things Started to Go Wrong • Lack of a Clear Product Roadmap – Founder A was very focused on getting something built fast, but we never signed off on a structured roadmap or milestones. I underestimated the complexity of what was actually needed for customer conversations. • Engineering Expectations vs. Reality – The team (one part-time lead + two full-time juniors from my dev shop) faced early feedback that development was too slow. In response, I ramped up the lead to full-time and added a part-time PM. But Founder A continued pushing for speed, despite real hurdles (OAuth integrations, etc.). • Shifting MVP Goalposts – Midway, Founder A concluded that an MVP wouldn’t cut it—we needed a more complete product to be competitive. This meant more engineering, more delays, and more of my own money spent on development. The Breaking Point Near the 1-year vesting mark, we had an opportunity: a paying client willing to fund an app. I didn’t have devs on the bench, so I asked Founder A to hold off our project briefly while I hired more engineers to avoid stalling either effort. This was the final straw. Founder A (with Founder C somewhat aligned) decided the arrangement wasn’t working—citing past disagreements and the “slowness” issue. The decision was made to end the partnership. Now, Founder A, as majority holder, is requesting a full handover of the code, Founder C is indifferent, and all engineering costs I covered are essentially lost. Key Takeaways (So Far) Crystal-Clear Agreements Upfront – A formalized product roadmap and timeline should’ve been locked in from day one. Business Needs > Engineering Standards – I wanted to build something solid and scalable, but in an early-stage startup, speed to market is king. This was before AI tools became mainstream, so our approach wasn’t as optimized. Don’t Overextend Without Protection – I personally financed all engineering, but without clear safeguards, that investment became a sunk cost. Expenses Must Be Distributed – I was solely covering engineering salaries, which created an imbalance in financial risk. Future partnerships should ensure costs are shared proportionally, rather than one person shouldering the burden. Where I Need Advice Looking back, I want to improve as an engineer, CEO, and co-founder. • What should I have done differently in structuring this partnership? • How do you balance engineering quality with the startup need for speed? • As a dev shop owner, how can I better navigate equity deals where I’m also bringing in engineering resources? I really appreciate everyone who went through this long post and provide any insights from founders, engineers, or anyone who has been in a similar situation. Thanks for reading! ===================================================================== For readers who might be thinking what set this type of expectation? Because I had a dev shop and I thought my co-founders will be understanding of my business circumstance and I was a bit trigger to build a product with a C-exec team, I gave the impression of "unlimited" engineering which I later realized down the line that it was not feasible for me. Something I learned that I have to be more careful with and set expectations accordingly from the very beginning. And from the feedback of the commenters here, I am much more aware what I should offer and how to set expectations, esp. in the early stages of execution. So thank you all! 🙏🏾 EDIT: I would like to thank everyone who contributed to this thread. You not only helped me but future founders who are considering to get into the startup scene!

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I feel Ai is mostly marketing - I will not promote

I run into this on X an made me think about it… the post says “AI is effectively ‘useless’ and it’s created a ‘fake it till you make it’ bubble that could end in disaster”. I think this is true. I haven't seen a product that really solves anything specifically except for the gimmicks. It needs a product normally people can use. Also the AI startups have cash burn rates 3x to 10x their revenue. No business model. It's very focused on getting acquired.

How I made a high tech salary in my first selling month

For over 7 years I worked as a full-stack developer, helping other companies bring their ideas to life. But one day, I thought “Why not try making my own dream come true?”. That’s when I decided to quit my job and start my own journey to becoming an entrepreneur. At first, it wasn’t easy. I didn’t make any money for months and had no idea where to start. I felt lost. Then, I decided to focus on something popular and trending. AI was everywhere, and ChatGPT was the most used AI platform. So I looked into it and I found the OpenAI community forum where people had been asking for features that weren’t being added. That gave me an idea. Why not build those features myself? I created a Chrome extension and I worked on some of the most requested features, like: Downloading the advanced voice mode and messages as MP3 Adding folders to organize chats Saving and reusing prompts Pinning important chats Exporting chats to TXT/JSON files Deleting or archiving multiple chats at once Making chat history searches faster and better It took me about a week to build the first version, and when I published it, the response was incredible. People loved it! Some even said things like, “You’re a lifesaver!” That’s when I realized I had something that could not only help people but also turn into a real business. I kept the first version free to see how people would respond. Many users have been downloading my extension, which prompted Chrome to review it to determine if it qualified for the featured badge. I received the badge, and it has significantly boosted traffic to my extension ever since. After all the positive feedback, I launched a paid version one month ago. A few minutes after publishing it, I made my first sale! That moment was so exciting, and it motivated me to keep going. I already have over 4,000 users and have made more than $4,500 in my first selling month. I’ve decided to release 1-2 new features every month to keep improving the extension based on what users ask for. I also created the same extension for Firefox and Edge users because many people have been asking for it! I also started a Reddit community, where I share updates, sales, discount codes, and ideas for new features. It’s been awesome to connect with users directly and get their feedback. Additionally, I’ve started working on another extension for Claude, which I’m hoping will be as successful as this one. My message to you is this: never give up on your dreams. It might feel impossible at first, but with patience, hard work, and some creativity, you can make it happen. I hope this inspires you to go after what you want. Good luck to all of us!

Just raised and here are the stats (July 2024)

CEO of a startup - bootstrapped for 10 months with a team of 7 - Built a waitlist of $15B AUM (fintech) and here's what it took (with no intended story structure) I didn't want to spam, so I decided to go the old school route and manually write every single email (some copy and paste) In order to feel prepared, I would do my research prior to reaching out, albeit sometimes limited due to time x reward Sent over 350 emails to around 300 funds and we received three yes' (to be honest we received more than three, but they wanted too much equity, or they weren’t a good fit culturally) Pre Seed is different for everyone. Some accept pre revenue others expect 100-300k ARR - this was one of the more frustrating pieces for me, due to the fact that it's extremely subjective to what "Earliest Stage" means to some funds. We're pre-product, we had to remove our CTO in the process due to performance issues, we let go of our front-end, hired a new CTO, hired an AI Engineer, and replaced our front end. It's a numbers game. We received 94% no reply - 5% nos (with meetings) - 1% yes' I used OpenVC as my main resource, highly recommend even their free product. I recommend using discount with a SAFE. Some Angels like it better, some VC’s hate it. You have to be willing to play ball with whoever leads. Mercury for banking, perks (like Carta), and SAFE agreement. All great at Mercury. Raising for a B2B business in an enterprise market is much easier, unless deep tech or science backed. But consumer products right now are not raising pre seed from what I can tell. If it means anything - it's a numbers game. Go get what you deserve, but put in the work because no one will just hand it to you. Love this community, always here to help anyone I can.

After building an AI Co-founder to solve my startup struggles, I realized we might be onto something bigger. What problems would you want YOUR AI Co-founder to solve?

A few days ago, I shared my entrepreneurial journey and the endless loop of startup struggles I was facing. The response from the community was overwhelming, and it validated something I had stumbled upon while trying to solve my own problems. In just a matter of days, we've built out the core modules I initially used for myself, deep market research capabilities, automated outreach systems, and competitor analysis. It's surreal to see something born out of personal frustration turning into a tool that others might actually find valuable. But here's where it gets interesting (and where I need your help). While we're actively onboarding users for our alpha test, I can't shake the feeling that we're just scratching the surface. We've built what helped me, but what would help YOU? When you're lying awake at 3 AM, stressed about your startup, what tasks do you wish you could delegate to an AI co-founder who actually understands context and can take meaningful action? Of course, it's not a replacement for an actual AI cofounder, but using our prior entrepreneurial experience and conversations with other folks, we understand that OUTREACH and SALES might actually be a big problem statement we can go deeper on as it naturally helps with the following: Idea Validation - Testing your assumptions with real customers before building Pricing strategy - Understanding what the market is willing to pay Product strategy - Getting feedback on features and roadmap Actually revenue - Converting conversations into real paying customers I'm not asking you to imagine some sci-fi scenario, we've already built modules that can: Generate comprehensive 20+ page market analysis reports with actionable insights Handle customer outreach Monitor competitors and target accounts, tracking changes in their strategy Take supervised actions based on the insights gathered (Manual effort is required currently) But what else should it do? What would make you trust an AI co-founder with parts of your business? Or do you think this whole concept is fundamentally flawed? I'm committed to building this the right way, not just another AI tool or an LLM Wrapper, but an agentic system that can understand your unique challenges and work towards overcoming them. Whether you think this is revolutionary or ridiculous, I want to hear your honest thoughts. But more importantly, I want to hear your unfiltered feedback in the comments. What would make this truly valuable for YOU? Edit 1: The AI cofounder will take no equity in your startup.

What I Learned from a Failed Startup: Seeking Advice on Engineering, Co-Founder Agreements & Execution (i will not promote)

Hey everyone! Long-time lurker, first-time founder here. I’m reaching out to get feedback on a recent startup experience—what went wrong, what I could have done better, and how I should approach future opportunities. The Background There were three founders in this venture: • Founder A (CEO, 50%) – The product/growth guy who identified the problem space. • Founder B (Me, CTO, 37.5%) – A software engineer with a software dev shop and multiple clients. I wanted to diversify into building my own products but am not inherently a “product person.” • Founder C (COO, 12.5%) – Brought into the mix by Founder A, with the goal of leveraging his network for traction once the product was built. The idea was to create Product X, a solution targeting the SMB space while competitors were moving upmarket. It wasn’t revolutionary—more of a strategic market play. The Initial Plan & My Role • Founder A would define and prioritize product specs, guiding what needed to be built. • I (Founder B) didn’t have time to code myself, so I allocated engineers from my dev shop (which I personally paid for). My stake was adjusted from 32.5% to 37.5% to reflect this contribution. • Founder C was more of an observer early on, planning to help with traction once we had a product ready. We agreed on a 1-year cliff and a 4-year vesting schedule for equity. Where Things Started to Go Wrong • Lack of a Clear Product Roadmap – Founder A was very focused on getting something built fast, but we never signed off on a structured roadmap or milestones. I underestimated the complexity of what was actually needed for customer conversations. • Engineering Expectations vs. Reality – The team (one part-time lead + two full-time juniors from my dev shop) faced early feedback that development was too slow. In response, I ramped up the lead to full-time and added a part-time PM. But Founder A continued pushing for speed, despite real hurdles (OAuth integrations, etc.). • Shifting MVP Goalposts – Midway, Founder A concluded that an MVP wouldn’t cut it—we needed a more complete product to be competitive. This meant more engineering, more delays, and more of my own money spent on development. The Breaking Point Near the 1-year vesting mark, we had an opportunity: a paying client willing to fund an app. I didn’t have devs on the bench, so I asked Founder A to hold off our project briefly while I hired more engineers to avoid stalling either effort. This was the final straw. Founder A (with Founder C somewhat aligned) decided the arrangement wasn’t working—citing past disagreements and the “slowness” issue. The decision was made to end the partnership. Now, Founder A, as majority holder, is requesting a full handover of the code, Founder C is indifferent, and all engineering costs I covered are essentially lost. Key Takeaways (So Far) Crystal-Clear Agreements Upfront – A formalized product roadmap and timeline should’ve been locked in from day one. Business Needs > Engineering Standards – I wanted to build something solid and scalable, but in an early-stage startup, speed to market is king. This was before AI tools became mainstream, so our approach wasn’t as optimized. Don’t Overextend Without Protection – I personally financed all engineering, but without clear safeguards, that investment became a sunk cost. Expenses Must Be Distributed – I was solely covering engineering salaries, which created an imbalance in financial risk. Future partnerships should ensure costs are shared proportionally, rather than one person shouldering the burden. Where I Need Advice Looking back, I want to improve as an engineer, CEO, and co-founder. • What should I have done differently in structuring this partnership? • How do you balance engineering quality with the startup need for speed? • As a dev shop owner, how can I better navigate equity deals where I’m also bringing in engineering resources? I really appreciate everyone who went through this long post and provide any insights from founders, engineers, or anyone who has been in a similar situation. Thanks for reading! ===================================================================== For readers who might be thinking what set this type of expectation? Because I had a dev shop and I thought my co-founders will be understanding of my business circumstance and I was a bit trigger to build a product with a C-exec team, I gave the impression of "unlimited" engineering which I later realized down the line that it was not feasible for me. Something I learned that I have to be more careful with and set expectations accordingly from the very beginning. And from the feedback of the commenters here, I am much more aware what I should offer and how to set expectations, esp. in the early stages of execution. So thank you all! 🙏🏾 EDIT: I would like to thank everyone who contributed to this thread. You not only helped me but future founders who are considering to get into the startup scene!

I will not promote. I am looking for a collaborator to develop an AI agent.

Hi, I got an Idea and I am looking for someone to collaborate to develop an MVP. I am from Algeria (North Africa), I recently graduated from a university abroad. During my years of study a lot of people (mainly from non-western countries) reached out to me for helping them gather information about enrolling to universities. I helped a lot of the students, and a lot of them were available to pay me for it. There is a huge market for people from non-western countries wanting to study in western countries, and people in my country are available to pay 500 dollars for just getting the chance to get an admission and a visa to study aborad. We are talking generally about sons of rich dads who are lazy or lack information to do the procedure. The procedure to get enrolled is pretty repetitive, meaning that it can be replicated, and generally the universities ask for the same documents, with slightly different requirements. Based on this, I was thinking: Why not automating this? I already have a network of people that can test whatever this AI agent will look like. Now I am in a state in which I need a tech person (I am a techie too) to collaborate. I am serious, and I have personal savings that can be used for tech tools and frameworks to develop an MVP.

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

AI Might Be the Best Industry for Ambitious Lazy People i will not promote

Not here to promote, just talk about my experience with starting a new business. I'm not new to the game, so I was able to speed-run my new AI automation agency. I currently run a software company with a co-founder, and I recently decided to start a new AI and automation agency. I just had a private launch this week, and I already have a $2K client lined up, ready to buy, along with some other interested parties, as I have sales calls with them coming up. I found all of my leads after choosing a niche to focus on and using this tool I built that automatically scrapes IG data. My tool is “unique” because it automagically qualifies the leads with AI. It even has a custom frontend, and I used this tool as a case study to secure the client I have now, and I accomplished all of this in the span of about a week. Granted, I have a background in engineering, so picking up AI was easier for me, but anyone can do it. You can even use AI to learn AI. If you haven’t used AI in your business yet, I would strongly suggest getting into AI and automation. If you've been considering starting a business but don't know what business to start, take this as a sign to turn AI into a business. i will not promote

Feeling stuck—built a startup, got rejected from YC & IVI, met smarter people, and now I don’t know what to do. ( i will not promote ) I will not promote

I will not promote I don’t even know where to start, but I just feel completely stuck right now. I’m 20 years oldI don’t even know where to start, but I just feel completely stuck right now. I’m 20 years old, have been grinding non-stop for months, and it feels like I have nothing to show for it. I built an AI agent that automates workflows for businesses. I can build tech, but I can’t sell. That’s been my biggest realization recently—I thought building would be enough, but it’s not. I need customers, I need a co-founder, I need to figure out the business side… and I have no idea how. I applied to YC, IVI at ISB, and EF, met a lot of insanely smart people—some were impressed with me and my work, but they were wiser, more experienced, and honestly, just better at all of this than I am. It made me realize how much I don’t know. I got rejected from YC & IVI. 💔 YC didn’t even give much feedback—just a standard rejection. 💔 IVI told me: “You're too young, you need more experience, and you should work with a team before trying to start something.” That hit me hard. I had already been struggling to find a co-founder, and this just made me wonder if I even belong in this space yet. The Frustrating Part? I KNOW my tool Has a Unique Edge. I’m not just another AI automation tool—I know my tool has a strong USP that competitors lack. It has the potential to be an AI employee for businesses, not just another workflow tool. But I still haven’t built the “perfect product” I originally envisioned. And that’s what’s eating at me. I see what it COULD be, but I haven’t made it happen yet. At the same time, the competition in the AI agent space is exploding. YC-backed companies are working on AI agent startups. OpenAI is making huge progress with Operator. Competitors are moving fast, while I feel stuck. I’ve delayed development because I’m unsure whether to double down, pivot, or just move on entirely. Where I’m Stuck Right Now 🔹 Do I keep pushing and try to crack sales somehow? 🔹 Do I join a startup as a founding engineer to get experience, make connections, and learn sales before trying again? 🔹 Do I move to Bangalore, meet founders, and figure out what’s next? 🔹 Do I pivot to something nicher instead of competing in the AI agent race? If so, how do I even find a niche worth pursuing? 🔹 Do I even belong in startups? Or am I just forcing something that’s not working? I feel stuck in a weird middle zone where I’m not a beginner, but I’m also not successful. I’ve done enough to see what’s possible, but not enough to make it real. Every rejection makes me question if I’m even on the right path. I don’t know if I’m posting this for advice or just to get it out of my system. Maybe both. Has anyone else felt like this before? If you’ve been in this situation—how did you figure out whether to keep going or move on? TL;DR: I’m 20, built an AI agent for automating workflows, got rejected from YC & IVI, met insanely smart and experienced people, realized I can build tech but can’t sell, struggling to find a co-founder, AI agent competition is growing, delaying development, confused about the future—don’t know whether to double down, pivot, or move on. The frustrating part? I\ know I have a unique edge that others lack, but I still haven’t built the perfect product I originally envisioned.* edit: removed the tool's name

I am considering starting a SaaS business that automates the creation of long-form SEO-optimized blog posts. Is this something you would find useful, as a business owner?

Trying to gauge the general interest level, from other entrepreneurs/business owners. The idea is, a tool that automates the process of creating long-form SEO optimized blog posts to promote your business -- perhaps creating entire batches of such posts, all from just one button click. Like if you could just describe your business, click a button, and BAM, it just outputs like an entire month's worth of absolutely fire SEO-optimized long-form blog posts? That would be super fucking convenient. Yes you can use ChatGPT for this, but the character limits make it so it can only output very short posts. Otherwise it requires first asking for an outline, then getting the different sections piecemeal and pasting it all together yourself. Still super time-consuming to do it that way. A GPT-based solution could probably automate the process I've hit upon in my own SEO blog-posting workflow -- where I output not just finished long-form blog posts, but also convert them into SEO-optimized HTML code so you can just paste it into your blog post website and have all the header tags etc set up for optimal SEO/keyword ranking purposes. Biggest counter-argument I make against this is, there are undoubtedly lots of companies already offering this. Doesn't mean I can't make money doing it. I just don't like entering super crowded marketplaces. Other main argument I have is, if I used my OpenAI account for this, there's the risk of some malicious/idiot user firing prompts that violate the OpenAI ToS and get me banned. I COULD have them input their own OpenAI API tokens, but that just adds adoption/usage barriers that would make it way harder to market/acquire initial customers. I guess I could sanitize the user inputs as a pre-processing step to block any obscene prompts or anything like that, but still, it's a risk. Let me know your thoughts on this idea. ASSUMING it worked effectively -- and made it very easy for you to just describe your business offerings / value propositions / target market(s), then get genuinely useful long-form SEO-optimized blog posts, is this something you'd be willing to pay for? If so, what dollar amount, to you, would seem reasonable? It would probably just be hosted on a website. Then you'd just copy the outputted final result for use as needed on your website. That would be the simplest way to do it. Technically it could function as like, a plugin for specific websites that maybe auto-posts them for you too -- it would be simpler, on my end, to start out doing this on a standalone website. (Might also make it easier to allow users to try it out, on first visit.) One last point -- MAYBE it would have an optional intermediate step, where it would first output the planned outline for the blog post, allowing you to pop in, quickly modify that, add your own thoughts / valuable ideas (to help make the blog post more unique, truly useful for readers, more your own) -- THEN you could finalize it and hit submit. Again, that's the workflow I've hit upon in my own semi-automated blog-posting workflow, and it's led to some pretty useful long-form content that isn't just, boring garbage, but contains lots of genuinely useful ideas that I would include in my own uniquely-created blog posts on the subject. But instead of me taking the time to write it, I just kinda toss in a few quickly typed out ideas to expand upon, and ChatGPT does the rest. Imagine that kind of optional / customizable workflow, but the rest of it is fully automated. OR you could just get the fully automated blog posts with no revisions on your part. Thanks!

Nuts and bolts AI implementation for small business

How can small businesses use AI to increase sales or decrease expenses without massive disruption? One way for us is using AI to process our email history to identify patterns and write personalized messages based on past correspondence. According to legal advice in which I have confidence, email that is personalized for each recipient (and meets other standards) does not need to be opt in. If you disagree - understood - but spam morality is not the topic here. Bottom line - obviously a game changer. Knowing phrases people have used before becoming clients - and all of the possible permutations of those phrases, and detecting where those phrases show up will make our sales and marketing many times more effective for a fraction of the cost. There's a reason big corps. record calls, and now small business can leverage the same technology. We are setting up a process that yields accurate, up to date, comprehensive data for our own business operations. Our clients - who are they and how has their demographic changed over time? To answer this question and for email personalization, we also need access to external data sources e.g. like accurate up to date company demographics. IMO - the leader in company data in the US? THEY SUCK. We found there is no magic fairy who is going to make good data appear for our AI. The process of applying our own proprietary knowledge to code and categorize the data is just as important, and obviously highly sensitive. How do we leverage the AI technologies of companies like Google and Microsoft (or anyone else) without being their bitch? Below is a list of some of the sources of my business's data: Data sources: PST/OST/Other Email data files Microsoft data from Windows/O365 Windows/Linux/Android/IOS application logs and other data Web server logs for the company website. SEO/Analytics Data Google data export Google voice/VOIP logs OneDrive/G drive Other Phone system/cell service logs Other SAAS and in-house application data. Facebook/social media data for company pages. QuickBooks/other accounting systems/business bank account logs POS/Credit card processing systems/PayPal, etc. OSINT to fill in the blanks

Good at coding, bad at marketing. Summary

Hello. I posted a question on what to do if you are good at coding but bad at marketing four days ago, and I received so many responses and tips. The original post is here. I was really glad and excited to read comments. To return the favor to the community and add some more value, I’ve summarized all the comments I got on the original post. Here are they, with my personal comments on some of the advice I got. You’ll never believe it, but the most common advice was to learn. Really, the first and only thing you should start with if you’re bad at marketing is learning. Yet learning could be different. I highlighted 5 main areas. Educate yourself on general questions. Learn more about some basics. For example, start by finding out what the 4P’s of marketing are, and afterward, you’ll inevitably run into YouTube videos, seminars, Udemy courses, or any other resource that resonates with you on some ideas/avenues you could pursue. Read books and watch videos. There are tons of books on marketing and sales. People shared in the comments books by Dan Kennedy and “Cashvertising”, written by Drew Eric Whitman. (I’ve never heard of them, but already ordered on Amazon). For sales, the most common idea was to start with YouTube videos. For example, Alex Hormozi videos and Startup school delivered by Ycombinator videos. Check out Indie Hackers and scrutinize it for a piece of good advice from developers in the same situation. Also, there was advice to follow up and read some guy on Twitter. (Don't want to get unfairly banned from here, so won't post it) Educate yourself and hire a professional or find a co-founder to help you: Hire a seasoned marketer in this field to help you out. He will help you achieve cost-efficient scales. But it could be a real problem to find the right person. Marketing agencies are expensive. Try to look on LinkedIn or among your acquaintances. Look for professionals with credentials or extensive experience. Seek marketing referrals from startups of a similar size/industry. If you don't have those, try to bring a trusted/experienced marketer friend into the intro meetings to help assess whether the service provider knows what they are doing. Talented freelancers can often get the job done for less than hiring an entire agency. Look for a co-founder who is savvy in marketing, passionate, and ready to work hard towards mutual success. Educate and DIY Being the face of your business is way better than having faceless communication. The startup checklist is made based on the comments is next: At least have your product defined. Define your target audience. Set up the goals you want to achieve. Make domain expertise and understand the market and the direction of its development. The next stage is answering tricky questions: Have you created a business model? How do you plan to compete? What’s your unique selling point? How much do you plan to budget for marketing? Are you planning to work alone, or will you need other devs? Then you start thinking about clients… You need the exposure to truly understand the customer's pain points and build a product that they love. You need to think about how your clients would think, and you should tailor each step you take for them. Get feedback from your early users if you already have a product. Interview your potential customers to learn how they buy. This will help you narrow your choice of marketing channels. Get your product or service used by several startups and help them achieve their goals. Endorsements are very valuable marketing assets. You need a landing to validate your value proposition and start sending traffic, or you can run meta instant form campaigns... It would depend on the category of your startup. You need a benchmark of the competition's ads both in Meta and Google, blog posts, domain authority, their landing page, and average search volumes. Do affiliate marketing for your product since it's an effective strategy. Educate and use AI tools for dealing with marketing. Build an LLM-based product to automate marketing. (Sounds like an idea for a startup, right?) Learn following ChatGPT advice. In 1–3 months, you will be another updated person. Look at marketowl, an AI marketing department for startups and microbusinesses that have no budget or time to do marketing. It will automate the basic tasks your business needs, but it doesn't require your marketing expertise. Check out AI tools that are delivering very good marketing content (gocharlie, jasper, copyai). Educate yourself and run socials Start a blog or YouTube channel where you can share your expertise in coding or anything else you are good at and how your product simplifies life. Engage with your audience on social media platforms like Instagram and LinkedIn, where you can showcase your industry knowledge. Start a page on Twitter and an account on Reddit. Follow and read subreddits and pages where your potential customers are. Learn the pain from the inside. Do not simply promote, people will lose interest immediately. Start by taking focused time to create informational content, so people will eventually be naturally intrigued by what you do and want to support you when they start to “know” you. Educate your potential users about the value of your product. Create content based on what ideal customers are asking at the various stages of marketing. e.g., if they are at the beginning of the process, they may use basic language; if they are further down the process, maybe they’ll be specific. Try to get on podcasts and build as many social links as you can. In other words, don’t live in a shell! Post regularly, and eventually you’ll find sites or people that are willing to promote for you. I omitted here all personal help offers and newsletters, however you could find them in the original post. Hope that will be helpful!

Service to create professional voice prompts for simple IVR? -No AI-

Hi everyone, have any of you used a service to create voice prompts for your answering IVR service? I’ve tinkered with the available AI options, even using custom code to slow speech, speed it up, and to change the phonetics of words to better match human inflection but it still sounds like AI at the end of the day. I would like to find a cheap/affordable service to create professional sounding prompts for me. I’ll write the scripts, not much to it, maybe 5-6 different prompts. Anyone suggestions? Edit to clarify: looking for humans, not AI

The Birth of My First (and Hilariously Flawed) Voice Agent: A Tale of No-Code Chaos

Okay Reddit, buckle up. I'm about to tell you the saga of how I birthed my very first voice agent, a chaotic and frankly, slightly embarrassing journey involving Retell.ai, Make.com, and Zapier. Looking back, it's equal parts hilarious and traumatizing. The Naive Dream: Back then (it feels like ages ago!), I was convinced I could easily whip up a voice agent that would take restaurant orders over the phone. Elegant, efficient, and completely automated! I envisioned a world where my clients' restaurant never missed a beat, all thanks to my coding prowess... or rather, my no-code prowess. How wrong I was. The Gauntlet Begins: Retell.ai's Murky Depths Retell.ai was the starting point, the "voice" of my operation. Getting the phone number hooked up felt like a small victory, quickly overshadowed by the realization that their documentation was... well, let's just say it wasn't written for complete novices. I spent what felt like an eternity staring at API keys, convinced I'd entered them correctly, only to be greeted by cryptic error messages. The sheer frustration I felt wrestling with that initial setup is something I'll never forget. Make.com: From Pretty Picture to Painful Puzzle Then came Make.com, the orchestra conductor of my workflow. It looked so beautiful, so user-friendly! Drag and drop, visual modules... what could go wrong? Oh, so much could go wrong. Trying to decipher the JSON data stream from Retell was like trying to understand a foreign language I only knew a few words of. Mapping that data to a Google Sheet? A complete and utter disaster. I remember spending hours just trying to get the correct fields to populate, each failed attempt fueling my growing despair. Zapier: Briefly Considered, Quickly Dismissed I flirted with the idea of using Zapier instead, seduced by its simplicity. But its limitations became glaringly obvious when I tried to build the complex, multi-step process I needed. Make.com was the only real option, which meant diving headfirst into a whole new world of modules, triggers, and data transformations. The Infernal Testing Loop: The absolute WORST part of the entire process was the testing. Picture this: Calling the agent, rambling through a mock order, waiting for the workflow to execute, only to discover (yet another) error. Then, tweaking the scenario, pushing "save," and repeating the entire agonizing process. Each test call felt like a mini-marathon, a grueling race against time and my own dwindling patience. The AI's... Quirks: And then there was the AI itself. It was... let's just say it had a personality of its own. Sometimes, it perfectly understood my order. Other times, it decided I wanted to order 500 pizzas with extra anchovies. Debugging the AI's interpretation felt like negotiating with a stubborn toddler. Lessons Hard-Learned (And Forever Etched in My Memory): Start absurdly small: I tried to build a fully functional system right away. A HUGE mistake. If I could go back, I would have focused on just extracting one piece of information (like, say, just the quantity) and gotten that rock solid before adding anything else. JSON is your friend (or should be): Back then, JSON felt like alien code. Now, I have a slightly better grasp on it. Trust me, learn JSON. It will save you so much pain. Test like your sanity depends on it: Because it does. After every. Single. Change. Test the entire flow. It's tedious, but it's the only way to catch errors before they snowball into a catastrophe. Don't suffer in silence: I tried to be a lone wolf, figuring everything out myself. Big mistake. Retell.ai's forums and Make.com's documentation are goldmines. Use them! Embrace the struggle: This is the most important lesson. Building a voice agent, especially your first one, is hard. It's frustrating. It will test your limits. But don't give up. The feeling of finally making it work (even partially) is worth it. The Bot That (Barely) Lived: In the end, I did create a voice agent that could take orders and log them into a spreadsheet. It wasn't pretty. It was buggy. It occasionally ordered things that didn't make any sense. But it was mine. And it was the first step on a long and winding road. Looking back, I laugh (and cringe) at my naivety. But I also appreciate the lessons I learned and the sheer grit it took to bring my little AI Frankenstein to life. Anyone else have a similar "first bot" story? Let's hear them! Misery (and laughter) loves company. #RetellAI #Makecom #Zapier #FirstBot #NoCodeFail #VoiceAgentStruggles #StoryTime

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

Feedback: Building a no-code platform to help users build GenAI functionalities within their existing product. Would you use it?

I’m building a product which allows users to build GenAI capabilities (currently: summaries, synthetic data generation and knowledge base querying) into their existing products without the need to code. You can either upload data from files or set up a webhook to read from an API and it constantly keeps updating results (served both on the dashboard as well as through api). You can also rapidly prototype by switching models (currently: GPT, Claude and Gemini). Either use our api keys (used for prototyping) or, provide your own API keys (built for enterprise), so you don’t pay for token consumption. If you are a developer/ non-tech person/ work for an enterprise, would love your thoughts on the idea along with how much would you pay for a product like this. Thanks in advance!

Idea Validation Post: Seeking Feedback on My AI-Driven Quick Launch Application! 🚀

Hey Members! I’m excited to share an idea for a new application I’m planning to build: Quick Launch . This AI-driven platform is designed to assist solopreneurs or anyone with an idea in launching their Minimum Viable Products (MVPs) by taking on the roles of the entire team needed for the process. Goal: Assistance in quickly moving from Idea to MVP Before I dive into the details, I’d love to hear your thoughts and feedback. Key Features: Product Creation: From Idea to Product Detailing AI-Generated Q&A: Real-time questions generation one-at-a-time to define the product requirements based on their knowledge levels to convert an Idea into a Product. Market Research Reports: In-depth analysis that identifies product-market fit, competitive landscape, and potential marketing strategies. Sentiment Analysis: Evaluation of user feedback and reactions across multiple subreddits to gauge public opinion on ideas. Product Development: Product Detailing to Actual Product User Story Generation: Identification and creation of comprehensive user stories, tasks, and sub-tasks to facilitate development. AI Project Management: AI agents assume roles of project managers and UI/UX designers to streamline product detailing and development. Integration Capabilities: Seamless integration with popular project management tools like Jira, Asana, and Trello for better workflow management. Target Audience: Solopreneurs: Individuals looking to bring their business ideas to life without extensive resources. Indie Hackers: Entrepreneurs focused on building small projects or startups with minimal overhead. Idea Validators: Anyone with a concept seeking initial validation and market feedback before committing significant resources. If you’re interested in learning more, check out our teaser website: Quick Launch Discussion Question: What features would you find most valuable in an application like this? Are there specific pain points you face when launching an MVP? Your insights would be incredibly helpful as I refine this idea! Looking forward to your thoughts! 🙌

The Future of AI in eCommerce Marketing: What to Expect 🚀

Hey Reddit community! As we dive deeper into 2025, the integration of AI in eCommerce marketing is becoming more sophisticated and impactful. Here’s a look at where AI is headed and how it's revolutionizing the industry: Personalized Shopping Experiences: AI is enhancing personalization by analyzing consumer behavior and preferences, allowing retailers to offer tailored recommendations and promotions. This not only boosts customer satisfaction but also increases conversion rates. Chatbots and Virtual Assistants: AI-powered chatbots are becoming more intuitive and capable of handling complex queries, providing 24/7 customer support, and improving overall user experience. They’re a game-changer for eCommerce businesses looking to enhance customer engagement. Predictive Analytics: With AI, businesses can leverage predictive analytics to forecast trends, optimize inventory, and refine marketing strategies. This helps in making data-driven decisions that align with consumer demands and market dynamics. Automated Content Creation: AI tools are being used to generate product descriptions, social media posts, and even ad copy. This automation saves time and ensures consistency across marketing channels. Visual and Voice Search: AI is powering visual and voice search capabilities, making it easier for consumers to find products using images or voice commands. This technology is set to transform how users interact with eCommerce platforms. Fraud Detection: AI algorithms are improving fraud detection by analyzing transaction patterns and identifying anomalies. This is crucial for maintaining trust and security in online shopping. As AI continues to evolve, it will undoubtedly reshape the eCommerce landscape, offering new opportunities for innovation and growth. What are your thoughts on the future of AI in eCommerce marketing? Let's discuss!

Am I Offering Too Many Services as a New Agency? Need Advice!

Hey everyone, I recently made a big decision to close my marketing agency (which was doing well) and reopen with my partner, who’s a talented graphic designer specializing in logos and branding. We’re excited to start fresh, but I’m worried we might be biting off more than we can chew. Our current plan is to offer a wide range of services, including: Graphic Design (logos, branding, social media graphics) Web Design & Development (landing pages, e-commerce, custom websites) Digital Marketing (SEO, PPC, email marketing, social media management) Copywriting (website copy, blogs, product descriptions) AI Solutions (chatbots, virtual assistants) To make it easier for clients, we’ve grouped these services into 3 main packages: Business Packages (websites, branding, and marketing essentials) Branding Packages (logos, brand identity, and design assets) Social Media Packages (content creation, management, and strategy) I used to focus solely on marketing, but now we’re combining our skills to offer a full-service experience. While this feels like a natural progression, I’m concerned about spreading ourselves too thin, especially as a new agency. Has anyone been in a similar situation? Should we narrow our focus initially and expand later, or is offering a broad range of services (with clear packages) a good strategy to attract more clients? Any advice or experiences would be super helpful! Thanks in advance!

Ai C-Level team

I've been exploring ways to run a company where I'm essentially the only internal team member, relying entirely on a suite of specialized AIs for executive roles, supported occasionally by external consultants for niche expertise. My goal is to stay lean, agile, and highly creative, especially in a fashion/tech brand context. Essentially, I'm building an AI-driven C-Level team, or what I like to call a "C-Level AI Wallet." Here's what I'm thinking for the key executive roles I'd need to cover with AI: CEO AI – Responsible for overall strategy, decision-making, trend analysis, and guiding the company's vision. I'd probably lean on something advanced like Gemini, GPT-4, or similar models, fine-tuned with market-specific data. COO AI (Operations): I'd need tools that streamline and automate logistics, supply chain management, and day-to-day operations (think something along the lines of Zapier AI integrations or Make). CMO AI (Marketing & Content): For branding, content creation, digital marketing, and consumer insights, I'd use Jasper or Copy.ai, combined with predictive analytics tools like Google Vertex AI to understand trends better. Additionally, for generating engaging visual and multimedia content, tools like Midjourney, DALL·E, Adobe Firefly, and Runway ML would be perfect. CFO AI (Financial Management): For financial management, cash flow control, and investment decisions, I'd probably leverage AI tools like Bloomberg GPT, combined with AI-powered forecasting platforms. CHRO AI (Human Resources & Culture): Although the internal team is minimal (just myself!), I'd still rely on AI for tasks like project management, freelancer hiring, and performance tracking—tools like HireVue AI, Motion, or even Notion's AI could be beneficial here. CSO AI (Sustainability & Compliance): Since sustainability and ethical sourcing are critical, I'd integrate ESG-focused AI tools to ensure transparency and responsible sourcing. My idea is that, with the right AI tools seamlessly integrated, I can manage the strategic vision and creative direction personally, leveraging external consultants only when necessary. This setup would ideally allow me to operate as a one-person internal team supported by a robust "wallet" of AI executives. Has anyone tried a similar approach? What AI tools would you recommend for a truly lean, innovative brand structure? I'm very curious about your experiences or suggestions—let me know your thoughts!

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

My clients are obsessed with AI and it's driving me nuts – are there any actually useful AI tools for service businesses?

I have a roster of a few home service companies (plumbers, roofers, landscapers, etc.) that I do freelance marketing for. Lately, the owners I work with have developed a serious case of AI shiny object syndrome. They’re bombarding me with links to scammy IG ads for “game-changing” AI tools they think will save their businesses overnight. Even talking about replacing their CSRs with "virtual agents". This will obviously lead to some terrible customer experiences, but all they can see is dollar signs at the prospect of laying off that part of their labor force. If I keep pushing back and pointing out how short sighted some of these ideas are, they’ll eventually find someone else that will implement them. So, I’m trying to get out in front of this a little bit and find any AI tools that don’t suck—something I can pitch back to them that’s actually useful and not just a fancy new way to ruin their customer experience. Then when they brag to their other buddies in the trades about how "cutting edge" their business is, it will be in part because of me, not in spite of me. Any suggestions for AI tools that: Help small service businesses without completely alienating their customers? Automate repetitive tasks in a way that doesn’t scream “this was done by a robot”? Aren’t just some scammy overpriced subscription service with a flashy demo? If you’ve actually used something that works, I’d love to hear about it. Honestly, the bar is low. Just help me stop these guys from accidentally burning their businesses down with bad AI ideas.

Nuts and bolts AI implementation for small business

How can small businesses use AI to increase sales or decrease expenses without massive disruption? One way for us is using AI to process our email history to identify patterns and write personalized messages based on past correspondence. According to legal advice in which I have confidence, email that is personalized for each recipient (and meets other standards) does not need to be opt in. If you disagree - understood - but spam morality is not the topic here. Bottom line - obviously a game changer. Knowing phrases people have used before becoming clients - and all of the possible permutations of those phrases, and detecting where those phrases show up will make our sales and marketing many times more effective for a fraction of the cost. There's a reason big corps. record calls, and now small business can leverage the same technology. We are setting up a process that yields accurate, up to date, comprehensive data for our own business operations. Our clients - who are they and how has their demographic changed over time? To answer this question and for email personalization, we also need access to external data sources e.g. like accurate up to date company demographics. IMO - the leader in company data in the US? THEY SUCK. We found there is no magic fairy who is going to make good data appear for our AI. The process of applying our own proprietary knowledge to code and categorize the data is just as important, and obviously highly sensitive. How do we leverage the AI technologies of companies like Google and Microsoft (or anyone else) without being their bitch? Below is a list of some of the sources of my business's data: Data sources: PST/OST/Other Email data files Microsoft data from Windows/O365 Windows/Linux/Android/IOS application logs and other data Web server logs for the company website. SEO/Analytics Data Google data export Google voice/VOIP logs OneDrive/G drive Other Phone system/cell service logs Other SAAS and in-house application data. Facebook/social media data for company pages. QuickBooks/other accounting systems/business bank account logs POS/Credit card processing systems/PayPal, etc. OSINT to fill in the blanks

Idea Validation Post: Seeking Feedback on My AI-Driven Quick Launch Application! 🚀

Hey Members! I’m excited to share an idea for a new application I’m planning to build: Quick Launch . This AI-driven platform is designed to assist solopreneurs or anyone with an idea in launching their Minimum Viable Products (MVPs) by taking on the roles of the entire team needed for the process. Goal: Assistance in quickly moving from Idea to MVP Before I dive into the details, I’d love to hear your thoughts and feedback. Key Features: Product Creation: From Idea to Product Detailing AI-Generated Q&A: Real-time questions generation one-at-a-time to define the product requirements based on their knowledge levels to convert an Idea into a Product. Market Research Reports: In-depth analysis that identifies product-market fit, competitive landscape, and potential marketing strategies. Sentiment Analysis: Evaluation of user feedback and reactions across multiple subreddits to gauge public opinion on ideas. Product Development: Product Detailing to Actual Product User Story Generation: Identification and creation of comprehensive user stories, tasks, and sub-tasks to facilitate development. AI Project Management: AI agents assume roles of project managers and UI/UX designers to streamline product detailing and development. Integration Capabilities: Seamless integration with popular project management tools like Jira, Asana, and Trello for better workflow management. Target Audience: Solopreneurs: Individuals looking to bring their business ideas to life without extensive resources. Indie Hackers: Entrepreneurs focused on building small projects or startups with minimal overhead. Idea Validators: Anyone with a concept seeking initial validation and market feedback before committing significant resources. If you’re interested in learning more, check out our teaser website: Quick Launch Discussion Question: What features would you find most valuable in an application like this? Are there specific pain points you face when launching an MVP? Your insights would be incredibly helpful as I refine this idea! Looking forward to your thoughts! 🙌

What CRM system works best for commercial loan brokers?

Setting up any business model needs a solid CRM that can also work with other software tools that automate the back office. In this new tech world AI has become a good tool that can help find this answers many entrepreneurs are looking for to maximize their time. So I recently asked and AI system the question on this post title and it came up with this: Selecting the right Customer Relationship Management (CRM) system is crucial for commercial loan brokers to efficiently manage client relationships, streamline loan processes, and enhance overall productivity. Here are some CRM solutions tailored for commercial loan brokers: • AscendixRE CRM for Capital Markets • BNTouch Mortgage CRM • LendingWise CRM • Salesforce Financial Services Cloud I personally do not have experience with these, but I used NetSuite for many years for a different industry and it great but it is very expensive for a small business. If you work in this space or have experience with CRMs, what works best yet affordable?

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

What to look for in the Best PDF Invoice Parser?

I've been thinking about starting using PDF Invoice Parser, so these are some key features to look out for in a PDF invoice parser I've learned about these days on Affinda. Machine Learning - There are invoice parsers available that use machine learning algorithms to learn from their mistakes, resulting in them being able to parse many data sources and become more accurate over time. Optical Character Recognition - An OCR invoice parser is one that uses optical character recognition to take images lacking text data and turn them into digital files. Natural Language Processing - This results in more efficient and effective invoice processing that seeks to understand the text and sort invoice fields correctly. Artificial Intelligence - Many parsers struggle to adapt and fail to complete information extraction from nonstandard invoice formats. That’s why you need a parser that leverages document AI to analyze the template and extract structured data no matter what invoice layout is used. Different Types Analysed - For example, you might receive a mailed invoice or Word document. You need a parser that can analyze and get extracted data from any format of the supplier invoice. So, is this enough information and benefits for me to choose this product? I guess so, I've even heard great stuff about it, but I would love to share all of this with you and maybe some of you already had any experience to share with all of us. Have a nice day, guys!

Ai C-Level team

I've been exploring ways to run a company where I'm essentially the only internal team member, relying entirely on a suite of specialized AIs for executive roles, supported occasionally by external consultants for niche expertise. My goal is to stay lean, agile, and highly creative, especially in a fashion/tech brand context. Essentially, I'm building an AI-driven C-Level team, or what I like to call a "C-Level AI Wallet." Here's what I'm thinking for the key executive roles I'd need to cover with AI: CEO AI – Responsible for overall strategy, decision-making, trend analysis, and guiding the company's vision. I'd probably lean on something advanced like Gemini, GPT-4, or similar models, fine-tuned with market-specific data. COO AI (Operations): I'd need tools that streamline and automate logistics, supply chain management, and day-to-day operations (think something along the lines of Zapier AI integrations or Make). CMO AI (Marketing & Content): For branding, content creation, digital marketing, and consumer insights, I'd use Jasper or Copy.ai, combined with predictive analytics tools like Google Vertex AI to understand trends better. Additionally, for generating engaging visual and multimedia content, tools like Midjourney, DALL·E, Adobe Firefly, and Runway ML would be perfect. CFO AI (Financial Management): For financial management, cash flow control, and investment decisions, I'd probably leverage AI tools like Bloomberg GPT, combined with AI-powered forecasting platforms. CHRO AI (Human Resources & Culture): Although the internal team is minimal (just myself!), I'd still rely on AI for tasks like project management, freelancer hiring, and performance tracking—tools like HireVue AI, Motion, or even Notion's AI could be beneficial here. CSO AI (Sustainability & Compliance): Since sustainability and ethical sourcing are critical, I'd integrate ESG-focused AI tools to ensure transparency and responsible sourcing. My idea is that, with the right AI tools seamlessly integrated, I can manage the strategic vision and creative direction personally, leveraging external consultants only when necessary. This setup would ideally allow me to operate as a one-person internal team supported by a robust "wallet" of AI executives. Has anyone tried a similar approach? What AI tools would you recommend for a truly lean, innovative brand structure? I'm very curious about your experiences or suggestions—let me know your thoughts!

ChatGPT for business automation (incredible new AI)

Hey fellow small business owners! I'm curious to know how you would use ChatGPT or other AI automation tools to improve your business. For those who are not aware, recently a new chat AI was made available to the public by OpenAI, called ChatGPT. (same company that did Dall-E) In a tweet Elon Musk wrote that "ChatGPT is scary good. We are not far from dangerously strong AI." It allows anyone (regardless of tech skill) to simply type commands and it will spit out answers. It can also create actual working code. For example most tasks you do in a browser can be automated with a Python script, but it takes time and coding knowledge to create. With ChatGPT you can just tell it what you want and it will create the code! The impact for businesses is insane: 1) Your entire customer service can be easily replaced by chat bots and probably soon by AI that can speak over the phone (google showcased this in 2018, it already exists). 2) you can have the AI automate your sales process, creating a 1-on-1 conversations, at scale. It can probably also improve and optimize it's closing rate over time as it learns more about your customers. 3) It can be used to train your staff. It's really good for 1on1 instruction and teaching because it will go a the students pace and answer questions (compare that to the usual PowerPoint presentation people use) 4) Since it can create code to automate most tasks a human can do in a browser, you can create for example bots that take customer orders and automatically import them to whatever shipping system you use, send customers tracking info etc. (a lot of this stuff is done with software and APIs, but now anyone can create their own, custom solutions) I feel like we hit an inflection point in 2022 with AI and now we are beginning to see some really useful stuff coming out. Am I crazy or are we about to see a massive shift in how we do things?

What AI Tools Would You Like to See on a Dashboard for Small Businesses?

Hello r/smallbusiness, I’m curious to learn more about what small business owners think about AI tools. If there was a dashboard specifically designed for small businesses, what kind of AI tools or features would you find most useful? • What kind of AI-driven features would help you the most? (e.g., sales forecasting, customer insights, automated marketing, inventory management) • What are your biggest challenges that you think AI could address? • How important is ease of use and integration with your current systems? • Have you used any AI tools before? If so, which ones were helpful or not so helpful? Looking forward to hearing your thoughts and experiences!

Exploring AI & Automation Options for handling calls!

Running a business solo is a grind, and one of the biggest challenges I have faced is handling calls while staying productive. I’d be in the middle of deep work, and suddenly, baam the phone rings. I have tried using a VA (virtual assistant), but the costs are just adding up, and they aren’t always available. Hiring full-time! Way too expensive. Lately, I have been thinking of getting AI-powered solutions that act as virtual receptionists—handling inquiries, scheduling appointments, and even answering customer questions that will not be too expensive. I came across this AI receptionist software called My AI Front Desk. It looks pretty cool – handles calls, booking appointments, even does customer support 24/7. I'm thinking about giving it a shot, but I'm curious if anyone else has used AI for this kind of stuff? What's your experience been like? How do you handle incoming calls? Have you tried automation or AI assistants? Curious to hear what’s worked for you!

Do You Believe AI Will Change the Game for Small Businesses?

Hey, folks! I operate a small business specializing in preparing dancers for competitions. As our business has grown recently, managing orders and client communications has become increasingly challenging. Initially, we considered hiring a social manager to handle these tasks manually. However, we opted for a more innovative approach. We set up an AI chatbot to automatically gather all information from our clients regarding the services they want to receive and send it to our management system. This automation was extremely convenient for us. I'm curious to hear about your experiences with such tools. Have you already integrated them, and are they useful to you? I know such tools are commonly used in customer support, but have you explored their usefulness in other areas?

AI Consulting for Small Businesses: Your Thoughts? Looking for feedback from small businesses.

I'm an AI consultant helping small businesses like yours leverage AI to boost efficiency and save money. I offer tailored solutions to address your unique needs, whether it's automating tasks, improving customer service, or optimizing sales. This is information will be used to help us improve our message and products. We are not looking to sell anyone. We just need honest opinions like a focus group. Thank you. I'm curious: *What are your biggest pain points in your business? *What solutions would you like technology to solve for you? What AI challenges are you facing? (e.g., automation, data analysis, customer support) Would you consider an AI consultation? Why or why not? What outcomes are most important to you? (e.g., increased revenue, cost savings, improved customer satisfaction) What concerns you about AI adoption? (e.g., cost, implementation, data privacy) How do you see AI impacting your business's future? Thank you for your feedback.

Is anyone using and getting reliable results from AI for social media, and automating some tasks in the business?

Hi, We are currently paying £600/month for a social media company to do a pretty meh job at promoting us, by just doing some posts on our socials I am just wondering if anyone has used AI to help with this and if so what do you use. I've looked at Blaze but I'm put off by their marketing and then Sintra looks interesting but hoping for some feedback from people that have used it, or any others!

My clients are obsessed with AI and it's driving me nuts – are there any actually useful AI tools for service businesses?

I have a roster of a few home service companies (plumbers, roofers, landscapers, etc.) that I do freelance marketing for. Lately, the owners I work with have developed a serious case of AI shiny object syndrome. They’re bombarding me with links to scammy IG ads for “game-changing” AI tools they think will save their businesses overnight. Even talking about replacing their CSRs with "virtual agents". This will obviously lead to some terrible customer experiences, but all they can see is dollar signs at the prospect of laying off that part of their labor force. If I keep pushing back and pointing out how short sighted some of these ideas are, they’ll eventually find someone else that will implement them. So, I’m trying to get out in front of this a little bit and find any AI tools that don’t suck—something I can pitch back to them that’s actually useful and not just a fancy new way to ruin their customer experience. Then when they brag to their other buddies in the trades about how "cutting edge" their business is, it will be in part because of me, not in spite of me. Any suggestions for AI tools that: Help small service businesses without completely alienating their customers? Automate repetitive tasks in a way that doesn’t scream “this was done by a robot”? Aren’t just some scammy overpriced subscription service with a flashy demo? If you’ve actually used something that works, I’d love to hear about it. Honestly, the bar is low. Just help me stop these guys from accidentally burning their businesses down with bad AI ideas.

Has automation or AI actually impacted your business?

For the better or the worse, how's AI impacted your business? Have you been able to automate anything you used to spend tons of hours in your day to day operations? I am genuinely curious and I am interested in getting into the agency or consulting side of business. I want to know if there's actual demand for business owners who aren't too tech savvy?

Is AI a Game-Changer for Small Businesses or Just Another Hype?

Big companies are going all-in on AI, but is it actually useful for small businesses? From automated marketing to customer service chatbots, AI tools promise to save time and boost sales—but do they really? Have you used AI in your business? Was it a win or a waste of time?

AI Consulting for Small Businesses: Your Thoughts? Looking for feedback from small businesses.

I'm an AI consultant helping small businesses like yours leverage AI to boost efficiency and save money. I offer tailored solutions to address your unique needs, whether it's automating tasks, improving customer service, or optimizing sales. This is information will be used to help us improve our message and products. We are not looking to sell anyone. We just need honest opinions like a focus group. Thank you. I'm curious: *What are your biggest pain points in your business? *What solutions would you like technology to solve for you? What AI challenges are you facing? (e.g., automation, data analysis, customer support) Would you consider an AI consultation? Why or why not? What outcomes are most important to you? (e.g., increased revenue, cost savings, improved customer satisfaction) What concerns you about AI adoption? (e.g., cost, implementation, data privacy) How do you see AI impacting your business's future? Thank you for your feedback.

Is anyone using and getting reliable results from AI for social media, and automating some tasks in the business?

Hi, We are currently paying £600/month for a social media company to do a pretty meh job at promoting us, by just doing some posts on our socials I am just wondering if anyone has used AI to help with this and if so what do you use. I've looked at Blaze but I'm put off by their marketing and then Sintra looks interesting but hoping for some feedback from people that have used it, or any others!

My clients are obsessed with AI and it's driving me nuts – are there any actually useful AI tools for service businesses?

I have a roster of a few home service companies (plumbers, roofers, landscapers, etc.) that I do freelance marketing for. Lately, the owners I work with have developed a serious case of AI shiny object syndrome. They’re bombarding me with links to scammy IG ads for “game-changing” AI tools they think will save their businesses overnight. Even talking about replacing their CSRs with "virtual agents". This will obviously lead to some terrible customer experiences, but all they can see is dollar signs at the prospect of laying off that part of their labor force. If I keep pushing back and pointing out how short sighted some of these ideas are, they’ll eventually find someone else that will implement them. So, I’m trying to get out in front of this a little bit and find any AI tools that don’t suck—something I can pitch back to them that’s actually useful and not just a fancy new way to ruin their customer experience. Then when they brag to their other buddies in the trades about how "cutting edge" their business is, it will be in part because of me, not in spite of me. Any suggestions for AI tools that: Help small service businesses without completely alienating their customers? Automate repetitive tasks in a way that doesn’t scream “this was done by a robot”? Aren’t just some scammy overpriced subscription service with a flashy demo? If you’ve actually used something that works, I’d love to hear about it. Honestly, the bar is low. Just help me stop these guys from accidentally burning their businesses down with bad AI ideas.

Is AI a Game-Changer for Small Businesses or Just Another Hype?

Big companies are going all-in on AI, but is it actually useful for small businesses? From automated marketing to customer service chatbots, AI tools promise to save time and boost sales—but do they really? Have you used AI in your business? Was it a win or a waste of time?

What I learn from my $200 MRR App I built 4 months ago?

4 month ago, I am just a 10-years experienced product manager without any software development experience. I have an $3K/month job, but I am so tired, I don’t like my life, don’t like my boss, don’t like my daily work, that make me feeling I already died however I am still living. I yearn for freedom and want to live each day the way I want to. So I quit my job, and become a Indie developer to build my own business, my own app, even my own life. I am so grateful for this time and experience, now my app reach $200 MRR, still very little compared to my previous salary, but I never regret. I have learned lots of things from this time and experience, more than I had in last 10 years. Here is the time-line of my App: \- Sep 2023: Launch first version to iOS App store \- Oct 2023: Release in-app-purchase features and have first subscriber, the revenue in October is $154 \- Nov 2023: Change from subscription to pay per use, and I did lots of marketing jobs in November, however, the revenue reduced to only $40. \- Dec 2023: Change back to subscription, and stop some invalid marketing jobs, only keep the ones that actually work. I almost did nothing in December, and the revenue come to $243. During this process, I have learned lots of things, there are some of them that I think could help you as well. Web or App My App is an iOS app that only can running on Apple’s device such like iPhone/iPad or Mac with Apple silicon. Many people ask me why my product is an iOS app not a website, because they don’t have any Apple device. It's true that promoting an app is much harder than promoting a website. However I am now very glad I made an App and not a website! If I make a website, I don't think it's possible to make $100 in the first month. My App is about keyword research, to help people find some ideas from search keyword, because every keyword people searched in Google are representing a real need of them, also can be used in SEO field. However there are a lot of website tools about keyword research, some of them are famous like Ahrefs, SEMrush… I have no intention of competing with them. Actually I don’t have any chance. While in app store, there are little apps about keyword research, each of them have terrible data and user experience, that means if my app has better data and experience that could be my chance. In fact, the App store brings me 20 organic installs a day that Google would never have been able to bring me if I had a website, at least for the first few months. Furthermore, Apple nearly did everything for developer, I don’t need to care about user login, payment and so on, Apple did everything, I just need to call their API, that save lots of time, if I build a website, I need to implement login and payment by myself, that would add some extra work. Not to mention I'd need to buy servers and domains, that would cost me a lot of money. Although Apple will take 30% of the revenue, I can live with that in the early stages because the most important thing for me is to get the product to market as soon as possible. Actually thought Apple’s SMB program, the take rate is 15% now. So Web or App is not important in the early stage, time is important, if people need my product, it's easy to make a website one. More Users or More Valuable Users In November, I notice some users would like use my app, and they were meet paywall, but they never subscribe. I provided 7 day free trail, but it seem that they don’t like it. So I decide to change subscription to pay per use. Because as a user, I don’t like subscription as well, pay per use seem like more friendly. So I change from subscription to pay per use. People can afford $9.99 to subscribe monthly for unlimited use or pay $1.99 for each data they want(First purchase is $0.99 then $1.99). I was expecting more user to pay, but it was the complete opposite! Some users who would have paid a higher subscription fee are switching to a lower priced single payment. Users are encountering paywalls more often, and each time they need to make a decision about whether or not to pay, which increases the probability that they will abandon payment. This resulted in a 75% decrease in revenue in November. In fact, the mostly of my revenue comes from a handful of long-cycle subscribers, such as annual subscription. \\Few bring in most of the revenue,\\ that is the most important thing I learned. You don't need a lot of customers, you just need more valuable ones. That's why it's only right to design a mechanism to filter out high-value customers and focus on them, all the things you want do is just let more people into the filter, and from that point of view, subscription with free trial period is the best way, even if most people don't like it. The rule of 20/80 will always be there. The most important thing is always focus on the 20 percent things and people. Effort does not always guarantee rewards. Unless one engages in deep thinking, or most efforts are invalid. I have been working very hard to promote my product for a period of time. It’s about in November. I did a lot of job, such as write script to send message to my potential clients on Fiverr, post and write comments on others post on Reddit, find related questions and answer them on Quora, post and comments on Twitte, etc. During that period, I was exhausted every day, but the outcome did not meet my expectations. There is only little growth on App installation, even less revenue than before. That make me frustrated. I finally realized that If I need to put in a tremendous amount of effort just to make a little progress, there is must something wrong. So I stop 80% of promote work I have ever did, only keep app store search ad, which will bring a installation with less than $0.5 cost. Then I dive into long time and deeply thinking, I spent more time on reading books, investigate other product with great MRR, watch interviews with people who are already living the kind of life I aspire to live, for example, u/levelsio. These things have given me great inspiration, and my life has become easier. It seems that the life I anticipated when I resigned is getting closer. I also have a clearer understanding of my app. Meanwhile, MRR has been growing. This experience let me learn that effort does not always guarantee results. Many times, our efforts are just wishful thinking, they are invalid, do the right thing after deeply thinking is more important. What Next? My goal is reach $3K MRR, as same as my job payment, I will never stop to building things, and I will keep my currently lifestyle. I still don't know how to get more people to use my app, but levelsio's interviews give me some inspiration that I can verified something by manually instead of build a software. I plan to launch a trend analysis product based on the keyword data provided by my current app. I have always wanted to combine AI to build such a product, but I didn't know how to do it. Now I intend to manually complete it first and start software development once there are paying users. If you are interested to my App, you could try it.

Small Business Owners: How's AI Working (or Not) for You?

I'm interested in doing some "user research" to hear from the community on how AI fits into the small business landscape. Some SMB owners I talked to felt like "AI is a cool novelty, but it's not transformative". Curious how people here feel about AI, thanks. How are you using (or have used) AI in your business? Seen any ROI boosts? Hit any roadblocks or adoption challenges? What do you wish AI could do for your biz that it doesn't currently? (besides run everything lol)

I Accidentally Made My Mom Redundant at Her Office Job

At my tech job, AI assistants have boosted productivity so much we’ve almost stopped hiring. It made me wonder: why isn’t AI used more in small businesses? My mom works in the office of a small local manufacturing company, handling repetitive tasks like inputting orders into their ERP system. After shadowing her for a half day, I built an AI program that automates most of her work. Now she has so much free time, she’s watching Netflix at the office lol I’m thinking of quitting my job and starting my own small local business, offering this as a service to other small businesses in the era, but before I jump on it and quit my current job, I’d love to know if this is a more common issue. My main question are: What’s the most repetitive/time-consuming (computer) tasks you wish you could automate? If possible, could you break it down step by step with a lot of boring details ? 😅 Any hacks or tools you've found to make things easier so far? And maybe what else I should think on that I am missing before quitting my job and starting my own business?

Is AI a Game-Changer for Small Businesses or Just Another Hype?

Big companies are going all-in on AI, but is it actually useful for small businesses? From automated marketing to customer service chatbots, AI tools promise to save time and boost sales—but do they really? Have you used AI in your business? Was it a win or a waste of time?

ChatGPT for business automation (incredible new AI)

Hey fellow small business owners! I'm curious to know how you would use ChatGPT or other AI automation tools to improve your business. For those who are not aware, recently a new chat AI was made available to the public by OpenAI, called ChatGPT. (same company that did Dall-E) In a tweet Elon Musk wrote that "ChatGPT is scary good. We are not far from dangerously strong AI." It allows anyone (regardless of tech skill) to simply type commands and it will spit out answers. It can also create actual working code. For example most tasks you do in a browser can be automated with a Python script, but it takes time and coding knowledge to create. With ChatGPT you can just tell it what you want and it will create the code! The impact for businesses is insane: 1) Your entire customer service can be easily replaced by chat bots and probably soon by AI that can speak over the phone (google showcased this in 2018, it already exists). 2) you can have the AI automate your sales process, creating a 1-on-1 conversations, at scale. It can probably also improve and optimize it's closing rate over time as it learns more about your customers. 3) It can be used to train your staff. It's really good for 1on1 instruction and teaching because it will go a the students pace and answer questions (compare that to the usual PowerPoint presentation people use) 4) Since it can create code to automate most tasks a human can do in a browser, you can create for example bots that take customer orders and automatically import them to whatever shipping system you use, send customers tracking info etc. (a lot of this stuff is done with software and APIs, but now anyone can create their own, custom solutions) I feel like we hit an inflection point in 2022 with AI and now we are beginning to see some really useful stuff coming out. Am I crazy or are we about to see a massive shift in how we do things?

I’m sharing my learnings on how to use ChatGPT and other AI tools to generate leads, automate and grow my business.

Ok! I've been diving deep into how I can streamline and optimize my lead gen processes, and the things I've discovered have been mind-blowing. Recently came across a term called "EmotionAI". Wondered if anyone here has jumped on this and started implementing for lead gen? According to Exploding Topics, searches for "emotion AI" have increased by 525% over the past five years. Simply put, the tech can be used to provide more personalized experiences. And we all know that more personalized outreach means more likely conversions. As the AI market continues to grow, this will become increasingly mainstream. So, I thought why not share my learnings and real-life examples of how to use some these AI coupled with good ol’ chatGPT to grow. The first newsletter issue went out today. I plan to send every other Saturday but I might send every Saturday, still undecided. Anyway please check it out and subscribe if you want. Also let me know if you found it insightful.

The Rise of AI: Will It Signal the Demise of LinkedIn Automation as We Know It?

Have you ever received a spammy LinkedIn automation sequence that left a bad taste in your mouth? You're not alone. But what if LinkedIn automation could be used in a way that was actually useful and effective? As a busy small business owner, you don't have time to spend hours on LinkedIn every day, so automation can be a lifesaver. After trying out many LinkedIn automation tools, I realized that the biggest gap in the market was in the area of ultra-personalization. Most tools only offer basic personalization like name, job title, and location tags, but that's not enough to get the attention of busy prospects. That's where AI comes in. Imagine being able to scrape publicly available information like someone's bio, work experience, headline, education, and more, and then use AI to create an ultra-personalized outreach for each individual. This would be a game-changer for LinkedIn marketers. That's why I have built an online tool that does just that. With this tool, you'll be able to create highly personalized outreach messages that are customized for each person you're targeting. And, of course, it will be automated to save you time and effort. So what do you think? Would you be interested in using a tool like this to market your offer on LinkedIn? Let me know in the comments!

What AI Tools Would You Like to See on a Dashboard for Small Businesses?

Hello r/smallbusiness, I’m curious to learn more about what small business owners think about AI tools. If there was a dashboard specifically designed for small businesses, what kind of AI tools or features would you find most useful? • What kind of AI-driven features would help you the most? (e.g., sales forecasting, customer insights, automated marketing, inventory management) • What are your biggest challenges that you think AI could address? • How important is ease of use and integration with your current systems? • Have you used any AI tools before? If so, which ones were helpful or not so helpful? Looking forward to hearing your thoughts and experiences!

My clients are obsessed with AI and it's driving me nuts – are there any actually useful AI tools for service businesses?

I have a roster of a few home service companies (plumbers, roofers, landscapers, etc.) that I do freelance marketing for. Lately, the owners I work with have developed a serious case of AI shiny object syndrome. They’re bombarding me with links to scammy IG ads for “game-changing” AI tools they think will save their businesses overnight. Even talking about replacing their CSRs with "virtual agents". This will obviously lead to some terrible customer experiences, but all they can see is dollar signs at the prospect of laying off that part of their labor force. If I keep pushing back and pointing out how short sighted some of these ideas are, they’ll eventually find someone else that will implement them. So, I’m trying to get out in front of this a little bit and find any AI tools that don’t suck—something I can pitch back to them that’s actually useful and not just a fancy new way to ruin their customer experience. Then when they brag to their other buddies in the trades about how "cutting edge" their business is, it will be in part because of me, not in spite of me. Any suggestions for AI tools that: Help small service businesses without completely alienating their customers? Automate repetitive tasks in a way that doesn’t scream “this was done by a robot”? Aren’t just some scammy overpriced subscription service with a flashy demo? If you’ve actually used something that works, I’d love to hear about it. Honestly, the bar is low. Just help me stop these guys from accidentally burning their businesses down with bad AI ideas.

How I Started Learning Machine Learning

Hello, everyone. As promised, I'll write a longer post about how I entered the world of ML, hoping it will help someone shape their path. I'll include links to all the useful materials I used alongside the story, which you can use for learning. I like to call myself an AI Research Scientist who enjoys exploring new AI trends, delving deeper into understanding their background, and applying them to real products. This way, I try to connect science and entrepreneurship because I believe everything that starts as scientific research ends up "on the shelves" as a product that solves a specific user problem. I began my journey in ML in 2016 when it wasn't such a popular field. Everyone had heard of it, but few were applying it. I have several years of development experience and want to try my hand at ML. The first problem I encountered was where to start - whether to learn mathematics, statistics, or something else. That's when I came across a name and a course that completely changed my career. Let's start You guessed it. It was Professor Andrew Ng and his globally popular Machine Learning course available on Coursera (I still have the certificate, hehe). This was also my first official online course ever. Since that course no longer exists as it's been replaced by a new one, I recommend you check out: Machine Learning (Stanford CS229) Machine Learning Specialization These two courses start from the basics of ML and all the necessary calculus you need to know. Many always ask questions like whether to learn linear algebra, statistics, or probability, but you don't need to know everything in depth. This knowledge helps if you're a scientist developing a new architecture, but as an engineer, not really. You need to know some basics to understand, such as how the backpropagation algorithm works. I know that Machine Learning (Stanford CS229) is a very long and arduous course, but it's the right start if you want to be really good at ML. In my time, I filled two thick notebooks by hand while taking the course mentioned above. TensorFlow and Keras After the course, I didn't know how to apply my knowledge because I hadn't learned specifically how to code things. Then, I was looking for ways to learn how to code it. That's when I came across a popular framework called Keras, now part of TensorFlow. I started with a new course and acquiring practical knowledge: Deep Learning Specialization Deep Learning by Ian Goodfellow Machine Learning Yearning by Andrew Ng These resources above were my next step. I must admit that I learned the most from that course and from the book Deep Learning by Ian Goodfellow because I like reading books (although this one is quite difficult to read). Learn by coding To avoid just learning, I went through various GitHub repositories that I manually retyped and learned that way. It may be an old-fashioned technique, but it helped me a lot. Now, most of those repositories don't exist, so I'll share some that I found to be good: Really good Jupyter notebooks that can teach you the basics of TensorFlow Another good repo for learning TF and Keras Master the challenge After mastering the basics in terms of programming in TF/Keras, I wanted to try solving some real problems. There's no better place for that challenge than Kaggle and the popular Titanic dataset. Here, you can really find a bunch of materials and simple examples of ML applications. Here are some of my favorites: Titanic - Machine Learning from Disaster Home Credit Default Risk House Prices - Advanced Regression Techniques Two Sigma: Using News to Predict Stock Movements I then decided to further develop my career in the direction of applying ML to the stock market, first using predictions on time series and then using natural language processing. I've remained in this field until today and will defend my doctoral dissertation soon. How to deploy models To continue, before I move on to the topic of specialization, we need to address the topic of deployment. Now that we've learned how to make some basic models in Keras and how to use them, there are many ways and services, but I'll only mention what I use today. For all my ML models, whether simple regression models or complex GPT models, I use FastAPI. It's a straightforward framework, and you can quickly create API endpoints. I'll share a few older and useful tutorials for beginners: AI as an API tutorial series A step-by-step guide Productizing an ML Model with FastAPI and Cloud Run Personally, I've deployed on various cloud providers, of which I would highlight GCP and AWS because they have everything needed for model deployment, and if you know how to use them, they can be quite cheap. Chose your specialization The next step in developing my career, besides choosing finance as the primary area, was my specialization in the field of NLP. This happened in early 2020 when I started working with models based on the Transformer architecture. The first model I worked with was BERT, and the first tasks were related to classifications. My recommendations are to master the Transformer architecture well because 99% of today's LLM models are based on it. Here are some resources: The legendary paper "Attention Is All You Need" Hugging Face Course on Transformers Illustrated Guide to Transformers - Step by Step Explanation Good repository How large language models work, a visual intro to transformers After spending years using encoder-based Transformer models, I started learning GPT models. Good open-source models like Llama 2 then appear. Then, I started fine-tuning these models using the excellent Unsloth library: How to Finetune Llama-3 and Export to Ollama Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth After that, I focused on studying various RAG techniques and developing Agent AI systems. This is now called AI engineering, and, as far as I can see, it has become quite popular. So I'll write more about that in another post, but here I'll leave what I consider to be the three most famous representatives, i.e., their tutorials: LangChain tutorial LangGraph tutorial CrewAI examples Here I am today Thanks to the knowledge I've generated over all these years in the field of ML, I've developed and worked on numerous projects. The most significant publicly available project is developing an agent AI system for well-being support, which I turned into a mobile application. Also, my entire doctoral dissertation is related to applying ML to the stock market in combination with the development of GPT models and reinforcement learning (more on that in a separate post). After long 6 years, I've completed my dissertation, and now I'm just waiting for its defense. I'll share everything I'm working on for the dissertation publicly on the project, and in tutorials I'm preparing to write. If you're interested in these topics, I announce that I'll soon start with activities of publishing content on Medium and a blog, but I'll share all of that here on Reddit as well. Now that I've gathered years of experience and knowledge in this field, I'd like to share it with others and help as much as possible. If you have any questions, feel free to ask them, and I'll try to answer all of them. Thank you for reading.

Are Genetic Algorithms Still Relevant in 2025?

Hey everyone, I was first introduced to Genetic Algorithms (GAs) during an Introduction to AI course at university, and I recently started reading "Genetic Algorithms in Search, Optimization, and Machine Learning" by David E. Goldberg. While I see that GAs have been historically used in optimization problems, AI, and even bioinformatics, I’m wondering about their practical relevance today. With advancements in deep learning, reinforcement learning, and modern optimization techniques, are they still widely used in research and industry?I’d love to hear from experts and practitioners: In which domains are Genetic Algorithms still useful today? Have they been replaced by more efficient approaches? If so, what are the main alternatives? Beyond Goldberg’s book, what are the best modern resources (books, papers, courses) to deeply understand and implement them in real-world applications? I’m currently working on a hands-on GA project with a friend, and we want to focus on something meaningful rather than just a toy example.

How I Started Learning Machine Learning

Hello, everyone. As promised, I'll write a longer post about how I entered the world of ML, hoping it will help someone shape their path. I'll include links to all the useful materials I used alongside the story, which you can use for learning. I like to call myself an AI Research Scientist who enjoys exploring new AI trends, delving deeper into understanding their background, and applying them to real products. This way, I try to connect science and entrepreneurship because I believe everything that starts as scientific research ends up "on the shelves" as a product that solves a specific user problem. I began my journey in ML in 2016 when it wasn't such a popular field. Everyone had heard of it, but few were applying it. I have several years of development experience and want to try my hand at ML. The first problem I encountered was where to start - whether to learn mathematics, statistics, or something else. That's when I came across a name and a course that completely changed my career. Let's start You guessed it. It was Professor Andrew Ng and his globally popular Machine Learning course available on Coursera (I still have the certificate, hehe). This was also my first official online course ever. Since that course no longer exists as it's been replaced by a new one, I recommend you check out: Machine Learning (Stanford CS229) Machine Learning Specialization These two courses start from the basics of ML and all the necessary calculus you need to know. Many always ask questions like whether to learn linear algebra, statistics, or probability, but you don't need to know everything in depth. This knowledge helps if you're a scientist developing a new architecture, but as an engineer, not really. You need to know some basics to understand, such as how the backpropagation algorithm works. I know that Machine Learning (Stanford CS229) is a very long and arduous course, but it's the right start if you want to be really good at ML. In my time, I filled two thick notebooks by hand while taking the course mentioned above. TensorFlow and Keras After the course, I didn't know how to apply my knowledge because I hadn't learned specifically how to code things. Then, I was looking for ways to learn how to code it. That's when I came across a popular framework called Keras, now part of TensorFlow. I started with a new course and acquiring practical knowledge: Deep Learning Specialization Deep Learning by Ian Goodfellow Machine Learning Yearning by Andrew Ng These resources above were my next step. I must admit that I learned the most from that course and from the book Deep Learning by Ian Goodfellow because I like reading books (although this one is quite difficult to read). Learn by coding To avoid just learning, I went through various GitHub repositories that I manually retyped and learned that way. It may be an old-fashioned technique, but it helped me a lot. Now, most of those repositories don't exist, so I'll share some that I found to be good: Really good Jupyter notebooks that can teach you the basics of TensorFlow Another good repo for learning TF and Keras Master the challenge After mastering the basics in terms of programming in TF/Keras, I wanted to try solving some real problems. There's no better place for that challenge than Kaggle and the popular Titanic dataset. Here, you can really find a bunch of materials and simple examples of ML applications. Here are some of my favorites: Titanic - Machine Learning from Disaster Home Credit Default Risk House Prices - Advanced Regression Techniques Two Sigma: Using News to Predict Stock Movements I then decided to further develop my career in the direction of applying ML to the stock market, first using predictions on time series and then using natural language processing. I've remained in this field until today and will defend my doctoral dissertation soon. How to deploy models To continue, before I move on to the topic of specialization, we need to address the topic of deployment. Now that we've learned how to make some basic models in Keras and how to use them, there are many ways and services, but I'll only mention what I use today. For all my ML models, whether simple regression models or complex GPT models, I use FastAPI. It's a straightforward framework, and you can quickly create API endpoints. I'll share a few older and useful tutorials for beginners: AI as an API tutorial series A step-by-step guide Productizing an ML Model with FastAPI and Cloud Run Personally, I've deployed on various cloud providers, of which I would highlight GCP and AWS because they have everything needed for model deployment, and if you know how to use them, they can be quite cheap. Chose your specialization The next step in developing my career, besides choosing finance as the primary area, was my specialization in the field of NLP. This happened in early 2020 when I started working with models based on the Transformer architecture. The first model I worked with was BERT, and the first tasks were related to classifications. My recommendations are to master the Transformer architecture well because 99% of today's LLM models are based on it. Here are some resources: The legendary paper "Attention Is All You Need" Hugging Face Course on Transformers Illustrated Guide to Transformers - Step by Step Explanation Good repository How large language models work, a visual intro to transformers After spending years using encoder-based Transformer models, I started learning GPT models. Good open-source models like Llama 2 then appear. Then, I started fine-tuning these models using the excellent Unsloth library: How to Finetune Llama-3 and Export to Ollama Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth After that, I focused on studying various RAG techniques and developing Agent AI systems. This is now called AI engineering, and, as far as I can see, it has become quite popular. So I'll write more about that in another post, but here I'll leave what I consider to be the three most famous representatives, i.e., their tutorials: LangChain tutorial LangGraph tutorial CrewAI examples Here I am today Thanks to the knowledge I've generated over all these years in the field of ML, I've developed and worked on numerous projects. The most significant publicly available project is developing an agent AI system for well-being support, which I turned into a mobile application. Also, my entire doctoral dissertation is related to applying ML to the stock market in combination with the development of GPT models and reinforcement learning (more on that in a separate post). After long 6 years, I've completed my dissertation, and now I'm just waiting for its defense. I'll share everything I'm working on for the dissertation publicly on the project, and in tutorials I'm preparing to write. If you're interested in these topics, I announce that I'll soon start with activities of publishing content on Medium and a blog, but I'll share all of that here on Reddit as well. Now that I've gathered years of experience and knowledge in this field, I'd like to share it with others and help as much as possible. If you have any questions, feel free to ask them, and I'll try to answer all of them. Thank you for reading.

What Reinforcement Learning Method Should I Use for Poker AI with LLMs?

Hey everyone, I’m working on a poker AI project, where I’m training a large language model (LLM) to predict poker actions from given game states (check, call, bet, raise, etc.). My end goal is to create a model that can play poker at a high level, primarily by self-play and opponent modeling. However, I’m running into some challenges that I hope you can help me with! Here's the situation: Training Method: I’m using supervised fine-tuning (SFT) on real poker hand history data to initially teach the LLM how to predict poker actions from game states. This means that the model learns from examples of past games, predicting the actions that players took in various situations. Self-Play Setup: I plan to eventually move to self-play, where the LLM will play against itself (or other types of models that I create to simulate different play styles). I’ll use these self-play sessions to improve the model over time. Opponent Pool: I’m creating 6 types of poker players (Loose Aggressive, Loose Passive, Tight Aggressive, Tight Passive, Maniac, and Nit), each trained at 5 different skill levels (Novice, Beg\*nner, Intermediate, Advanced, Expert). This gives me a decent range of opponent behavior for training. The problem: Here’s the catch: The LLM I’m using only outputs discrete actions (e.g., bet 3BB, raise to 10BB, etc.) with no access to the probabilities of actions, so I can't directly use methods like policy gradients or Q-learning that rely on action probabilities or continuous action spaces. This makes applying traditional RL methods a bit tricky. My question: Given that I don't have access to action probabilities, what RL method or strategy should I pursue to improve my model? Specifically, I’m looking for a way to: Incorporate self-play with reward-based learning. Refine the model through reinforcement learning, without the need for continuous probabilities. Ensure the model doesn’t just overfit to its own prior behavior but learns to adapt and exploit different strategies in poker. I’ve considered a few approaches like reward-weighted supervised fine-tuning or using simpler RL techniques like Monte Carlo updates, but I’m not sure which would work best with the LLM setup I have. I've also considered Q-learning or Deep Q-learning. Any advice or suggestions on which RL approach I should take given my situation would be greatly appreciated! Yes I used AI to write this queston. But it captures everything I want to say, and I suck at writing.

Strategies for training AI players on asymmetric games?

I'm familiar with things like self-play in training a player for games like Chess, Checkers, and many other games where move sets and goals are the same for both players - e.g. eliminate the other player's pieces, prevent the other player from moving (like in Amazons, for example), etc. But what about training a computer player for a game where one side has a different goal than the other? Thing like Maker-Breaker Games. I imagine I would want to train a strong Maker and then train a strong Breaker. So it seems like like an application of Reinforcement Learning and more like a Generative Adversarial Network. Does anyone have any reading on these types of problems? Thanks. Additionally, I'm looking to build a home computer with some funds I came into recently to help me train models (I can't depend on cloud services since the money is only available for a short time), and my budget is pretty big for a home system. Where should I go looking for something that is relatively quiet, usable, doesn't raise my electricity bill too high, and is still powerful enough to train models for years to come? I've looked into /r/buildapcforme but folks seem more focused on gaming over there. And I'm pretty hardware ignorant.

Is MIT Sloan's: "AI: Implications for Business Strategy Online Short Course" worth the money?

Hey everyone, I'm a CPA and have no IT background, but since I have some time in October due to a career break, I was thinking about taking this course: https://www.getsmarter.com/products/mit-sloan-artificial-intelligence-implications-for-business-strategy-online-program?focused=true I think it might be an interesting start to become an early follower in this whole AI story in Finance and Audit. I honestly don't see myself coding, and I don't think that's what would be expected from me as a Finance Manager in the future. But... $4,300 is quite a price tag for an online course. But then again, if I want to effectively use it in a next career step, it would probably pay out to have an actual certificate instead of one of the many (certainly very good) free courses. &#x200B; What are your thoughts? Does anyone have experience with this or a similar program?

[Help Needed] Developing an AI to Play Mini Metro – Struggling with Data Extraction & Strategy method

Hello everyone ! First of all, please excuse my English if i do mistakes, as it is not my native language and I am not necessarily comfortable with it :) Regarding this project, I will explain my initial intention. I know very little about coding, but I enjoy it and have had some Python lessons, along with a few small personal projects for fun, mostly using YouTube tutorials. Nothing too advanced... However, now I want to take it to the next level. Since I have some familiarity with coding, I’ve wanted to work on artificial intelligence for a while. I have never coded AI myself, but I enjoy downloading existing projects (for chess, checkers, cat-and-mouse games, etc.), testing their limits, and understanding how they work. One of my favorite strategy game genres is management games, especially Mini Metro. Given its relatively simple mechanics, I assumed there would already be AI projects for it. But to my surprise, I could only find mods that add maps ! I admit that I am neither the best nor the most patient researcher, so I haven’t spent hours searching, but the apparent lack of projects for this game struck me. Maybe the community is just small ? I haven't looked deeply into it. So, I got it into my head to create my own AI. After all, everything is on the internet, and perseverance is key ! However, perseverance alone is not enough when you are not particularly experienced, so I am turning to the community to find knowledgeable people who can help me. The First Obstacle: Getting Game Data I quickly realized that the biggest challenge is that Mini Metro does not have an accessible API (at least, not one I could find). This means I cannot easily extract game data. My initial idea was to have an AI analyze the game, think about the best move, and then write out the actions to be performed, instead of coding a bot that directly manipulates the game. But first, I needed a way to retrieve and store game data. Attempt #1: Image Recognition (Failed) Since there was no API, I tried using image recognition to gather game data. Unfortunately, it was a disaster. I used mss for screenshots ,Tesseract for OCR, andNumPy to manipulate images in the HSV color space but it produced unreliable results : It detected many false positives (labeling empty spaces as stations) It failed to consistently detect numbers (scores or resources like trains and lines) Dotted bridge indicators over rivers were misinterpreted as stations While I could detect stations, lines, and moving trains, the data was chaotic and unreliable Attempt #2: Manual Data Entry (Partially Successful but Impractical) Since image recognition was unreliable, I decided to manually update the game data in real-time. I created a script that : Displays an overlay when I press Shift+R. Allows me to manually input stations, lines, and other game elements. Saves the current state when I press Shift+R again, so I can resume playing. Implements a simple resource management system (trains, lines, etc.). This works better than image recognition because I control the input, but I’m running into serious limitations : Some game mechanics are hard to implement manually (adding a station in the middle of a line, extending the correct line when two lines overlap at a station) Keeping track of station demands (the shapes passengers want to travel to) becomes overwhelming as the game progresses Updating the score in real-time is practically impossible manually, and the score is essential for training an AI (for my reward systems) My Dilemma At this point, I am unsure of how to proceed. My questions for the community : Am I going in the right direction? Should I continue improving my manual tracking system or is it a dead end? Should I have persevered with image recognition instead? Is there a better way to extract game data that I haven’t thought of? I would appreciate any guidance or ideas. Thanks in advance ! if you need more info, i have posted my codes here : https://github.com/Dmsday/mini\metro\data\analyzer (for the image detection version I'm not sure that it's the latest version aka the most "functional" version that I could do because I think I deleted it out of boredom...)

How do byte-level language models work?

I've recently been trying to pre-train my own small language model on the tiny-series datasets on huggingface: https://huggingface.co/collections/nampdn-ai/tiny-series-6503910fd491144159519c70. I also wanted to use a model similar to MEGABYTE: https://arxiv.org/pdf/2305.07185.pdf, but I don't understand how using bytes would work. The only implementation I could find: https://github.com/lucidrains/MEGABYTE-pytorch used str(chr(max(32, token))) to decode any token (byte) to a character and put the embedding size as 256. Firstly, why 256 and not 256-32 as any values below 32 are ignored? Also, many byte-level models including this and ByteT5 mention that they can process any text sequence even in a multilingual setting, however how would that be true if we are only using one byte, would we have to move to 2 bytes or use an UNK token, and if we did use 2 bytes that would make our embedding size around 65000 which defeats sort of the point as one of the advantages mentioned is that we are able to use a small embedding matrix? Furthermore, most language models add special tokens like bos, eos, unk and even for llama they use beginning of instruction, end of instruction, and more for system instructions, response, context... Should I use something like this as my dataset has some structures where there is a context, instruction and response, and if i did how would I add these if I'm using byte-level encodings? Final questions: Firstly, for the datasets mentioned including code,stories,webtext,... would I tokenise all of these datasets then concatenate them to then randomly sample from, or should i train seperately on each as some like code and webtext are much larger than the others? Finally, for the webtext part of the dataset, there is a passage of text then a passage analysing the text (main ideas,purpose,...), how should I encode this, should I use an extra ANALYSE token or just concatenate? Thank you for reading this far, I am sort of a beginner so if I said something stupid please point it out. Also, if there were unclear parts in my question I'm sorry as I struggled how to word these questions. Any help would be appreciated!

𝗠𝗮𝘀𝘁𝗲𝗿 𝗟𝗶𝗻𝗲𝗮𝗿 𝗥𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: 𝗔 𝗠𝘂𝘀𝘁-𝗞𝗻𝗼𝘄 𝗳𝗼𝗿 𝗕𝗲𝗴𝗶𝗻𝗻𝗲𝗿𝘀

Scikit-learn vs Statsmodel Linear regression is often the first model introduced to those stepping into the world of data science and machine learning. A deep understanding of this fundamental concept is crucial for building a solid foundation. In this post, I explore two widely used approaches to linear regression, each with distinct purposes: 1️⃣ 𝗦𝗰𝗶𝗸𝗶𝘁-𝗟𝗲𝗮𝗿𝗻’𝘀 𝗟𝗶𝗻𝗲𝗮𝗿 𝗥𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻: Optimized for machine learning applications and large datasets, this model focuses on efficiency and scalability. 2️⃣ 𝗦𝘁𝗮𝘁𝘀𝗺𝗼𝗱𝗲𝗹𝘀’ 𝗢𝗿𝗱𝗶𝗻𝗮𝗿𝘆 𝗟𝗲𝗮𝘀𝘁 𝗦𝗾𝘂𝗮𝗿𝗲𝘀 (𝗢𝗟𝗦): Known for its comprehensive statistical insights, this approach provides a detailed report ideal for understanding relationships and diagnosing issues like multicollinearity. It’s essential to gain hands-on experience with both libraries to appreciate their unique strengths. To make this learning process more accessible, I’ve created detailed videos and example code to guide you through practical applications: 🎥 𝗛𝗮𝗻𝗱𝘀-𝗢𝗻 𝗧𝘂𝘁𝗼𝗿𝗶𝗮𝗹𝘀: 📌 Learn Linear Regression in Python with LLM Prompt Chaining : https://www.youtube.com/watch?v=KOEG4rs1SUU 📌 In-Depth Linear Regression: Statsmodels OLS, Multicollinearity, and VIF : https://www.youtube.com/watch?v=QQWKY30XzNA 💻 𝗖𝗼𝗱𝗲 𝗳𝗼𝗿 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗲: 🔗 Scikit-Learn Implementation: https://github.com/pritkudale/ML-for-Teachers/blob/main/Linear%20Regression/Linear\Regression.ipynb 🔗 Statsmodels Implementation: https://github.com/pritkudale/ML-for-Teachers/blob/main/Linear%20Regression/Linear\regression\using\stats\model.ipynb What makes these tutorials unique? I’ve incorporated LLM prompt chaining, enabling beginners to confidently write code without requiring extensive Python expertise. 📩 𝘚𝘵𝘢𝘺 𝘢𝘩𝘦𝘢𝘥 𝘪𝘯 𝘈𝘐 𝘢𝘥𝘷𝘢𝘯𝘤𝘦𝘮𝘦𝘯𝘵𝘴! 𝘚𝘶𝘣𝘴𝘤𝘳𝘪𝘣𝘦 𝘵𝘰 𝘰𝘶𝘳 𝘯𝘦𝘸𝘴𝘭𝘦𝘵𝘵𝘦𝘳 𝘧𝘰𝘳 𝘦𝘹𝘱𝘦𝘳𝘵 𝘪𝘯𝘴𝘪𝘨𝘩𝘵𝘴: 𝘝𝘪𝘻𝘶𝘢𝘳𝘢 𝘈𝘐 𝘕𝘦𝘸𝘴𝘭𝘦𝘵𝘵𝘦𝘳: https://vizuara.ai/email-newsletter/

Sophomore computer science student, looking at ISLP vs ESL vs mlcourse.ai

For background, I am currently a computer science sophomore, with intermediate skills in Python and C++. I have taken university courses on data structure and algorithms, calc 1-3, linear algebra, and an introductory stat course (which covered confidence interval, Z and T sample test, and hypothesis testing). I also have read up to Chapter 5 of the MML book and am currently self-studying probability theory (through STAT 110 video and textbook by Joe Blitzstein). I have done a few beginner ML projects with Tensorflow and scikit-learn, but most of the work is in EDA and feature engineering, while the ML model is just a black box that I plug and chug. So now, I want to learn how to implement ML models from scratch. I've been skimming over ISLP, which many people online recommended, but it seems that while it talks about mathematical equations used, I don't really get to implement it; as the labs are a lot of importing an already implemented model then plug and chug. So now, I am looking at ESL, which I believe is the more detailed and mathematically rigorous version of ISL. However, there aren't any labs or code along to ease beginners in (which I somewhat understand given the intended audience of the book). Another option I am looking at is mlcourse.ai, which seems to cover mathematics and has some lab/code along for it. But it doesn't seem to span as many subjects as ESL does. Given these options, I am unsure of which one to pick, should I first finish my self-study on probability theory and then Chapters 6-8 of MML? Then should I do ISLP first or just get into ESL? Or maybe I should do mlcourse.ai first then into ESL? Or should I just do the ML course/book along with the maths? In addition, there is also the data science + feature engineering stuff which I wonder if I should study more about. Sorry if this seems like a mess, there are just so many things to ML that I am kinda overwhelmed.

Advice Needed

Hey everyone, I’ve been diving into Artificial Intelligence, Machine Learning, and Deep Learning recently, but I find myself a little confused about how to approach the learning process effectively. My goal isn’t just to secure a job but to actually build cool AI products or startups—something innovative and impactful, like what companies such as OpenAI, Anthropic, or ElevenLabs are doing. I often see founders or engineers building incredible AI-driven startups, and I can’t help but wonder: • What kind of learning path did these people follow? • Surely they didn’t just stick to basic Udemy or YouTube courses that most people use for job prep. • What resources or approaches do serious AI practitioners use? I’ve heard that implementing research papers is a great way to gain a deep, intuitive understanding of AI concepts. But as someone who is still a beginner, I’m unsure how to start implementing papers without feeling overwhelmed. Here’s what I’m hoping to get clarity on: Where should I begin as a complete beginner? What resources, projects, or habits would you recommend to build solid fundamentals in AI/ML? How do I progress from beginner to a level where I can implement research papers? Are there intermediate steps I need to take before diving into papers? What would the ideal roadmap look like for someone who wants to build startups in AI? If you’re an AI practitioner, researcher, or startup founder, I’d love to hear about your experiences and learning pathways. What worked for you? What didn’t? Any advice or resources would be immensely appreciated. I’m ready to put in the hard work, I just want to make sure I’m moving in the right direction. Thanks in advance! Looking forward to learning from this community.

NeRFs (2025)

Hey everyone! I'm currently working on my final year project, and it's focused on NeRFs and the representation of large-scale outdoor objects using drones. I'm looking for advice and some model recommendations to make comparisons. My goal is to build a private-access web app where I can upload my dataset, train a model remotely via SSH (no GUI), and then view the results interactively — something like what Luma AI offers. I’ll be running the training on a remote server with 4x A6000 GPUs, but the whole interaction will be through CLI over SSH. Here are my main questions: Which NeRF models would you recommend for my use case? I’ve seen some models that support JS/WebGL rendering, but I’m not sure what the best approach is for combining training + rendering + web access. How can I render and visualize the results interactively, ideally within my web app, similar to Luma AI? I've seen things like sMPLerNeRF, SNeRFs, and Instant-NGP, but I’m curious if there are more beginner-friendly or better-documented alternatives that can integrate well with a custom web interface. Any guidance on how to stream or render the output inside a browser? I’ve seen people use WebGL/Three.js, but I’m still not clear on the pipeline. I’m still new to NeRFs, but my goal is to implement the best model I can, and allow interactive mapping through my web application using data captured by drones. Any help or insights are much appreciated!

Learning Resources + Side Project Ideas

I made a post last night about my journey to landing an AI internship and have received a lot of responses asking about side projects and learning resources, so I am making another thread here consolidating this information for all those that are curious! Learning Process Step 1) Learn the basic fundamentals of the Math USE YOUTUBE!!! Literally just type in 'Machine Learning Math" and you will get tons of playlists covering nearly every topic. Personally I would focus on Linear Algebra and Calculus - specifically matrices/vector operations, dot products, eigenvectors/eigenvalues, derivatives and gradients. It might take a few tries until you find someone that meshes well with your learning style, but 3Blue1Brown is my top recommendation. I also read the book "Why Machines Learn" and found that extremely insightful. Work on implementing the math both with pen and paper then in Python. Step 2) Once you have a grip on the math fundamentals, I would pick up Hands-on Machine Learning with Sci-kit Learn, Keras and TensorFlow. This book was a game changer for me. It goes more in depth on the math and covers every topic from Linear Regression to the Transformers architecture. It also introduces you to Kaggle and some beginner level side projects. Step 3) After that book I would begin on side projects and also checking out other similar books, specifically Hands on Large Language Models and Hands on Generative AI. Step 4) If you have read all three of these books, and fully comprehend everything, then I would start looking up papers. I would just ask ChatGPT to feed you papers that are most relevant to your interests. Beginner Side Project Ideas 1) Build a Neural Network from scratch, using just Numpy. It can be super basic - have one input layer with 2 nodes, 1 hidden layer with 2 nodes, and output layer with one node. Learn about the forward feed process and play around with different activation functions and loss functions. Learn how these activation functions and loss functions impact backpropagation (hint: the derivatives of the activation functions and loss functions are all different). Get really good at this and understand the difference between regression models and classification models and which activation/loss functions go with which type of model. If you are really feeling crazy and are more focused on a SWE type of role, try doing it in a language other than python and try building a frontend for it so there is an interface where a user can input data and select their model architecture. 2) Build a CNN Image Classifier for the MNIST - Get familiar with the intricacies of CNN's, image manipulation, and basic computer vision concepts. 3) Build on top of open source LLM's. Go to Hugging Face's models page and start playing around with some. 4) KAGGLE COMPETITIONS - I will not explain further, do Kaggle Competitions. Other Resources I've mentioned YouTube, several books and Hugging Face. I also recommend: DataLemur.com \- Python practice, SQL practices, ML questions - his book Ace the Data Science Interview is also very good. X.com \- follow people that are prominent in the space. I joined an AI and Math Group that is constantly posting resources in there deep-ml.com If you have found any of this helpful - feel free to give me a follow on X and stay in touch @ x.com/hark0nnen\

Starting with Deep Learning in 2025 - Suggestion

I'm aware this has been asked many times here. so I'm not here to ask for a general advice - I've done some homework. My questions is - what do you think about this curriculum I put together (research + GPT)? Context: \- I'm a product manger with technical background and want to get back to a more technical depth. \- BSc in stats, familiar with all basic ML concepts, some maths (linear algebra etc), python. Basically, I got the basics covered a while ago so I'm looking to go back into the basics and I can learn and relearn anything I might need to with the internet. My focus is on getting hands on feel on where AI and deep learning is at in 2025, and understand the "under the hood" of key models used and LLMs specifically. Veterans - whats missing? what's redundant? Thanks so much! 🙏🏻 PS - hoping others will find this useful, you very well might too! |Week/Day|Goals|Resource|Activity| |:-|:-|:-|:-| |Week 1|Foundations of AI and Deep Learning||| |Day 1-2|Learn AI terminology and applications|DeepLearning.AI's "AI for Everyone"|Complete Module 1. Understand basic AI concepts and its applications.| |Day 3-5|Explore deep learning fundamentals|Fast.ai's Practical Deep Learning for Coders (2024)|Watch first 2 lessons. Code an image classifier as your first DL project.| |Day 6-7|Familiarize with ML/LLM terminology|Hugging Face Machine Learning Glossary|Study glossary terms and review foundational ML/LLM concepts.| |Week 2|Practical Deep Learning||| |Day 8-10|Build with PyTorch basics|PyTorch Beginner Tutorials|Complete the 60-minute blitz and create a simple neural network.| |Day 11-12|Explore more projects|Fast.ai Lesson 3|Implement a project such as text classification or tabular data analysis.| |Day 13-14|Fine-tune pre-trained models|Hugging Face Tutorials|Learn and apply fine-tuning techniques for a pre-trained model on a simple dataset.| |Week 3|Understanding LLMs||| |Day 15-17|Learn GPT architecture basics|OpenAI Documentation|Explore GPT architecture and experiment with OpenAI API Playground.| |Day 18-19|Understand tokenization and transformers|Hugging Face NLP Course|Complete the tokenization and transformers sections of the course.| |Day 20-21|Build LLM-based projects|TensorFlow NLP Tutorials|Create a text generator or summarizer using LLM techniques.| |Week 4|Advanced Concepts and Applications||| |Day 22-24|Review cutting-edge LLM research|Stanford's CRFM|Read recent LLM-related research and discuss its product management implications.| |Day 25-27|Apply knowledge to real-world projects|Kaggle|Select a dataset and build an NLP project using Hugging Face tools.| |Day 28-30|Explore advanced API use cases|OpenAI Cookbook and Forums|Experiment with advanced OpenAI API scenarios and engage in discussions to solidify knowledge.|

What is the best setup to implement for Ai

first of all I'm a fresh machine learning eng(not working yet) and my laptop system running on 128gb ssd + usual 1tb hdd + gtx1050. I used to install python locally and its libraries (from numpy and pandas to tensorflow and pytorch) with vscode (instead of anaconda) and I was happy about that. whenever I do project and want to deploy it i used pepenv. I got problems in storage when it comes to docker or cuda or wsl recently I got an storage upgrade to 512gb ssd and looking for new ideas and approaches about my new instlations What Should I do for each aspect use anaconda and make different environments (I feel this gonna drain storage specially I don't know what should each env contain) Shoul I use docker for windows or install wsl and install docker through it. Same for cuda should i install cuda native windows installation or intall it using wsl I don't try how to use programs in wsl for ex. I don't know how to use cuda on local development if it installed in wsl same as docker I know my gtx1050 won't be effecient when it comes to cuda and maybe more effective to use colab or kaggle gpu. but it's better practice i guess to develop on cuda.

Month of August in AI

🔍 Inside this Issue: 🤖 Latest Breakthroughs: This month it’s all about Agents, LangChain RAG, and LLMs evaluation challenges.* 🌐 AI Monthly News: Discover how these stories are revolutionizing industries and impacting everyday life: EU AI Act, California’s Controversial SB1047 AI regulation act, Drama at OpenAI, and possible funding at OpenAI by Nvidia and Apple.* 📚 Editor’s Special: This covers the interesting talks, lectures, and articles we came across recently. Follow me on Twitter and LinkedIn at RealAIGuys and AIGuysEditor to get insight on new AI developments. Please don't forget to subscribe to our Newsletter: https://medium.com/aiguys/newsletter Latest Breakthroughs Are Agents just simple rules? Are Agents just enhanced reasoning? The answer is yes and no. Yes, in the sense that agents have simple rules and can sometimes enhance reasoning capabilities compared to a single prompt. But No in the sense that agents can have a much more diverse functionality like using specific tools, summarizing, or even following a particular style. In this blog, we look into how to set up these agents in a hierarchal manner just like running a small team of Authors, researchers, and supervisors. How To Build Hierarchical Multi-Agent Systems? TextGrad. It is a powerful framework performing automatic “differentiation” via text. It backpropagates textual feedback provided by LLMs to improve individual components of a compound AI system. In this framework, LLMs provide rich, general, natural language suggestions to optimize variables in computation graphs, ranging from code snippets to molecular structures. TextGrad showed effectiveness and generality across various applications, from question-answering and molecule optimization to radiotherapy treatment planning. TextGrad: Improving Prompting Using AutoGrad The addition of RAG to LLMs was an excellent idea. It helped the LLMs to become more specific and individualized. Adding new components to any system leads to more interactions and its own sets of problems. Adding RAG to LLMs leads to several problems such as how to retrieve the best content, what type of prompt to write, and many more. In this blog, we are going to combine the LangChain RAG with DSPy. We deep dive into how to evaluate the RAG pipeline quantitatively using RAGAs and how to create a system where instead of manually tweaking prompts, we let the system figure out the best prompt. How To Build LangChain RAG With DSPy? As the field of natural language processing (NLP) advances, the evaluation of large language models (LLMs) like GPT-4 becomes increasingly important and complex. Traditional metrics such as accuracy are often inadequate for assessing these models’ performance because they fail to capture the nuances of human language. In this article, we will explore why evaluating LLMs is challenging and discuss effective methods like BLEU and ROUGE for a more comprehensive evaluation. The Challenges of Evaluating Large Language Models AI Monthly News AI Act enters into force On 1 August 2024, the European Artificial Intelligence Act (AI Act) enters into force. The Act aims to foster responsible artificial intelligence development and deployment in the EU. The AI Act introduces a uniform framework across all EU countries, based on a forward-looking definition of AI and a risk-based approach: Minimal risk: most AI systems such as spam filters and AI-enabled video games face no obligation under the AI Act, but companies can voluntarily adopt additional codes of conduct. Specific transparency risk: systems like chatbots must clearly inform users that they are interacting with a machine, while certain AI-generated content must be labelled as such. High risk: high-risk AI systems such as AI-based medical software or AI systems used for recruitment must comply with strict requirements, including risk-mitigation systems, high-quality of data sets, clear user information, human oversight, etc. Unacceptable risk: for example, AI systems that allow “social scoring” by governments or companies are considered a clear threat to people’s fundamental rights and are therefore banned. EU announcement: Click here https://preview.redd.it/nwyzfzgm4cmd1.png?width=828&format=png&auto=webp&s=c873db37ca0dadd5b510bea70ac9f633b96aaea4 California AI bill SB-1047 sparks fierce debate, Senator likens it to ‘Jets vs. Sharks’ feud Key Aspects of SB-1047: Regulation Scope: Targets “frontier” AI models, defined by their immense computational training requirements (over 10²⁶ operations) or significant financial investment (>$100 million). Compliance Requirements: Developers must implement safety protocols, including the ability to immediately shut down, cybersecurity measures, and risk assessments, before model deployment. Whistleblower Protections: Encourages reporting of non-compliance or risks by offering protection against retaliation. Safety Incident Reporting: Mandates reporting AI safety incidents within 72 hours to a newly established Frontier Model Division. Certification: Developers need to certify compliance, potentially under penalty of perjury in earlier drafts, though amendments might have altered this. Pros: Safety First: Prioritizes the prevention of catastrophic harms by enforcing rigorous safety standards, potentially safeguarding against AI misuse or malfunction. Incentivizes Responsible Development: By setting high standards for AI model training, the company encourages developers to think critically about the implications of their creations. Public Trust: Enhances public confidence in AI by ensuring transparency and accountability in the development process. Cons: Innovation Stagnation: Critics argue it might stifle innovation, especially in open-source AI, due to the high costs and regulatory burdens of compliance. Ambiguity: Some definitions and requirements might be too specific or broad, leading to legal challenges or unintended consequences. Global Competitiveness: There’s concern that such regulations could push AI development outside California or the U.S., benefiting other nations without similar restrictions. Implementation Challenges: The practicalities of enforcing such regulations, especially the “positive safety determination,” could be complex and contentious. News Article: Click here Open Letter: Click here https://preview.redd.it/ib96d7nk4cmd1.png?width=828&format=png&auto=webp&s=0ed5913b5dae72e203c8592393e469d9130ed689 MORE OpenAI drama OpenAI co-founder John Schulman has left the company to join rival AI startup Anthropic, while OpenAI president and co-founder Greg Brockman is taking an extended leave until the end of the year. Schulman, who played a key role in creating the AI-powered chatbot platform ChatGPT and led OpenAI’s alignment science efforts, stated his move was driven by a desire to focus more on AI alignment and hands-on technical work. Peter Deng, a product manager who joined OpenAI last year, has also left the company. With these departures, only three of OpenAI’s original 11 founders remain: CEO Sam Altman, Brockman, and Wojciech Zaremba, lead of language and code generation. News Article: Click here https://preview.redd.it/0vdjc18j4cmd1.png?width=828&format=png&auto=webp&s=e9de604c26aed3e47b50df3bdf114ef61f967080 Apple and Nvidia may invest in OpenAI Apple, which is planning to integrate ChatGPT into iOS, is in talks to invest. Soon after, Bloomberg also reported that Apple is in talks but added that Nvidia “has discussed” joining the funding round as well. The round is reportedly being led by Thrive Capital and would value OpenAI at more than $100 billion. News Article: Click here https://preview.redd.it/ude6jguh4cmd1.png?width=828&format=png&auto=webp&s=3603cbca0dbb1be3e6d0efcf06c3a698428bbdd6 Editor’s Special The AI Bubble: Will It Burst, and What Comes After?: Click here Eric Schmidt Full Controversial Interview on AI Revolution (Former Google CEO): Click here AI isn’t gonna keep improving Click here General Intelligence: Define it, measure it, build it: Click here

GPT Weekly - 19the June Edition - OpenAI's function calling, Meta's free LLM, EU Regulation and more.

This is a recap covering the major news from last week. 🔥Top 3 news - OpenAI’s updates, Meta’s upcoming free LLM and EU Regulation 🗞️Interesting reads include PSA about protecting your keys, The GPT ouroboros, Reddit - OpenAI’s moat, and more.. 🧑‍🎓Learning includes a Step-by-step guide from a non-technical founder who launched his MVP, Chatbot for your Gdrive and more 🔥Top 3 AI news in the past week OpenAI: New Pricing, Models, & Functions OpenAI has been on a roll. Last week we saw the release of OpenAI best practice on using GPT. This week we saw some amazing updates. Three major buckets were: First, the price decreases for both embeddings and GPT-3.5 tokens. Second, new models for gpt-4 and gpt-3.5. A new longer context model for gpt-3.5. Third, a new function calling capability. Why is it important? Previously, the output from OpenAI was all text. So, calling an external API from GPT was quite difficult. You had to parse the text data and things were often incorrect. Langchain created the Agents and Tools feature to tackle this problem. It was still unreliable and prone to issues. Now you get native support to generate a fixed format output. You can use the output to generate functional calls and also pass functions which need to be called. For example, if your app has multiple API endpoints then you can use GPT to generate the API calls with parameters. You can also pass the endpoints as function calls to ensure the correct function is executed. This functionality can further be used to generate structured data (JSON) out of GPT. So, you can generate data from GPT and load it into your backend. What’s next? This functionality allows turning natural language responses into structured data. This can be used to create “intelligent” backends using LLMs. We might see implementations in no-code tools to allow more robust and natural-language tools for non-technical folks. The structured data process goes both ways. You can also feed structured data into GPT for better responses. This feature also has its share of issues. Function calling suffers from the same prompt injection issues. Malicious actors can pass malicious code in function or the responses. For example, creation of queries using functions might contain malicious code to delete data. Without proper user validation this code will be executed automatically and delete data. So, using LLM as the back-end layer needs proper security implementation. Meta's LLM: Commercial Use Ahead Llama has been a boon for the open source community. Many of the open source models rely on Llama. The issue is that Llama is research-only and cannot be used commercially. So, no one can use it to build any product. Meta is now working on the next version of the model. This model will be available for commercial use. This is in stark contrast to both OpenAI and Google. Both safe-guarde their models and make it available through API. Why is it important? Certain industries cannot use LLM APIs because of strict restrictions on data privacy. These companies would want to run their own instance of a foundational model. A commercially available foundational model is also going to help people who want to keep their “API call” costs next to 0. A commercially available free-for-all model will also help push the open source community further. Just like Llama. What’s next? Sam Altman has said OpenAI didn’t release GPT-3 as open-source because they didn’t think people would be able to run it. Now OpenAI is working on an open-source model. This is going to be weaker than GPT-4. Let the battle of LLMs begin. EU's Proposed Legislation and Its Impact on AI Usage The EU parliament voted to move ahead with the E.U. AI Act. This act aims to ensure consumer protection against the dangers of AI. Why is it important? OpenAI and Sam Altman want regulations for models. They have proposed a IAEA-type of agency to stop the proliferation of LLM models. As per OpenAI, all models should be regulated and monitored. The suggestion of a license based regulation has led to significant backlash. Many people have called it “regulatory capture” - with the aim of shutting down competing LLMs. Licensing based regulations might not really be effective. The EU is approaching regulation from a different angle. It doesn’t focus on how models are developed. Rather focuses on how AI will/can be used. They have broken down use cases into 4 categories - unacceptable (prohibited), high, medium and low risk. For example, Building a Pre-Crime software,on%20crimes%20not%20yet%20committed.) to predict crimes? Building a Social credit system? Unacceptable. Using tools to influence elections or recommendation algorithms? High (Highly regulated). Using generative AI tools to create text or images on news sites? Medium (Add label that the content is AI generated) AI providers also need to disclose their training source. To me this sounds like good legislation. What do you guys think? But, OpenAI has warned that EU regulations might force them to pull out completely. What’s next? The disclosure requirements might help various publishing companies. AI and media companies are in talks to pay for training data. Google has been leading the charge. Additionally, OpenAI and Deepmind will open their models for safety and research purposes to the UK government. 🗞️10 AI news highlights and interesting reads PSA: If you are using Repl to write code, you might want to check your OpenAI API keys. If you have left them embedded then people can pirate and steal the keys. LLMs rely on human annotation or human feedback to learn. And one way to generate human annotation is crowdsourcing. But what if the crowdsource human annotators use LLMs? Research shows 33-46% workers used LLMs. So, basically we go from Human -> AI -> Human -> AI. The AI ouroboros. Researchers also say generated data to train models might cause serious issue. All the talks about moats \- Reddit might be OpenAI’s \future\ moat. Given the amount of complaints about how Google search experience has deteriorated during the blackout, this might be true? Doctors are using ChatGPT but not to diagnose.Rather to be more empathetic. We discussed this just a month ago. And guess where the data for this study came from? Reddit AskDocs. Moat FTW?! Beatles to make a comeback…using Generative AI. SnapFusion - Text to Image diffusion on mobile phones. Large context lengths are important for better GPT experience. The secret sauce for 100k context length. There is a lot of bad AI research out there. Some border on snake oil. Most AI “research” should be double checked and challenged. A new research on huggingface said that GPT-4 can ace MIT curriculum. Now someone is replicating the results and say that GPT-4 can’t beat MIT. Are we seeing peak AI? Especially when people from Deepmind and Meta are involved? Mistral AI raised $113 million in seed round with no product. Some might say this funding is for the team and the team is really solid. The issue though is whether the valuation is justified when OpenAI and Google already have a head start. The AI Hype Wall of Shame. \- Collection of articles which mislead people about AI in various aspects. 🧑‍🎓3 Learning Resources Building and Launching a company using GPT-4 with prompts. (The author didn’t know how to code but created and launched the MVP in a month). Chatbot for your Gdrive - https://www.haihai.ai/gpt-gdrive/ Building ChatGPT plugin using Supabase - https://supabase.com/blog/building-chatgpt-plugins-template That’s it folks. Thank you for reading and have a great week ahead. If you are interested in a focused weekly recap delivered to your inbox on Mondays you can subscribe here. It is FREE!

Join the AI4Earth challenge with the European Space Agency to highlight our footprint on Earth using Earth Observation data and Machine Learning

&#x200B; https://preview.redd.it/ww109cba14f71.png?width=2401&format=png&auto=webp&s=8bd3d43e8b63848af85c73478be61e43d9e10189 The primary goal is to get an insight into the human impact on Earth, to drive and guide conservation efforts of this planet we call home. Our approach will be twofold:  Firstly we will work on AI algorithms that can serve as an early detection system of human impact sites. Secondly we will use these detection systems to find satellite images that show the most impactful human-caused changes, which will be used in the creation of a video to launch an awareness campaign. You will be working with ESA to detect things like: Wildfires and Deforestation Marine Litter and Melting Glaciers Air quality detection & Novel animal migration patterns  and much more!  European Space Agency To reach these goals we’ve partnered up with ESA, who are able to use our algorithms to monitor new satellite data and guide conservation efforts. They will provide us with multi-spectral data of their Sentinel-2 satellite pair and with invaluable knowledge and research on the domain of Earth Observation data in participant only masterclasses.  Format The challenge will run throughout September and October, where you will collaborate with a diverse team of over 30 international data specialists and domain experts in subteams, all tackling this problem from different angles. Subtasks like the detection of deforestation, wildfires, marine litter or any other human caused impact. All contributors in the challenge are expected to spend 12 hours or more per week during the entirity of the two month challenge. To learn more subscribe to the info session on the 3rd of August 19:00 CEST HERE! Some important dates: 3rd of August – Info session 1st of September – Challenge Kick-off 29th of September – Midterm presentations 29th of October – Final presentations PARTNERS SUN - https://spacehubs.network The project is spearheaded by SUN whose goal is to increase the commercialization of space enabled solutions and growth of European start-ups and scale-ups in the space downstream and upstream sectors. ESA - https://esa.int ESA will be the main stakeholder and domain knowledge provider in the challenge. Their efforts to aid human’s space endeavours as well as protect the planet we live on will serve us for many years to come.  MLReef - https://mlreef.com MLReef provides an open source platform for collaborative Machine Learning. They provide the computational infrastructure to support the EO4Earth project as part of their AI4GOOD and Open Science initiatives. Brimatech  As a partner in the SUN project, the innovation management and market research expert Brimatech helps out in the overall organisation of the challenge.  Mothership The ‘Mothership’ is a dedicated open innovation program created by Space4Good and World Startup Factory. The Mothershi is leveraging recent advancements in artificial intelligence and satellite technologies in support of the UN Sustainable Development Goals. Space4Good  Space4Good is a geospatial innovation lab supporting impact makers on the ground with earth observation insights from above. Worldstartup  Worldstartup is a collective of international entrepreneurs, experts, mentors and investors, dedicated to help the best impact-driven startups and scaleups.

Study Plan for Learning Data Science Over the Next 12 Months [D]

In this thread, I address a study plan for 2021. In case you're interested, I wrote a whole article about this topic: Study Plan for Learning Data Science Over the Next 12 Months Let me know your thoughts on this. &#x200B; https://preview.redd.it/emg20nzhet661.png?width=1170&format=png&auto=webp&s=cf09e4dc5e82ba2fd7b57c706ba2873be57fe8de We are ending 2020 and it is time to make plans for next year, and one of the most important plans and questions we must ask is what do we want to study?, what do we want to enhance?, what changes do we want to make?, and what is the direction we are going to take (or continue) in our professional careers?. Many of you will be starting on the road to becoming a data scientist, in fact you may be evaluating it, since you have heard a lot about it, but you have some doubts, for example about the amount of job offers that may exist in this area, doubts about the technology itself, and about the path you should follow, considering the wide range of options to learn. I’m a believer that we should learn from various sources, from various mentors, and from various formats. By sources I mean the various virtual platforms and face-to-face options that exist to study. By mentors I mean that it is always a good idea to learn from different points of view and learning from different teachers/mentors, and by formats I mean the choices between books, videos, classes, and other formats where the information is contained. When we extract information from all these sources we reinforce the knowledge learned, but we always need a guide, and this post aims to give you some practical insights and strategies in this regard. To decide on sources, mentors and formats it is up to you to choose. It depends on your preferences and ease of learning: for example, some people are better at learning from books, while others prefer to learn from videos. Some prefer to study on platforms that are practical (following online code), and others prefer traditional platforms: like those at universities (Master’s Degree, PHDs or MOOCs). Others prefer to pay for quality content, while others prefer to look only for free material. That’s why I won’t give a specific recommendation in this post, but I’ll give you the whole picture: a study plan. To start you should consider the time you’ll spend studying and the depth of learning you want to achieve, because if you find yourself without a job you could be available full time to study, which is a huge advantage. On the other hand, if you are working, you’ll have less time and you’ll have to discipline yourself to be able to have the time available in the evenings, mornings or weekends. Ultimately, the important thing is to meet the goal of learning and perhaps dedicating your career to this exciting area! We will divide the year into quarters as follows First Quarter: Learning the Basics Second Quarter: Upgrading the Level: Intermediate Knowledge Third Quarter: A Real World Project — A Full-stack Project Fourth Quarter: Seeking Opportunities While Maintaining Practice First Quarter: Learning the Basics &#x200B; https://preview.redd.it/u7t9bthket661.png?width=998&format=png&auto=webp&s=4ad29cb43618e7acf793259243aa5a60a8535f0a If you want to be more rigorous you can have start and end dates for this period of study of the bases. It could be something like: From January 1 to March 30, 2021 as deadline. During this period you will study the following: A programming language that you can apply to data science: Python or R. We recommend Python due to the simple fact that approximately 80% of data science job offers ask for knowledge in Python. That same percentage is maintained with respect to the real projects you will find implemented in production. And we add the fact that Python is multipurpose, so you won’t “waste” your time if at some point you decide to focus on web development, for example, or desktop development. This would be the first topic to study in the first months of the year. Familiarize yourself with statistics and mathematics. There is a big debate in the data science community about whether we need this foundation or not. I will write a post later on about this, but the reality is that you DO need it, but ONLY the basics (at least in the beginning). And I want to clarify this point before continuing. We could say that data science is divided in two big fields: Research on one side and putting Machine Learning algorithms into production on the other side. If you later decide to focus on Research then you are going to need mathematics and statistics in depth (very in depth). If you are going to go for the practical part, the libraries will help you deal with most of it, under the hood. It should be noted that most job offers are in the practical part. For both cases, and in this first stage you will only need the basics of: Statistics (with Python and NumPy) Descriptive statistics Inferential Statistics Hypothesis testing Probability Mathematics (with Python and NumPy) Linear Algebra (For example: SVD) Multivariate Calculus Calculus (For example: gradient descent) Note: We recommend that you study Python first before seeing statistics and mathematics, because the challenge is to implement these statistical and mathematical bases with Python. Don’t look for theoretical tutorials that show only slides or statistical and/or mathematical examples in Excel/Matlab/Octave/SAS and other different to Python or R, it gets very boring and impractical! You should choose a course, program or book that teaches these concepts in a practical way and using Python. Remember that Python is what we finally use, so you need to choose well. This advice is key so you don’t give up on this part, as it will be the most dense and difficult. If you have these basics in the first three months, you will be ready to make a leap in your learning for the next three months. Second Quarter: Upgrading the Level: Intermediate Knowledge &#x200B; https://preview.redd.it/y1y55vynet661.png?width=669&format=png&auto=webp&s=bd3e12bb112943025c39a8975faf4d64514df275 If you want to be more rigorous you can have start and end dates for this period of study at the intermediate level. It could be something like: From April 1 to June 30, 2021 as deadline. Now that you have a good foundation in programming, statistics and mathematics, it is time to move forward and learn about the great advantages that Python has for applying data analysis. For this stage you will be focused on: Data science Python stack Python has the following libraries that you should study, know and practice at this stage Pandas: for working with tabular data and make in-depth analysis Matplotlib and Seaborn: for data visualization Pandas is the in-facto library for data analysis, it is one of the most important (if not the most important) and powerful tools you should know and master during your career as a data scientist. Pandas will make it much easier for you to manipulate, cleanse and organize your data. Feature Engineering Many times people don’t go deep into Feature Engineering, but if you want to have Machine Learning models that make good predictions and improve your scores, spending some time on this subject is invaluable! Feature engineering is the process of using domain knowledge to extract features from raw data using data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself. To achieve the goal of good feature engineering you must know the different techniques that exist, so it is a good idea to at least study the main ones. Basic Models of Machine Learning At the end of this stage you will start with the study of Machine Learning. This is perhaps the most awaited moment! This is where you start to learn about the different algorithms you can use, which particular problems you can solve and how you can apply them in real life. The Python library we recommend you to start experimenting with ML is: scikit-learn. However it is a good idea that you can find tutorials where they explain the implementation of the algorithms (at least the simplest ones) from scratch with Python, since the library could be a “Black Box” and you might not understand what is happening under the hood. If you learn how to implement them with Python, you can have a more solid foundation. If you implement the algorithms with Python (without a library), you will put into practice everything seen in the statistics, mathematics and Pandas part. These are some recommendations of the algorithms that you should at least know in this initial stage Supervised learning Simple Linear Regression Multiple Linear Regression K-nearest neighbors (KNN) Logistic Regression Decision Trees Random Forest Unsupervised Learning K-Means PCA Bonus: if you have the time and you are within the time ranges, you can study these others Gradient Boosting Algorithms GBM XGBoost LightGBM CatBoost Note: do not spend more than the 3 months stipulated for this stage. Because you will be falling behind and not complying with the study plan. We all have shortcomings at this stage, it is normal, go ahead and then you can resume some concepts that did not understand in detail. The important thing is to have the basic knowledge and move forward! If at least you succeed to study the mentioned algorithms of supervised and unsupervised learning, you will have a very clear idea of what you will be able to do in the future. So don’t worry about covering everything, remember that it is a process, and ideally you should have some clearly established times so that you don’t get frustrated and feel you are advancing. So far, here comes your “theoretical” study of the basics of data science. Now we’ll continue with the practical part! Third Quarter: A Real World Project — A Full-stack Project &#x200B; https://preview.redd.it/vrn783vqet661.png?width=678&format=png&auto=webp&s=664061b3d33b34979b74b10b9f8a3d0f7b8b99ee If you want to be more rigorous you can have start and end dates for this period of study at the intermediate level. It could be something like: From July 1 to September 30, 2021 as deadline. Now that you have a good foundation in programming, statistics, mathematics, data analysis and machine learning algorithms, it is time to move forward and put into practice all this knowledge. Many of these suggestions may sound out of the box, but believe me they will make a big difference in your career as a data scientist. The first thing is to create your web presence: Create a Github (or GitLab) account, and learn Git*. Being able to manage different versions of your code is important, you should have version control over them, not to mention that having an active Github account is very valuable in demonstrating your true skills. On Github, you can also set up your Jupyter Notebooks and make them public, so you can show off your skills as well. This is mine for example: https://github.com/danielmoralesp Learn the basics of web programming*. The advantage is that you already have Python as a skill, so you can learn Flask to create a simple web page. Or you can use a template engine like Github Pages, Ghost or Wordpress itself and create your online portfolio. Buy a domain with your name*. Something like myname.com, myname.co, myname.dev, etc. This is invaluable so you can have your CV online and update it with your projects. There you can make a big difference, showing your projects, your Jupyter Notebooks and showing that you have the practical skills to execute projects in this area. There are many front-end templates for you to purchase for free or for payment, and give it a more personalized and pleasant look. Don’t use free sub-domains of Wordpress, Github or Wix, it looks very unprofessional, make your own. Here is mine for example: https://www.danielmorales.dev/ Choose a project you are passionate about and create a Machine Learning model around it. The final goal of this third quarter is to create ONE project, that you are passionate about, and that is UNIQUE among others. It turns out that there are many typical projects in the community, such as predicting the Titanic Survivors, or predicting the price of Houses in Boston. Those kinds of projects are good for learning, but not for showing off as your UNIQUE projects. If you are passionate about sports, try predicting the soccer results of your local league. If you are passionate about finance, try predicting your country’s stock market prices. If you are passionate about marketing, try to find someone who has an e-commerce and implement a product recommendation algorithm and upload it to production. If you are passionate about business: make a predictor of the best business ideas for 2021 :) As you can see, you are limited by your passions and your imagination. In fact, those are the two keys for you to do this project: Passion and Imagination. However don’t expect to make money from it, you are in a learning stage, you need that algorithm to be deployed in production, make an API in Flask with it, and explain in your website how you did it and how people can access it. This is the moment to shine, and at the same time it’s the moment of the greatest learning. You will most likely face obstacles, if your algorithm gives 60% of Accuracy after a huge optimization effort, it doesn’t matter, finish the whole process, deploy it to production, try to get a friend or family member to use it, and that will be the goal achieved for this stage: Make a Full-stack Machine Learning project. By full-stack I mean that you did all the following steps: You got the data from somewhere (scrapping, open data or API) You did a data analysis You cleaned and transformed the data You created Machine Learning Models You deployed the best model to production for other people to use. This does not mean that this whole process is what you will always do in your daily job, but it does mean that you will know every part of the pipeline that is needed for a data science project for a company. You will have a unique perspective! Fourth Quarter: Seeking Opportunities While Maintaining Practice &#x200B; https://preview.redd.it/qd0osystet661.png?width=1056&format=png&auto=webp&s=2da456b15985b2793041256f5e45bca99a23b51a If you want to be more rigorous you can have start and end dates for this period of study at the final level. It could be something like: From October 1 to December 31, 2021 as deadline. Now you have theoretical and practical knowledge. You have implemented a model in production. The next step depends on you and your personality. Let’s say you are an entrepreneur, and you have the vision to create something new from something you discovered or saw an opportunity to do business with this discipline, so it’s time to start planning how to do it. If that’s the case, obviously this post won’t cover that process, but you should know what the steps might be (or start figuring them out). But if you are one of those who want to get a job as a data scientist, here is my advice. Getting a job as a data scientist “You’re not going to get a job as fast as you think, if you keep thinking the same way”.Author It turns out that all people who start out as data scientists imagine themselves working for the big companies in their country or region. Or even remote. It turns out that if you aspire to work for a large company like data scientist you will be frustrated by the years of experience they ask for (3 or more years) and the skills they request. Large companies don’t hire Juniors (or very few do), precisely because they are already large companies. They have the financial muscle to demand experience and skills and can pay a commensurate salary (although this is not always the case). The point is that if you focus there you’re going to get frustrated! Here we must return to the following advise: “You need creativity to get a job in data science”. Like everything else in life we have to start at different steps, in this case, from the beginning. Here are the scenarios If you are working in a company and in a non-engineering role you must demonstrate your new skills to the company you are working for*. If you are working in the customer service area, you should apply it to your work, and do for example, detailed analysis of your calls, conversion rates, store data and make predictions about it! If you can have data from your colleagues, you could try to predict their sales! This may sound funny, but it’s about how creatively you can apply data science to your current work and how to show your bosses how valuable it is and EVANGELIZE them about the benefits of implementation. You’ll be noticed and they could certainly create a new data related department or job. And you already have the knowledge and experience. The key word here is Evangelize. Many companies and entrepreneurs are just beginning to see the power of this discipline, and it is your task to nurture that reality. If you are working in an area related to engineering, but that is not data science*. Here the same applies as the previous example, but you have some advantages, and that is that you could access the company’s data, and you could use it for the benefit of the company, making analyses and/or predictions about it, and again EVANGELIZING your bosses your new skills and the benefits of data science. If you are unemployed (or do not want, or do not feel comfortable following the two examples above)*, you can start looking outside, and what I recommend is that you look for technology companies and / or startups where they are just forming the first teams and are paying some salary, or even have options shares of the company. Obviously here the salaries will not be exorbitant, and the working hours could be longer, but remember that you are in the learning and practice stage (just in the first step), so you can not demand too much, you must land your expectations and fit that reality, and stop pretending to be paid $ 10,000 a month at this stage. But, depending of your country $1.000 USD could be something very interesting to start this new career. Remember, you are a Junior at this stage. The conclusion is: don’t waste your time looking at and/or applying to offers from big companies, because you will get frustrated. Be creative, and look for opportunities in smaller or newly created companies. Learning never stops While you are in that process of looking for a job or an opportunity, which could take half of your time (50% looking for opportunities, 50% staying in practice), you have to keep learning, you should advance to concepts such as Deep Learning, Data Engineer or other topics that you feel were left loose from the past stages or focus on the topics that you are passionate about within this group of disciplines in data science. At the same time you can choose a second project, and spend some time running it from end-to-end, and thus increase your portfolio and your experience. If this is the case, try to find a completely different project: if the first one was done with Machine Learning, let this second one be done with Deep learning. If the first one was deployed to a web page, that this second one is deployed to a mobile platform. Remember, creativity is the key! Conclusion We are at an ideal time to plan for 2021, and if this is the path you want to take, start looking for the platforms and media you want to study on. Get to work and don’t miss this opportunity to become a data scientist in 2021! Note: we are building a private community in Slack of data scientist, if you want to join us write to the email: support@datasource.ai I hope you enjoyed this reading! you can follow me on twitter or linkedin Thank you for reading!

MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: https://preview.redd.it/mdyyv1qmdz291.png?width=1834&format=png&auto=webp&s=e9e10710794c78c64cc05adb75db385aa53aba40 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: &#x200B; https://preview.redd.it/nz8zrbbpdz291.png?width=1280&format=png&auto=webp&s=28dae7e031621bc8819519667ed03d8d085d8ace Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/d7syq47rdz291.png?width=1280&format=png&auto=webp&s=b43df9abd380b7d9a52e3045dd787f4feeb69635 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: &#x200B; https://preview.redd.it/aa7pxx8tdz291.png?width=1280&format=png&auto=webp&s=e3727c29d1bde6eea2e1cccf6c46d3cae3f4750e Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/2mw4qpjudz291.png?width=1280&format=png&auto=webp&s=1cf1db667892b9b3a40451993680fbd6980b5520 The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

6 principles to data architecture that facilitate innovation

My team and I have been re-building our company's data architecture. In the process of doing so, I got together six key principles to transforming data architectures and thought I would share them, as a strong data architecture is crucial for businesses looking to stay competitive in the digital landscape, as it improves decision-making, time to market, and data security. When executed with efficiency, a resilient data architecture unleashes unparalleled degrees of agility. Principle 1: Agility and flexibility To quickly adjust to market fluctuations, businesses must create adaptable data infrastructures that can effortlessly manage an ever-growing influx of data. To accomplish this objective, we recommend to our clients to implement Enterprise Service Bus, Enterprise Data Warehouse, and Master Data Management integrated together. &#x200B; I believe the best option is this: \- By centralizing communication, ESB reduces the time and effort required to integrate new systems; \- EDW consolidates data from different sources, resulting in a 50% reduction in software implementation time; \- Finally, MDM ensures consistency and accuracy across the organization, leading to better decision-making and streamlined operations. Implementing these solutions can lead to reduced software implementation time, better ROI, and more manageable data architecture. By fostering a culture of collaboration and adopting modern technologies and practices, businesses can prioritize agility and flexibility in their data architecture to increase the pace of innovation. Principle 2: Modularity and reusability Data architecture that fosters modularity and reusability is essential for accelerating innovation within an organization. By breaking data architecture components into smaller, more manageable pieces, businesses can enable different teams to leverage existing architecture components, reducing redundancy and improving overall efficiency. MDM can promote modularity and reusability by creating a central repository for critical business data. This prevents duplication and errors, improving efficiency and decision-making. MDM enables a single source of truth for data, accessible across multiple systems, which promotes integration and scalability. MDM also provides standardized data models, rules, and governance policies that reduce development time, increase quality, and ensure proper management throughout the data’s lifecycle. Another way to achieve modularity in data architecture is through the use of microservices and scripts for Extract, Transform, and Load (ETL) processes. Adopting a structured methodology and framework can ensure these components are well-organized, making it easier for teams to collaborate and maintain the system. Microservices can also contribute to modularity and reusability in data architecture. These small, independent components can be developed, deployed, and scaled independently of one another. By utilizing microservices, organizations can update or replace individual components without affecting the entire system, improving flexibility and adaptability. Principle 3: Data quality and consistency The efficiency of operations depends on data’s quality, so a meticulously crafted data architecture plays a pivotal role in preserving it, empowering enterprises to make well-informed decisions based on credible information. Here are some key factors to consider that will help your company ensure quality: \- Implementing Master Data Management (MDM) – this way, by consolidating, cleansing, and standardizing data from multiple sources, your IT department will be able to create a single, unified view of the most important data entities (customers, products, and suppliers); \- Assigning data stewardship responsibilities to a small team or an individual specialist; \- Considering implementing data validation, data lineage, and data quality metrics; \- By implementing MDM and adopting a minimal data stewardship approach, organizations can maintain high-quality data that drives innovation and growth. Principle 4: Data governance Data governance is a strategic framework that goes beyond ensuring data quality and consistency. It includes ensuring data security, privacy, accessibility, regulatory compliance, and lifecycle management. Here are some key aspects of data governance: \- Implementing robust measures and controls to protect sensitive data from unauthorized access, breaches, and theft. This is only possible through including encryption, access controls, and intrusion detection systems into your company’s IT architecture; \- Adhering to data privacy regulations and guidelines, such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA); \- Defining stringent conditions for who has access to specific data assets to maintain control over data and ensure its accessibility only for legitimate purposes. Managing the entire lifecycle of data, from creation and storage to archiving and disposal, including defining policies for data retention, archiving, and deletion in compliance with legal and regulatory requirements. To facilitate effective data governance, organizations can leverage various tools and technologies, such as: \- Data cataloging tools: Solutions like Collibra, Alation, or Informatica Enterprise Data Catalog help organizations discover, understand, and manage their data assets. \- Data lineage tools: Tools like Talend, IBM InfoSphere, or Apache Atlas help track data’s origin, transformation, and usage, providing insights into data quality issues and potential areas for improvement. \- Data quality tools: Solutions like Informatica Data Quality, Trifacta, or SAS Data Quality help organizations maintain high-quality data by identifying and correcting errors, inconsistencies, and inaccuracies. \- Data security and privacy tools: Tools like Varonis, BigID, or Spirion help protect sensitive data and ensure compliance with data privacy regulations. Principle 5: Cloud-first approach A cloud-first approach prioritizes cloud-based solutions over on-premises ones when it comes to data management. Cloud-based data management pros: \- Virtually limitless scalability, so that organizations can grow and adapt to changing data requirements without significant infrastructure investments; \- The pay-as-you-go model of cloud services reduces maintenance costs usually associated with the on-premise choice; \- Greater flexibility for deploying and integrating new technologies and services; \- Cloud can be accessed from anywhere, at any time, turning team collaboration and remote work into a breeze; \- Built-in backup and disaster recovery capabilities, ensuring data safety and minimizing downtime in case of emergencies. Cloud-based data management cons: \- Cloud-first approach raises many data security, privacy, and compliance concerns; \- Transferring large data volumes to and from cloud is often time-consuming and results in increased latency for certain apps; \- Relying on a single cloud provider makes it difficult to switch them or move back to the on-premises option without significant funds and effort. Challenges that organizations that choose a cloud-first approach face: \- Integrating cloud-based systems with on-premises ones can be complex and time-consuming; \- Ensuring data governance and compliance in a multi-cloud or hybrid environment is also another problem reported by my clients. How EDW, ESB, and MDM promote cloud-first approach: A cloud-based EDW centralizes data from multiple sources, enabling a unified view of the organization’s data and simplifying data integration across cloud and on-premises systems. An ESB facilitates communication between disparate cloud and on-premises systems, streamlining data integration and promoting a modular architecture. Cloud-based MDM solutions are used for maintaining data quality and consistency across multiple data sources and environments. Principle 6: Automation and artificial intelligence Incorporating automation tools and AI technologies into data architecture can optimize processes and decision-making. Key Applications: \- Data ingestion and integration: Automation simplifies data schema updates and identifies data quality issues, while AI-assisted development helps create tailored connectors, scripts, and microservices. \- Data quality management: Machine learning algorithms improve data quality and consistency by automatically detecting and correcting inconsistencies and duplicates. \- Predictive analytics: AI and machine learning models analyze historical data to predict trends, identify opportunities, and uncover hidden patterns for better-informed decisions. How No-Code Tools and AI-Assisted Development Work: Business users define data requirements and workflows using no-code tools, enabling AI models to understand their needs. AI models process the information, generating recommendations for connector creation, ETL scripts, and microservices. Developers use AI-generated suggestions to accelerate development and tailor solutions to business needs. By combining automation, AI technologies, and no-code tools, organizations can streamline data architecture processes and bridge the gap between business users and developers, ultimately accelerating innovation. I share more tips on building an agile data architectures in my blog.

AI Noob where to start?

Hello, TL;DR: Where do I get started with AI from an ICT engineer POV? I find the subject complex and vague, and I have no idea where to start. A little bit about myself, I am a telecoms engineer with 7 years of experience in networking, servers (virtualisation and containers), Audio-visual and industrial/home automations and CAD, but I am more specialised in the first 4 layers of the OSI model with a little experience in Python, YAML and Ansible (nowhere near a software engineer, but decent enough to make simple automations work if needed). I am starting to have clients that ask questions about AI and its use for their business, and I am not confident in answering them. Where should I start? My only knowledge about AI was gathered from a course I have done “AI Infrastructure and Operations Fundamentals” from Nvidia and the fact that Lamma is an open-source model from Meta (which I absolutely adore the idea of local open-source AI). I am do not think I want to be an AI developer and pivot, but more like how AI can enhance my current skill set. I want to understand what the technical requirements are, technical terminology, how the different models can be used for different purposes (text, images, etc.). From a HW perspective, I am long overdue for a workstation upgrade (currently i7 9^(th) Gen, RTX 2060 Super 8Gb VRAM, 16Gb DDR4 RAM) I use my workstation as a homelab and for CAD and gaming. My hope is that by the time intel 15^(th) gen and Nvidia 5000 will be released, I will have some kind of idea of what I want to do with it from an AI perspective. I have seen a lot of knowledgeable people in this subreddit and wanted to know what it was their journey and how did they get started? What do you recommend (courses, books, HW/SW, etc.)?

Let’s Build One Person Business Using 100% AI

AI made it possible for 9-to-5 workers to start a one-person business without quitting their jobs. Full Article https://preview.redd.it/tynb9y6z695d1.png?width=1309&format=png&auto=webp&s=b490d3676a63adcc01faff8c476056cb7d420022 https://i.redd.it/9x3okti0795d1.gif The Opportunities for Starting a Business ○ There are huge opportunities to start your own business by leveraging valuable skills to attract paying audiences. ○ New software and AI platforms make it easier to distribute products/services and automate tasks that were previously time-consuming. Our One Person Book Publication House ○ This article explores building a one-person AI-powered business focused on publishing books. ○ Users input data on a topic, and AI generates a comprehensive book structure and content based on that. ○ The generated content can be formatted, designed, and published digitally or in print easily. Why Read This Article? ○ It presents an innovative AI-powered approach to streamline the book publishing process. ○ It provides technical implementation details using LLM, Python and the Streamlit library as a reference. ○ It highlights AI's potential in automating creative tasks like writing and content creation. Approaching the One Person Business ○ Reflect on areas where you overcame personal struggles and gained valuable skills. ○ Leverage that expertise to build an AI business serving others facing similar obstacles. ○ Use AI tools to create content, automate processes, and efficiently scale your offerings. The Publication Business Idea ○ Focus on writing and publishing small books using AI writing assistants. ○ AI can streamline research, writing drafts, outlines, and ideas across genres. ○ Concentrate efforts on editing, formatting, and marketing while AI handles writing. The Book Generation Process ○ Users input structured topic data like outlines, key points, and references. ○ Advanced AI language models generate flowing book content from that data. ○ Minimal human effort is needed beyond initial inputs and refinement. ○ AI systems automatically handle formatting, design, and publishing. Technical Implementation ○ Includes a Book class to represent a book's hierarchical structure in Python. ○ Functions to generate book structures and section content using AI models. ○ Integrates with a Streamlit app for user input and output. ○ Allows downloading the final book in Markdown format. Closing Thoughts ○ This AI-powered approach makes book writing and publishing more accessible to individuals. ○ AI handles the heavy lifting, with humans providing quality control through editing. ○ It opens up possibilities for innovative knowledge sharing as technology evolves.

What if… Employers Employ AI Agents to Get 360° Feedback from Employees?

AI Agent powered Comprehensive 360° Feedback Collection & Analysis Full Article &#x200B; https://i.redd.it/1ieczv6pud1d1.gif ⚪ What is this Article About? ● This article demonstrates how AI agents can be used in the real-world for gathering feedback from employees ● It explores using AI agents to collect insights on employee experiences, job satisfaction, and suggestions for improvement ● By leveraging AI agents and language models, organizations can better understand their workforce's needs and concerns ⚪Why Read this Article? ● Learn about the potential benefits of using AI agents for comprehensive feedback collection ● Understand how to build practical, real-world solutions by combining AI agents with other technologies ● Stay ahead of the curve by exploring cutting-edge applications of AI agents ⚪What are we doing in this Project? \> Part 1: AI Agents to Coordinate and Gather Feedback ● AI agents collaborate to collect comprehensive feedback from employees through surveys and interviews ● Includes a Feedback Collector Agent, Feedback Analyst Agent, and Feedback Reporter Agent \> Part 2: Analyze Feedback Data with Pandas AI and Llama3 ● Use Pandas AI and Llama3 language model to easily analyze the collected feedback data ● Extract insights, identify patterns, strengths, and areas for improvement from the feedback ⚪ Let's Design Our AI Agent System for 360° Feedback \> Feedback Collection System: ● Collect feedback from employees (simulated) ● Analyze the feedback data ● Report findings and recommendations \> Feedback Analysis System: ● Upload employee feedback CSV file ● Display uploaded data ● Perform natural language analysis and queries ● Generate automated insights and visual graphs ⚪ Let's get Cooking ● Explanation of the code for the AI agent system and feedback analysis system ● Includes code details for functions, classes, and streamlit interface ⚪ Closing Thoughts ● AI agents can revolutionize how businesses operate and tackle challenges ● Their ability to coordinate, collaborate, and perform specialized tasks is invaluable ● AI agents offer versatile and scalable solutions for optimizing processes and uncovering insights ⚪ Future Work ● This project is a demo to show the potential real-world use cases of AI Agents. To achieve the results seen here, I went through multiple iterations and changes. AI Agents are not fully ready yet (although they are making huge progress every day). AI Agents still need to go through an improvement cycle to reach their full potential in real-world settings. &#x200B;

Let’s Build One Person Business Using 100% AI

AI made it possible for 9-to-5 workers to start a one-person business without quitting their jobs. Full Article https://preview.redd.it/tynb9y6z695d1.png?width=1309&format=png&auto=webp&s=b490d3676a63adcc01faff8c476056cb7d420022 https://i.redd.it/9x3okti0795d1.gif The Opportunities for Starting a Business ○ There are huge opportunities to start your own business by leveraging valuable skills to attract paying audiences. ○ New software and AI platforms make it easier to distribute products/services and automate tasks that were previously time-consuming. Our One Person Book Publication House ○ This article explores building a one-person AI-powered business focused on publishing books. ○ Users input data on a topic, and AI generates a comprehensive book structure and content based on that. ○ The generated content can be formatted, designed, and published digitally or in print easily. Why Read This Article? ○ It presents an innovative AI-powered approach to streamline the book publishing process. ○ It provides technical implementation details using LLM, Python and the Streamlit library as a reference. ○ It highlights AI's potential in automating creative tasks like writing and content creation. Approaching the One Person Business ○ Reflect on areas where you overcame personal struggles and gained valuable skills. ○ Leverage that expertise to build an AI business serving others facing similar obstacles. ○ Use AI tools to create content, automate processes, and efficiently scale your offerings. The Publication Business Idea ○ Focus on writing and publishing small books using AI writing assistants. ○ AI can streamline research, writing drafts, outlines, and ideas across genres. ○ Concentrate efforts on editing, formatting, and marketing while AI handles writing. The Book Generation Process ○ Users input structured topic data like outlines, key points, and references. ○ Advanced AI language models generate flowing book content from that data. ○ Minimal human effort is needed beyond initial inputs and refinement. ○ AI systems automatically handle formatting, design, and publishing. Technical Implementation ○ Includes a Book class to represent a book's hierarchical structure in Python. ○ Functions to generate book structures and section content using AI models. ○ Integrates with a Streamlit app for user input and output. ○ Allows downloading the final book in Markdown format. Closing Thoughts ○ This AI-powered approach makes book writing and publishing more accessible to individuals. ○ AI handles the heavy lifting, with humans providing quality control through editing. ○ It opens up possibilities for innovative knowledge sharing as technology evolves.

Best way to pivot into AI/ML as a non-dev engineer?

I’m a biomedical engineer with a Masters, working in the Medical device industry for over a decade now. I have an interest in learning AI/ML to pivot my career. I know some basic python but I’m not a developer by any means. Most of my career is in the product/design quality engineering and regulatory compliance side of the business. Currently my role is in Failure Analysis for software medical devices. I’ve considered taking the Google Cloud ML Engineer related courses to get the certification, but I’m not sure if it will actually help pivot me into this field. Perhaps my focus should be more on the MLOps side of things as it may be an easier leap? I want to make a jump due a higher salary ceiling for AI/ML roles and I also have a genuine interest in automation. Overall just a bit confused and wanted to know what are the best options to pursue, and path to follow. Any guidance from folks who pivoted from other non-dev engineering would be super helpful. Thanks!

Best way to pivot into AI/ML as a non-dev engineer?

I’m a biomedical engineer with a Masters, working in the Medical device industry for over a decade now. I have an interest in learning AI/ML to pivot my career. I know some basic python but I’m not a developer by any means. Most of my career is in the product/design quality engineering and regulatory compliance side of the business. Currently my role is in Failure Analysis for software medical devices. I’ve considered taking the Google Cloud ML Engineer related courses to get the certification, but I’m not sure if it will actually help pivot me into this field. Perhaps my focus should be more on the MLOps side of things as it may be an easier leap? I want to make a jump due a higher salary ceiling for AI/ML roles and I also have a genuine interest in automation. Overall just a bit confused and wanted to know what are the best options to pursue, and path to follow. Any guidance from folks who pivoted from other non-dev engineering would be super helpful. Thanks!

I started with 0 AI knowledge on the 2nd of Jan 2024 and blogged and studied it for 365. Here is a summary.

FULL BLOG POST AND MORE INFO IN THE FIRST COMMENT :) Edit in title: 365 days\* (and spelling) Coming from a background in accounting and data analysis, my familiarity with AI was minimal. Prior to this, my understanding was limited to linear regression, R-squared, the power rule in differential calculus, and working experience using Python and SQL for data manipulation. I studied free online lectures, courses, read books. \Time Spent on Theory vs Practice\ At the end it turns out I spent almost the same amount of time on theory and practice. While reviewing my year, I found that after learning something from a course/lecture in one of the next days I immediately applied it - either through exercises, making a Kaggle notebook or by working on a project. \2024 Learning Journey Topic Breakdown\ One thing I learned is that \fundamentals\ matter. I discovered that anyone can make a model, but it's important to make models that add business value. In addition, in order to properly understand the inner-workings of models I wanted to do a proper coverage of stats & probability, and the math behind AI. I also delved into 'traditional' ML (linear models, trees), and also deep learning (NLP, CV, Speech, Graphs) which was great. It's important to note that I didn't start with stats & math, I was guiding myself and I started with traditional and some GenAI but soon after I started to ask a lot of 'why's as to why things work and this led me to study more about stats&math. Soon I also realised \Data is King\ so I delved into data engineering and all the practices and ideas it covers. In addition to Data Eng, I got interested in MLOps. I wanted to know what happens with models after we evaluate them on a test set - well it turns out there is a whole field behind it, and I was immediately hooked. Making a model is not just taking data from Kaggle and doing train/test eval, we need to start with a business case, present a proper case to add business value and then it is a whole lifecycle of development, testing, maintenance and monitoring. \Wordcloud\ After removing some of the generically repeated words, I created this work cloud from the most used works in my 365 blog posts. The top words being:- model and data - not surprising as they go hand in hand- value - as models need to deliver value- feature (engineering) - a crucial step in model development- system - this is mostly because of my interest in data engineering and MLOps I hope you find my summary and blog interesting. https://preview.redd.it/pxohznpy4dae1.png?width=2134&format=png&auto=webp&s=03c16bb3535d75d1f009b44ee5164cc3e6483ac4 https://preview.redd.it/0y47rrpy4dae1.png?width=1040&format=png&auto=webp&s=f1fdf7764c7151ff0a05ae92777c5bb7d52f4359 https://preview.redd.it/e59inppy4dae1.png?width=1566&format=png&auto=webp&s=2566033777a90410277350947617d3ce8406be15

Is MIT Sloan's: "AI: Implications for Business Strategy Online Short Course" worth the money?

Hey everyone, I'm a CPA and have no IT background, but since I have some time in October due to a career break, I was thinking about taking this course: https://www.getsmarter.com/products/mit-sloan-artificial-intelligence-implications-for-business-strategy-online-program?focused=true I think it might be an interesting start to become an early follower in this whole AI story in Finance and Audit. I honestly don't see myself coding, and I don't think that's what would be expected from me as a Finance Manager in the future. But... $4,300 is quite a price tag for an online course. But then again, if I want to effectively use it in a next career step, it would probably pay out to have an actual certificate instead of one of the many (certainly very good) free courses. &#x200B; What are your thoughts? Does anyone have experience with this or a similar program?

How to Start Research in Computer Science & AI in 2025 – A Modernized Framework

Over a decade ago, I wrote two articles: "A Beginner’s Guide to Computer Science Research" and "How to Start a Research Work in Computer Science: A Framework for Beginners" \- that have been used at several universities around the world for the same purpose. These articles aimed to help students and early-career researchers navigate the complexities of academic research in computer science. However, since 2014, the research landscape has changed dramatically with the rise of AI, automation, and powerful collaborative tools. Now, in 2025, starting research in computer science and AI is more accessible than ever. With AI-powered research assistants, open-access repositories, and real-time collaborative platforms, researchers can work more efficiently and focus on innovation. I recently published an updated guide in The Times of India, presenting a modern “Eight-Step Approach to Research” framework that integrates the latest methodologies and tools for AI and CS research. This framework is designed to help students and researchers independently explore their chosen topics while leveraging cutting-edge technology. If you’re curious about how to streamline your research workflow, enhance your literature review process, and effectively collaborate in the AI research space, check out the article here: 🔗 How to Start a Research Work in Computer Science and AI in 2025 – An Updated Framework Block Diagram of “Eight-Step Approach to Research” in 2025 Would love to hear thoughts from the ML research community—what tools and techniques do you use to make research more efficient in 2025? Let’s discuss! 🚀

MarkDrop

I’m excited to share my Python package, Markdrop, which has hit 5.01k+ downloads in just a month, so updated it just now! 🚀 It’s a powerful tool for converting PDF documents into structured formats like Markdown (.md) and HTML (.html) while automatically processing images and tables into descriptions for downstream use. Here's what Markdrop does: Key Features: PDF to Markdown/HTML Conversion: Converts PDFs into clean, structured Markdown files (.md) or HTML outputs, preserving the content layout. AI-Powered Descriptions: Replaces tables and images with descriptive summaries generated by LLM, making the content fully textual and easy to analyze. Earlier I added support of 6 different LLM Clients, but to improve the inference time, now this supports only GEMINI\API\KEY and OPENAI\API\KEY. Downloadable Tables: Can add accurate download buttons in HTML for tables, allowing users to download them as Excel files. Seamless Table and Image Handling: Extracts tables and images, generating detailed summaries for each, which are then embedded into the final Markdown document. At the end, one can have a .md file that contains only textual data, including the AI-generated summaries of tables, images, graphs, etc. This results in a highly portable format that can be used directly for several downstream tasks, such as: Can be directly integrated into a RAG pipeline for enhanced content understanding and querying on documents containg useful images and tabular data. Ideal for automated content summarization and report generation. Facilitates extracting key data points from tables and images for further analysis. The .md files can serve as input for machine learning tasks or data-driven projects. Ideal for data extraction, simplifying the task of gathering key data from tables and images. The downloadable table feature is perfect for analysts, reducing the manual task of copying tables into Excel. Markdrop streamlines workflows for document processing, saving time and enhancing productivity. You can easily install it via: pip install markdrop There’s also a Colab demo available to try it out directly: Open in Colab. Github Repo If you've used Markdrop or plan to, I’d love to hear your feedback! Share your experience, any improvements, or how it helped in your workflow. Check it out on PyPI and let me know your thoughts!

Tried no-code AI builder Lovable

So I recently got some time to check out Lovable, a new no-code platform that’s been making waves. I built three projects: Crypto Coin Tracker Simple CRM Netflix-Style Streaming Site What I Liked: • Editable Display Items: Lovable makes tweaking components straightforward. You can select a specific element and prompt around just that (eg: a button) instead of the whole app/website. • Community-Driven Templates: A ton of pre-built templates are available for remixing, simplifying prototyping. Plus, any project created on the free tier becomes publicly accessible, thus creating a bunch of community templates to be used as inspiration. Pricing: Lovable’s pricing is so similar to Bolt.new. Both their free tiers suck and don’t give you much. The starter tiers are worth it at $20/m. For a detailed walkthrough of my experience with Lovable, check out this video. https://youtu.be/QZi9JvIKgJE?si=E8umG6LilCJQNmJy I’d love to hear your thoughts—are you using Lovable, Bolt.new, or another platform? Share your experiences below!

Building a No-Code AI Customer Service Tool While Working 9-5 | All real - No BS

I want to share my journey of building Chaterimo, my first revenue-generating side project that I've been working on for the past 1.5 years alongside my day job. What started as a solution to make AI chatbots more accessible has grown to over 300 signups, 30 paying customers, and 50,000+ customer queries handled. The Problem I Wanted to Solve: It started with my father's business struggling with customer service - hiring staff was expensive and they would eventually leave, creating a constant cycle of training new people. I decided to help by building a livechat chatbot powered by AI to handle customer queries. The first version was basic (running on ChatGPT-3 with 4k tokens), but it worked! Seeing its success at my father's business, I realized this could help many other businesses too. As I kept improving it and adding features, I expanded to focus on e-commerce stores facing similar challenges. What Makes Chaterimo Different: True no-code setup: Install and run in seconds Choice of AI Models: ChatGPT by default, with options for Claude and the latest Gemini Flexible API Integration: Bring your own API keys for cheaper, unlimited messaging Smart Context Understanding: Can search Google or scan the current webpage to provide relevant answers Lead Generation: Capture and manage potential customer information Rich Integrations: Works with Shopify, Facebook Messenger, and Make for automation Customizable Bot Personality: Edit your chatbot's role and behavior through system prompts The Journey: This is my first side project that's actually generating revenue ($500+ MRR), unlike my previous "just for fun" projects. The past 1.5 years have been a learning experience, balancing development with a full-time job. What started as a simple idea has evolved based on real user feedback and needs. Current Metrics: 300+ total signups 30 paying customers 50,000+ customer queries successfully handled by AI $500+ monthly recurring revenue All while maintaining a 9-5 job Some Things I've Learned: Focus on making things simpler, not adding more features Listen to users - they'll tell you what they really need Flexibility matters - letting users use their own API keys was a game-changer Building something you believe in makes all the difference I'm still actively improving Chaterimo based on feedback. If you're running a website or e-commerce store and want to try it out, I'd love to hear your thoughts. What's Next: I'm focused on making the onboarding even smoother and adding more customization options while keeping the core simplicity that makes Chaterimo work. Would love to hear your thoughts or answer any questions! Has anyone else built successful side projects while working full-time? What were your biggest learnings?

I'm a designer with no coding experience – built an AI storytelling site for kids using GPT

A friend asked me to help design an AI tool for kids to create their own stories. I'm a designer, not a developer, but I was curious how far I could take it myself. I used GPT + some no-code tools (mainly Lovable) and surprisingly ended up with a working MVP. It’s super rough but functional — and I learned a lot. Curious if anyone else here has tried making stuff for kids. Would love thoughts on how to simplify it further or what you’d expect from a tool like this.

Why I would encourage everyone to create a side project

Many people are afraid to start working on their projects, fearing they will be unsuccessful and waste a lot of time without gaining anything in return. However, this is the biggest trap of all: you actually gain much more than just money. Even if you don't become super successful and make millions of dollars, what is it really about? When you work on your project, you immerse yourself in development across all aspects. For example, when I used to work, I focused solely on my direct responsibilities. But when you create your project, you cannot limit yourself to a narrow range of tasks; you need to handle everything. If it's a website or an app, you must manage the frontend, backend, and deployment. If it's an app, you need to upload it to stores and understand legal nuances like terms of use and privacy policies. This is just one part of it. Here, you already realize the wealth of knowledge you can gain. Additionally, you are likely to enhance your competence in the technical aspects of your work. Now, let's move to part two—part one is about creating, and part two is about selling. Selling is essentially a separate art and often more complex than development. Thus, you will probably have to immerse yourself in a completely new area and gain experience in it. On top of that, there's another nice bonus: introductions. If you develop a product publicly, you will receive feedback, and perhaps someone will appreciate your project. That person may reach out to you, leading to new connections and acquaintances—often very valuable ones. So even if you don't earn a penny from your project, you will have gained tremendous experience. Of course, if your project consists merely of jumping into AI, writing something, and publishing it immediately without thoughtful consideration, it's unlikely you'll gain any benefit. Therefore, every time I complete a project, I never focus on making millions of dollars. Instead, I first thank the universe for the opportunities I had to create this project, gain experience, and meet wonderful people. Good luck!

I built a library to visualize and edit audio filters

Hey everyone! TLDR: No fancy AI Agents or trendy micro-SaaS here — just an old-school library. Scroll down for the demo link! 🙃 App Demo The Story Behind Several years ago, I deep-dived into reverse engineering the parameter system used in VAG (Volkswagen, Audi, Porsche, etc) infotainment units. I managed to decode their binary format for storing settings for each car type and body style. To explain it simply - their firmware contains equalizer settings for each channel of the on-board 5.1 speaker system based on cabin volume and other parameters, very similar to how home theater systems are configured (gains, delays, limiters, etc). I published this research for the car enthusiast community. While the interest was huge, the reach remained small since most community members weren't familiar with hex editors. Only a few could really replicate what I documented. After some time, I built a web application that visualized these settings and allowed to unpack, edit and repack that data back into the binary format. Nowadays The original project was pretty messy (spaghetti code, honestly) and had a very narrow focus. But then I realized the visualization library itself could be useful for any audio processing software. When I first tried to visualize audio filters with that project, I hit a wall. Most charting libraries are built for business data, all those "enterprise-ready visualization solutions". But NONE of them is designed for audio-specific needs. D3.js is the only real option here — it’s powerful but requires days of digging through docs just to get basic styling right. And if you want interactive features like drag-and-drop? Good luck with that. (Fun fact: due to D3's multiple abstraction layers, just the same filter calculations in DSSSP are 1.4-2x faster than D3's implementation). So, I built a custom vector-based graph from scratch with a modern React stack. The library focuses on one thing - audio filters. No unnecessary abstractions, no enterprise bloat, just fast and convenient (I hope!) tools for tools for audio processing software. Core Features Logarithmic frequency response visualization Interactive biquad filter manipulation Custom audio calculation engine Drag-and-drop + Mouse wheel controls Flexible theming API Technical Details Built with React + SVG (no Canvas) Zero external dependencies besides React Full TypeScript support Live Demo & Docs & GitHub This is the first public release, landing page is missing, and the backlog is huge, and docs do not cover some aspects. (You know, there's never a perfect timimng - I just had to stop implementing my ideas and make it community driven). I'd love to see what you could build with these components. What's missing? What could be improved? I'm still lacking the understanding of how it could gain some cash flow, while staying open-source. Any ideas?

How I got 1000 users on day one.

This might sound like a small number, depending on who you ask, but you know it’s a start. I’ll just share my learnings so far. Introduction: The product is simple: you type what you want to build, like, let's say, a SaaS idea, and it generates the code using a framework of your choice (like NextJS). Currently, it only generates front-end code. The marketing strategy was mainly focused on social media. My social media stats are as follows: I have a whopping 14 followers on Twitter, and 10 of them are bot accounts, and on LinkedIn, it’s about 400 or so. Launching on LinkedIn: LinkedIn is unique in two different ways: The algorithm is friendly to the little guy. Your network (the people) aren’t always friendly to the little guy. Let me elaborate. This is something I learned today, actually. When I posted for the first time and asked about three of my friends to repost it, within the first hour there were about 200 views, and the click-through rate was around 40%. This was really good, given that it was in the morning. I don’t know the exact factors, but I did have a video in my post, and those three reposts probably amplified it. However, people don’t seem to like or comment on it as much as you would think. Most of my connections are CS students because I am a recent grad, so it seems like most people can relate to this product, but none of them would even put a comment or a like. At the same time, I see people liking posts from big brands like OpenAI, Microsoft, etc. I am really confused, to be honest. However, throughout the day, the view count was going up, and people were coming. Launching on Twitter: Twitter didn’t really work for me at all. I think you need a decent audience. But there are tweets like “What startup are you working on?” type questions, and from that, I find you get a couple of views on your profile. Even though Twitter didn’t really help with the views, one guy tweeted, “Keep posting on Twitter and one day this might become something like Notion.” That really made my day, to be honest. Launching on Discord: This worked really well, to be honest, especially given that I was in a lot of Discord servers where there are software devs. If you use the right language that resonates with them, it’s a home run. Not much to say, but don’t use marketing lingo; people don’t like it there. Instagram and TikTok didn’t really work. Mainly, I think my video didn’t really resonate much. Finally, Facebook Launch: The Facebook reels didn’t really do the trick. Then I posted in a bunch of groups, and still, it didn’t really do anything. But then I sent cold DMs on Facebook, and that had a pretty high open rate because I sent them to people who I saw commented on posts related to what my product was solving. Obviously, after a while, Facebook blocks the ability to send DMs. That’s all for now. Thanks I’ll post my promo video in the comment section just so that you know the video and why it might have resonated with some platforms. Also this is the first time I made a video and I’m actually proud of making that more than the product itself. To summarize, for this idea LinkedIn worked really well, because of the algorithm not the ppl commenting and liking which is what I thought should be the way. Followed by Discord groups and Facebook DMs. The video I made seemed to resonate really well with the LinkedIn audience (the engagement was around 60%) despite falling in TikTok and other video sharing platforms.

Compare trading strategies on the fly - pnl.ai - please check it out

Part of my covid project and part of my long obsession with prediction markets, I have created a web page that displays and allows to compare best and worst performing trading strategies. TL;DR: best stocks + best strategies -> the list of top and bottom performing trading algorithms.  Product Typically, trading newsletters and stock-scanners display only price return for top market gainers and losers. I have forever been interested in inspecting top and bottom performing trading strategies for a given set of securities and could not find any websites that do that. So, I decided to create a tool of my own. I wanted the tool that would help me to answer questions like if there is a better strategy than buy and hold, should I follow greed and fear indicator of the market or do the opposite. Top and bottom performing securities do not tell you if a stock is going to go up or down, but they do alert you to rapidly changing market conditions, such as change in the competitive landscape, impending lawsuits, changes in the company's management and, at the very least, the stocks you should avoid in your programmatic trading. Top strategies do all that, but they can also alert you to a change in the market regime. For example, MACD strategy, which is a variant of oscillator strategy, executed on Citibank stock returned 20% in the first half of 2020. In the same time period, the Citibank stock went down and "BuyAndHold" strategy, which is pretty much what it sounds, lost 45%. Now, compare that to the end of 2020 through spring of 2021, when MACD lost 1% and "BuyAndHold" gained 70%. This happened due to the change in the market due to the rally in financial stocks at the end of 2020. The market player who detect change in the market conditions first will reap most benefits. Another example, TSLA since the beginning of 2021 until end of April lost 7%. The StopLoss strategy sells the position after abrupt price drop and waits until the price returns to the level before the drop. For the same time interval the StopLoss strategy gained 10%. In this particular example, StopLoss outperformed BuyAndHold. To me personally, the most important feature is the ability to quickly tweak and modify trading strategies and observe change in their performance. You can change strategies parameters on the fly and even design your own custom trading strategy. In the end, I developed a tool I can use for myself but hope other investors who are experimenting with trading algorithms will find it useful as well. I called it "Profit and Loss AI", or PnL.ai for short. PnL.ai Description The web-tool in the link below allows you to customize parameters of existing strategies and essentially create your own strategy and seeing how it will compare to the set of original strategies. http://ec2-54-185-19-38.us-west-2.compute.amazonaws.com:5006/srv In the section above you can specify security and data range. In the section below you can choose strategy to customize and modify it's parameters. The strategy comparison table will automatically update and will display a newly created strategy side by side with the original strategies. Technology The tool is developed on bokeh and python and allows you to edit configuration parameters of each strategy all without programming knowledge. The strategies are fully specified via key/value pairs in the format of ini files used to initialize programs. The strategy classes are autogenerated by reading the ini config files dynamically using "factory" pattern. You can find a simplified code in this github repo: https://github.com/varturas/PnlAITk Next Steps In the future I want to give users ability to monitor their chosen strategy by receiving trading algo alerts whenever performance of their custom trading algo is changes significantly. I'm going to be adding more strategies, some of standard technical analysis variety and some will be more custom and more advanced. I'll also be adding more columns to the performance table to give better information. You can receive daily newsletter with the list of trading strategies generated by above-mentioned web-tool by registering on http://pnl.ai/ and checking subscribe checkmark.

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension &#x200B; https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing &#x200B; https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) &#x200B; https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. &#x200B; https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

How I built my SaaS and earned $273 MRR in the first month

Hi everyone! I’m Alex Varga, an indie developer. Last year, I focused on accelerating my development speed and launched 10 projects in 12 months. One of them called Bulk Image Generation started growing through SEO, so I decided to focus on it. After one month of SEO efforts, it’s generating $273 MRR. I hope my experience will be useful to others. Concept bulkimagegeneration.com website helps to generate up to 100 images in 15 seconds using AI I was using Google, started with keywords like "Bulk Image ..." a lot of them are Bulk Image Resizer, Downloader etc. But there was no Bulk Image Generator. I thought: yeah, this domain is available, let's buy. So I bought bulkimagegeneration.com and bulkimagegenerator.com So, the app concept is to help people generate images with AI at scale: let\`s say 100 images in 15 seconds. Marketing Gap https://preview.redd.it/4luzib02bbie1.png?width=1905&format=png&auto=webp&s=cbe845107aca46ae5729dfe121fefd5e9cdab9ac Most builders create a product first and figure out how to sell it later. I took a completely different approach with Bulk Image Generator. I identified a market gap and secured a domain name that matched exactly what people were searching for and launched app. https://preview.redd.it/h6vwur34bbie1.png?width=1905&format=png&auto=webp&s=9a163ff6f503be4c175c6e5e82e2003b32df1fe0 Growth Strategy SEO has become the main acquisition channel, so I’ve decided to focus even more on it with this experiment. Almost every day, I publish either a new article or a free micro-app (as a lead magnet) for Bulk Image Generator. I also tried Google Ads, spent $20, and got a $0.35 CPC. https://preview.redd.it/3rhnzvs6bbie1.png?width=1905&format=png&auto=webp&s=f9819d1e82d3e2429d6ccb7b00dcac86a7a351c2 In comparison, the Free Image to Text Prompt Converter (one of the lead magnets) has a $0.011 CPC, which is more than 30 times cheaper than Google Ads. So I decided not to focus now on paid ads. https://preview.redd.it/p333fyl9bbie1.png?width=1905&format=png&auto=webp&s=2e96532d7709b44b7459e7ccf37ef9a0fa784728 After using our free tools, some users explore our main product - a bulk image generation service. Users pay a monthly subscription to get credits, which they can spend on image generation, face swaps, and bulk background removal. Currently, this app generates around $250 in Monthly Recurring Revenue: https://preview.redd.it/9wcm0tjfbbie1.png?width=1905&format=png&auto=webp&s=41bcdd4f7594b09087c51cc5044e4b9c94c129c8 SEO Keyword Research I use Semrush or similar tools to find keywords with a search volume greater than 300 and then write articles targeting those keywords. If the topic has enough potential, I might create a free tool (e.g., a Free Image to Text Prompt Converter) to attract more users. Occasions matter. For instance, I wrote an article about creating images for Super Bowl ads, which led to one paying user who replicated the exact creatives showcased in the article https://preview.redd.it/shpax6mlbbie1.png?width=1905&format=png&auto=webp&s=d491385761df126424c2f9ba14c5da15f8cbb603 AI Tools Aggregators This can be an excellent acquisition channel. When BulkImageGeneration.com was featured in an article on Toolify.ai, I immediately gained three paying users (\~$60). I took 2 more AI Aggregators, and on average I had CPC = $0.2, which is a fair price and usually it has ROAs > 100%. However, some major aggregators are expensive ($300–400 per placement). I want to try it once I reach $500+ MRR. Next Steps bulkimagegeneration.com currently ranks #1 in search results for relevant keywords (e.g., “bulk image generation,” “bulk image generator”). I plan to keep producing content targeting niche keywords and timely occasions. buy more places in AI Aggregators I also want to reach out to YouTubers and ask them to include Bulk in their reviews for free

I made a bunch of side projects over the last 9 months, and even accrued 500+ accounts and some donations!

I just stumbled upon this subreddit and have a bunch of fun projects I'd like to present, any thoughts/feedback/criticism, etc. all welcome. So, first things first, a little about me, I work full time in an unrelated job, but have picked up full stack and mobile programming. I have two roommates who help a bit in their own way, one is a server expert and happened to have a server in our apartment basement, and the other is my brother and he picked up some frontend programming. We're all avid cyclists and decided to start building about 9 months ago. Our first idea was https://sherpa-map.com a SPA website allowing users to create cycling routes, send them to their Garmin devices, download them as GPX files, etc. This site uses the open-source software Graphhopper on the backend which I've augmented to send back surface type information. This site has a loooonnnggg list of features, from the simple, like a live weather radar, to the extreme like this functionality: &#x200B; AI surface classification This video demonstrates the ability to classify road surface types in real time using high-resolution satellite imagery of road portions with unknown surface types! I trained a Pytorch resnet 50 model with tuned hyperparameters and 10 epochs on 200,000 satellite images of roads with known surface types! (We host a OSM Postgres server with coordinates of roads and their associated surface types, I made a script to pull images of said roads for training). I built the model into a secondary backend written in flask and piped the images being used back through live web sockets to my node.js backend to the person who is logged in! &#x200B; Okay, on to the next side project, a cycling physics simulator! https://sherpa-map.com/cycling-route-calculator.html Cycling Physics Simulation This site lets users enter information about their bike setup, upload or use a preset route, and enter in their physical information to see how different changes in their setup might affect how fast they will be throughout a course! It can also pull complex weather information throughout the course and give a full suite of nutrition details! &#x200B; Okay, Next project! The Activity Racer! https://sherpa-map.com/activity-racer.html Activity Racer This site lets users upload their own or competitors' GPX activity files and line them up against each other at any point in an event, to see who was faster where! It's great if you've done the same even year after year with differing setups, allowing you to get insights as to which might have done better at what point. &#x200B; Okay, final project, this one's pretty half-baked as I'm still in the process of implementing so many other things, a podcast creation app! (I was bored and just started working on this a week or so ago, for no good reason). Currently, this one lives on https://sherpa-map.com/podcast.html This podcasting web app creates a peer to peer to peer... mesh network using webRTC so, small groups can communicate with the highest level of fidelity both in audio and video! Simply enter a room name and have other users enter the room name as well and they're connected! I've already used tensorflow.js AI to allow a blur background option, similar to MS Teams, whereby bodypix classifier AI picks out the person and I use a blur on a JS canvas behind them. I also went a little bit off the deep end and managed to implement the RNNoise background noise suppressor on the frontend, it's written in C, but I was able to use Windows Subsystem for Linux + emscrption to compile it in just the right way, with exposed malloc and free and a JS wrapper to use on the frontend in WASM. I actually use WASM (typically Rust) in many fun ways throughout all of these projects. I'm also in the middle of recreating the first site in React-Native + Maplibre for IOS and Android as individual APPs. In addition, I'm also working on the integration of my main site into a different project for a different group. So, I have a fun collection of side projects with slightly different GUIs, across different platforms with no coherent landing page as of yet but I've been having a blaaaast putting them together. As a final note, I even have a bit of an easter egg in the automated email system I use for account verifications and password resets do\not\reply@sherpa-map.com I hooked it up to ChatGPT API and told it it is a disgruntled worker whose sole task in life is to watch a do\not\reply email box and respond sarcastic/snarky to anyone who dares send a message to it, if AI comes for humanity, I bet I'll be on a list for this one lol.

Day 1 of my BIP for my AdonisJS Boilerplate (turbosaas) [Built in public]

Hello everyone, here is day 1 (not really, I started a bit earlier) of my project: A boilerplate using AdonisJS, Inertia What technologies are used/present? AdonisJS Inertia Stripe OpenAI TailwindCSS Vite (React) Why? Firstly, I want to save time when launching my projects, and I think you do too, so I've included as many relevant features as possible. I'm tired of seeing attitudes like 'develop your SaaS in 1 hour and produce terrible code!' The purpose of this codebase is to provide the highest quality code possible and to maintain that standard throughout the development process. You might spend an extra 20 minutes doing things right, but you'll save 2 hours on refactoring. And no, you won't have to pay for updates. (WTF by the way?) Why these technologies? I've seen a lot of NextJS for boilerplates, and I've also used NextJS before, but I quickly abandoned it. It quickly becomes a mess You lose track of what is what, and start doing anything Every update breaks your application Whereas with AdonisJS, life is beautiful. There are plenty of community packages already available, and everything you need is here. What am I offering? Authentication: Social authentication, OTP, Magic Links, and credentials, along with complete account management features like password recovery. Payment & Mailing Integration: Seamless integration from start to finish, with multiple options to choose from. Detailed Documentation: Thorough explanations of every aspect, covering even the smallest, potentially confusing details in the code. Maintainable & Scalable Code: Organized by features, allowing you to easily drag and drop features to extend functionality. Developer Tools: Handy commands for generating new features and automatically adding necessary imports; a complete config to enable/disable a feature in less than 10 seconds... Pre-made Pages: Ready-to-use pages such as an admin dashboard for tasks like automatically updating products on Stripe. Extensive Component Library: A variety of components to streamline development. I've designed this boilerplate to be as developer-friendly and robust as possible, aiming to support maintainability and scalability from the get-go. Summary of today and previous days Day 2 Stripe is a nightmare to set up if you've never done it before, it quickly becomes tedious. But I've finally finished setting everything up: one-time payments, subscriptions, and subscription updates. It was complicated. Today I finally implemented the 'forgot password' option, and I've completed all the authentication by adding magic links (working with OTP). I also set up automatic deployment with GitHub Actions, and everything works well. The build runs with the action to ensure everything goes smoothly, then using SSH, I pull the project, build it, and launch it. Tomorrow: What I want to do tomorrow Tomorrow, I want to create the blog, because yes, I want to include a blog as well, and especially complete it as soon as possible so it can be available on turbosaas(dot)dev, and write my build in public. It will probably use markdown. Thank you for reading this short build in public, you can also check out how it's going on turbosaas(dot)dev.

I created a free workout plan generator

I created a GPT-powered workout training plan generator : https://train-programs.ai/. It's using your goal, preferences and physiological data to define a tailor-made training plan for workout at the gym or at home with bodyweight. I decided to make it 100% free after it reaches... 0 customer after my launch on ProductHunt (and I don't have an audience to share the tool with). I'm building the tool in public on X (https://twitter.com/GuillaumeGay\) and I just implemented the multimodal functionnality: it will create a plan based on a photo of you by analysing your body fat, strenghts, potential weaknesses and your morphology. Feel free to try it. I'm also trying to find the good marketing angle. Should it be used by people, by coaches to get faster to create personnalized plans, for gym, for fitness apps, and so on. I'm happy to read your ideas!

I made a website to generate craft ideas from existing materials

Idea: When browsing crafts groups, I noticed that members searched for craft ideas, either randomly, using available materials, or recycling existing things: First attempt: This attempt was a failure. After studying the idea well, I started trying to implement it with the help of Gpt. Because I am a beginner in programming, I only have a little experience in. html and css. I used gpt for php and js. The goal of the site was for the user to enter the materials he owns and the degree of difficulty of implementation to get a title for the idea. And how to implement it. This was all writing generated through the open ai api. After a few struggles, it became clear to me that writing could not describe the idea as it is. I changed the idea. Ideas are generated using images. The results were amazing. Here I faced a budget problem, as the subscriptions to the API for images were very high in my opinion. Because I plan to make the tool free.So I left the project. Second attempt. A year later while I was browsing I discovered stability.ai. From stablediffision, I found their prices to be reasonable, so I returned to the project and completed it. Website link: Craftivi

Finally launched my own app in the app store!

After reading on the sidelines here for about a year I just launched Kalo. My app is the 100th million ai powered calorie-counting app, hahaha. I know I know. Here it comes: Kalo Screenshots Despite being in a crowded space, Kalo has some caveats I am a bit proud of: \- I am a daily user of my app. Everything that bugs me will be gone ASAP. \- I have already lost 10kg with Kalo. I can't do any sports due to an energy-debilitating sickness (hello my me/cfs friends 👋), so this is huge. \- I HATE nudging. Hence, Kalo has no streaks, no notifications to rip off your valuable time. It’s just a tool to track calories and learn to get a feel for it. \- Ease of daily use and doing anything so it doesn't feel like a grind is Kalo's mission. I already implemented a lot of ways to quickly access tracking and leaving the app. \- Next feature will be tracking your own progress with some proper research based analytics is the one next step, that Im working on. \- Data: Minimal footprint as possible. Anything is currently saved only on the device, especially all health data. Check Kalo out here: https://apps.apple.com/de/app/kalo/id6739449751?l=en-GB Tech used to make it possible: There are some terrific security functions in here, and a robust paywall integration, both of which I could never have done without the MVP help of \- Claude and GPT \- Claude's Project function was basically my base project folder here. Claude is perfect when it comes to traditional features. Anything more recent than iOS14 can become a very difficult endeavour \- GPT 4o was great for error logging overview and general sorting measures. Claude's message restriction could be fended of many times here. \- GPT 1o became available more recently and its coding is a lot more robust than 4o. This helped me to not clog Claude with tedious bug fixing. Also it helped when Claude ran away in terrible directions Pre knowledge: I was a digital product designer way back, so I know a thing or two about making things easier to use, especially when it comes to the ease of daily use. Marketing: Will be my biggest focus now. I am quite shit at it, which means It can only get better. It's gonna be some rough weather to get eyes on my app. If anyone thinks they can help or knows how to, any tips are appreciated. Thats it for now. I'll try and keep you updated. I am happy. Let's see if this app will make me happy on a nicer bed, or a jet ski. Again, happy to get your impression of Kalo: https://apps.apple.com/de/app/kalo/id6739449751?l=en-GB

I spent 6 months on a web app as a side project, and got 0 users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I very rarely have stuff to post on Reddit, but I share how my project is going on, just random stuff, and memes on X. In case few might want to keep up 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2B products beats building B2C products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I Made $20K in 2 Months by Building in Public on X

Hey everyone, I wanted to share my journey of making $20K in just 2 months by leveraging Twitter (X) and building in public. It’s been an exciting ride, and I hope my story inspires others to take action on their ideas. Here’s exactly what I did: Building in Public I started sharing everything about my work openly. My wins, struggles, and process. I showed: How I build MVPs for clients. The tools I use (Next.js, Supabase, Cursor AI, etc.). The challenges I face and how I solve them. Transparency builds trust, and trust brings clients. Consistency is Key For the past 2 months, I’ve posted consistently on X, even when I felt like no one was watching. Here’s what I focused on: Sharing value (pro tips, workflows, tools). Asking for advice and engaging with my community. Highlighting my projects and client work. Building an audience takes time, but showing up daily pays off. Personal Brand = Inbound Clients I never did any “engagement farming” or gimmicky posts. I just shared my knowledge, and it led to over 35M views on my tweets and 7K followers. Many of these followers turned into inbound client leads. I’ve always believed: Share value for free, and charge for implementation. The Power of Community Engaging with my community on X has been game-changing. People have: Helped refine my processes. Shared valuable tools and advice. Connected me to opportunities I wouldn’t have found otherwise. Key Takeaway: You don’t need a perfect process or a huge following to start. Be consistent. Build in public. Share your journey. In 2 months, I’ve gone from wondering if this would work to making $20K by simply showing up and adding value. If you’re thinking about building in public or starting a personal brand, DO IT. It works. Feel free to ask me anything. I’m happy to share more details about my process, tools, or lessons learned! Let’s build together.

How I Implemented OpenAI's API In My First SaaS! DebateTrend!

About Me I'm a 17 y/o aspiring solopreneur from Bulgaria! I have a passion for 3D printing, coding, video creation, and space! My Project https://debatetrend.com is a website where you can debate with AI on different topics! You can have multiple debates with different debate styles for different lengths of time! The special part is that at the end of each debate, you can have another AI look through the debate! It will give you and the AI you debated with a score from a system I call "debate score" It will also give you recommendations on where you can improve your debating skills! Quick showcase How I implemented AI - ChatGPT 4-o mini It's my first time implementing AI in a project but I think I got the hang of it relatively quickly! Here's a diagram explaining what I did Diagram of the process of debate creation. I used the assistants API from the OpenAI API. Using the threads functionality, I created a different thread operated by an assistant I had already made. When a user creates a debate my app creates a thread with custom information that was decided by the user. I save parts of the thread object in my MongoDB database which is hosted on Atlas. After that, I redirect the user to a generated page in which you can chat with the AI. I maintain the connection using Pusher which is what I use for web sockets. When a user refreshes the page the previous messages are displayed by making a call to the API with the thread id. After that, I retrieve the user messages while still allowing the user to continue the debate. This is part of what I do on the back end. Of course, I have some security measures in check but I don't know if they are enough. I chose the 4-o mini because it's still very intelligent, with a good response time, and a lot cheaper than 4-o. My Tech Stack Language: Javascript Database: MongoDB hosted on Atlas Hosting: Vercel Framework: Express Auth: PassportJs Emails: Resend Payments: Stripe Front End: TailWindCSS, some regular CSS, and DaisyUI WebSockets: Pusher, because Vercel = no sockets integrated into your web app which I found the painful way AI: OpenAI’s API ChatGPT 4-o mini Do you think I could have done anything better? I would love to hear your opinions!

Running and selling multiple side projects alongside a 9-5

My current side project started 56 days ago when I started writing 1,000 words per day. My core businesses are an agency and job board, and I just needed a creative outlet. The likes of Chris Guillebeau and Nathan Barry attribute their progression to writing so I thought I’d see if it might do the same for me. At first I was just vomiting words onto the screen, I made a blog and wrote mainly technical guides related to my skills. Over time I realised I was writing more and more about running a business as a solopreneur, or lean operator. There is tons of content out there giving you the Birds Eye of going from 0 to £10m. Inspiring stuff, but I think there is a void in real content, explaining the nuts and bolts of the how.  What is the day-to-day like for the solopreneurs who make a good living and have plenty of free time? That’s what I’m striving for anyway. I’m not talking about the 7-figure outliers. Or the ones teaching you to make content so you can have a business teaching others how to make content, and so on. I’m also sick of the ‘I made $X in 5 minutes and how you can too’  So, I started chatting to people in my network who run lean businesses and/or side hustles. I ask them a bit about their journey and ask them to teach something - how they operate, or a skill/process/system/tool that other people like you/me will find useful. One of my first chats was with Sam Dickie, who runs multiple side projects so thought I’d share here, see if others find it useful and get some feedback. I’ve removed all links as I’ve never posted on Reddit before so conscious of not being promotional, I’m posting this stuff to a tiny email list of friends with no upsells. Just finding my feet on whether others find it useful or not: — Sam is a serial entrepreneur who builds projects in his spare time whilst working a 9-5. He’s scaled and sold multiple ventures and currently runs one of the best newsletters out there for builders and entrepreneurs. Building audience through newsletters has always been a cornerstone strategy for him, so, along with sharing his advice on solopreneurism, he’s also generously shared his lean newsletter writing process. About Sam Sam is a Senior Product Manager who has spent the last 15 years working in the tech sector after starting his career as a town planner. In addition to his job he spends some of his spare time building side projects. These have included a 3D printing startup, a tech directory, a newsletter, a beta product directory, and consultancy. Sam is the epitome of making a success out of following your interest and curiosity. It’s clear he enjoys his business ventures and builds in a risk-free way.   It’s often touted by business gurus to avoid building around your interests, but Sam bucks the trend successfully. I think he’s someone who has already found his 1,000 true fans.  Descending rabbit holes, Sam’s journey of invention and curation 3D printing Sam’s first foray into launching a startup was with Fiilo, a 3D printing business. This was at the height of the 3D printing craze and he self-admits that he used the launch as an excuse to buy a 3D printer. He ended up with two and launching a product called GrowGo. GrowGo is a sustainable 3D-printed product that turns any bottle into somewhere that you can grow plants and herbs. He eventually sold this business and the printers, making around £10k. Along the way, he was exposed to various business tasks, including building a website in Weebly, the biggest nocode website builder of the time, and built an API that enabled print on demand for his product. NoCode.Tech The experiences of building as someone non-technical led to numerous friends asking how he built all of this tech. Back then, nocode wasn’t popular, and it had almost zero search volume, so Sam created a basic directory. A quick landing page on Weebly with a basic value prop, a short explanation and a list of the tools he had used before. It hit the top spot on Product Hunt, and he landed 2,000 subscribers in the first 48 hours. But, he hadn’t built it at this point, so he set about getting to work. He built the directory and list to 30,000 subs and monetised the site through advertising. At its peak with Sam, it was receiving about £2,000 per month in ad revenue. He was still working his 9-5 at this point, so thought it might be a good time to exit. The site was still growing, but it was becoming anxiety inducing whilst he was still working full-time. So, he ended up selling the site and making friend’s with the buyer. Fast forwarding a bit, Nocode.tech was eventually acquired by Stackr, a nocode app. Sam was working for their competitor at the time and ended up being offered a job by his friend who acquired the site. All of this from a side project in his area of passion. Creator Club After selling the directory, Sam lost his outlet for sharing his tools and learnings.  Being fascinated with curation and loving sifting through for nuggets, he invested more time into his personal website and launched Creator Club newsletter. Sam writes monthly and currently has over 8,000 subs. It’s one of the few newsletters that I let bypass my email filters and land in my main inbox. Life as a Part-Time Multipreneur Side Hustler If it’s not obvious already Sam is a curiosity led business creator. He’s found that the products without a revenue focus or intention have ironically outperformed those created for the sole purpose of creating money. He enjoys working on his side hustles. He could have run the Nocode.Tech for 10 more years and wouldn’t have tired of it as it’s a byproduct of his interest. For this reason, he has also created the Beta Directory, simply because he loves unearthing early-stage products. He admits he gets the fear when he thinks about quitting his 9-5, although he suspects if he devoted the same energy to one of his projects it could replace his income (no doubts from me here). This same fear means that he can run his ventures with less fear. This way, he can experiment with freedom and isn’t risking the ranch with a young family to consider. For example, recently he stopped paid sponsors on his newsletter as it was more stress than the value of the income to him. Sam divides his time on evenings and weekends (unequally) between the following: Creator Club Validation Co Beta directory Consultancy The pure side hustle status magnifies the need to run lean, let’s jump into his process…. Sam’s lean newsletter curation and creation process Starting out publishing his personal newsletter Going against his expertise, Sam originally over-engineered his process.  He curated with Feedly and tried to automate the full writing process with Zapier. The trouble is that there are too many points of failure which can lead the whole  chain to break down, and you spend more time fixing the system. For a 200 subscriber newsletter, he needed to pare things back. His set-up now Sam scaled back and now simple builds automations when he needs them. He keeps the process simple, right down to the design and any welcome automations. Keeping things real We touched on the trend that keeping things raw is better. Content has come full circle with the advent of AI. Everything looks too perfect and consequently, people’s tastes are changing. Sam mentioned watermarks that show content isn’t AI written, and we referenced content such as Greg Isenberg’s sketches, and Chris Donnelly’s image posts. \\Step by Step Process:\\ Using Stoop Inbox to manage sources Curation with Pocket Managing content with Airtable and Zapier Using Bearly to summarise Substack for writing Monitoring content sources Sam uses Stoop Inbox, an RSS curation tool, to manage his content sources. It gives him a dedicated email address for newsletters and he follows an Inbox Zero methodology. He checks in daily in Stoop, and on X, Reddit and IndieHackers. With X, he just uses the standard interface but has been careful to curate his feed, sometimes adding in extra notifications to hear from interesting people. Highlighting content When curating links, Sam uses Arc browser and the Pocket extension to save links. It’s super simple and lightweight. He creates tags which trigger an automation that curates the link to Airtable. If you watch the video, here’s a shoutout to Alice, the AI interface I use which has recently featured on Product Hunt. It’s a fantastic tool with bags of potential to enhance a solopreneur’s life. Ranking and sorting content He sends the links indexed using Pocket to a basic Airtable base via Zapier. From there, he grades the content and sets aside some time to read it in more depth. Pocket pulls through the title, metadata, and URL link. Review Sam does this manually but has used a tool as a shortcut for digesting long form content — Bearly.ai. Bearly.ai was created by Trung Phan and linking back to raw content, Trung is 1/3 of the hosts on the Not Investment Advice podcast. Its irreverent style and thumbnail are an example of a successful podcast that doesn’t over polish. Writing it all up Being a huge Notion fan (check out the free templates on his site), Sam originally used Notion for writing and linked it into Revue. When Elon sunsetted Revue, he switched to Substack. He loves the Substack interface so drafts in Substack based on a duplication of last month’s edition. Before publishing, Sam runs through a 10-point Notion checklist, which he shared with me. Parting Advice Keep your tool stack as lean as possible. Avoid tool switching to the shiny new object. Getting launched quickly is key. Don’t think that you have to be everywhere for distribution, Sam sticks with what he knows on X and LinkedIn. Overall, he advises just keeping things simple and therefore minimising risk. Resources He says they’re cliche, but I don’t agree; they’re timeless. Paul Graham of Y Combinator is someone Sam recommends following. He doesn’t write much, which is great as Sam gets anxiety when someone good often writes and he can’t keep up with the writing. His content is well thought out and distills complex concepts in entrepreneurship and startups. In addition, Sam loves Naval Ravikant’s approach. He mentions checking out the Almanac of Naval Ravikant for collected wisdom. Follow Sam’s Journey Again, not going to link here but you can find Sam’s stuff easily enough if you want to. His personal website is beautiful and contains loads of free downloads. He has also curated personal websites he admires if you need some inspiration. Sam is a super nice guy so reach out to him, I did before I started my personal blog recently, and he gave me some great advice. Also, worth keeping an eye on Validation Co, where he aims to help early-stage makers and creators validate their ideas. He’s building super slow — trying to enjoy the process without unachievable deadlines. Maintaining his stamina and passion. Amazing, I hope he writes more about that soon! -- That’s my second shot at an interview, hope you enjoyed it and found something useful in it. I’m talking to a marketplace founder who spends 2–3 hours per month his project, a multiple job board owner with a 9-5 and a leading book designer next. As this is my side project, should I keep going?

Solopreneur making $40k MRR with a No Code SaaS sideproject

Hey, I'm Elias and I do case studies analyzing successful startups and solopreneurs. I wanted to share the summarized version of this one with you because this entrepreneurial journey blew my mind. This post will be about FormulaBot (ExcelFormulaBot), an AI No Code SaaS founded by David Bressler back in August 2022. FormulaBot is currently making $40k MRR (monthly recurring revenue). How did the founder come up with the idea. David is a data guy who worked in analytics for several years. In July 2022, David got really interested in AI, especially ChatGPT. One night, he tried it out at home, just like we all did back in the time. But in his case, trying ChatGPT gave him a big idea. That idea ended up making him a lot of money and changing the life of 750 million people who use Excel. That night David started by asking GPT easy questions, then complex ones. Since he used Excel a lot and helped his colleagues with it, he thought about an AI that could make Excel easier, like generating formulas from text. He looked online but found nothing. Seeing a big chance, he decided to do something about it. What challenges did the founder face. But David didn’t have any idea about how to develop an app. However, with no-code tools this is not a problem anymore. He discovered Bubble, a no-code web app tool that could connect with the OpenAI API.After, learning Bubble from YouTube tutorials and through trial and error and spending his nights studying the OpenAI API documentation, he launched the first version of the app in around three weeks. Strategies that made the project successful. David validated his idea by posting about ExcelFormulaBot on a Reddit Excel subreddit, receiving surprising attention with 10,000 upvotes. This encouraged him to offer the tool for free to gather feedback. Facing a hefty $4,999 API bill after the Reddit post, David quickly monetized his product with a subscription-based SaaS website. On launch day, 82 customers signed up, surpassing his expectations. A successful Product Hunt launch followed, generating $2.4k in sales within 24 hours, and a TikTok influencer with 4.5 million followers brought in thousands of new users overnight with a viral video. Marketing approach: -Paid ads: FormulaBot boosted website traffic with Paid Ads, notably on Google Ads, prioritizing Quality Score. This ensured ads aligned better with user searches, maximizing visibility and cost-efficiency, targeting those seeking Excel formula assistance. -SEO: a) Content/Keyword optimization: FormulaBot improved its SEO by making helpful pages about Excel formulas, like guides on topics such as "How to use SUMIFS." b) Site Speed Enhancement: David boosted FormulaBot's marketing site speed by moving it from Bubble to Framer, aiming to improve user experience and SEO performance. c) On-page optimization: David optimized FormulaBot's on-page elements by adjusting title tags, meta descriptions, and content to enhance SEO performance and align with search intent. These strategic refinements aimed to address ranking declines and emphasize FormulaBot's uniqueness, ultimately improving its visibility and competitiveness in search results. -Virality: FormulaBot went viral as users found it highly useful and cool. Influencers on platforms like TikTok and Twitter shared it with their followers because they found it valuable. Offering numerous free features further enhanced its appeal. Lessons: successes and mistakes. ✅ Leverage industry expertise: David identified a problem in analytics and used his experience to start an online business addressing it, turning an industry challenge into a profitable venture. ✅ Embrace learning new skills: Despite lacking initial technical know-how, David learned what he needed to develop the software himself, demonstrating a commitment to continuous learning and adaptability crucial for success. ❌ Minimize dependency on third parties: Relying solely on the ChatGPT API poses risks for FormulaBot. Any issues with the API could disrupt functionality and limit scalability. ⁉️ Caution with free tools: Offering a free tool can attract users and drive viral growth, but converting them to paying customers is challenging. Avoid relying solely on a 100% free model unless your revenue comes from non-user sources like ads. For businesses dependent on user subscriptions or purchases, balancing user attraction with conversion challenges is crucial. How could you replicate this idea step-by-step. To replicate the success of FormulaBot and similar AI wrapper startups, it's crucial to tread carefully in a competitive market. Avoid mere replication of existing solutions unless you can offer something distinct or superior. Consider these steps to effectively develop an AI Wrapper/ChatGPT wrapper product using Bubble as a no-code tool: Design the user interface: Utilize Bubble's drag-and-drop editor to create a user-friendly interface with input fields, buttons, and result displays. Set up workflows: Define workflows to connect the interface with the ChatGPT API, enabling seamless interaction between users and the AI. Integrate the ChatGPT API: Obtain the API key from OpenAI and integrate it into your app using Bubble's API connector feature. Test and gather feedback: Thoroughly test your app, soliciting feedback to refine functionality and usability. Refine and optimize: Continuously improve your app based on user input and testing results to enhance performance and user experience. The in-depth version of the case study was originally posted here. Feel free to comment if you have any questions, and let me know which similar ideas you'd like me to analyze.

I am building my agency to help founders build AI startups after 2 successful AI SaaS exits and 4 failures

Hey everyone, I have been building AI products before ChatGPT was launched. In these years, I have managed to launch, scale and exit 2 SaaS products successfully. Today I am launching a new service offering - Query Labs - Helping you build AI agents for your startups. Like all my previous products, I will be building this in public and share my learning along the way. Here's what I have built so far : Microsponsors ( Fail ) My first product ever. I tried to create a marketplace for newsletter writers to find sponsorship opportunity. Got a few very big newsletter listed on the marketplace as well. However, building marketplace is tough. I found it very difficult to bring in sponsors. Ended up shutting it down, AI Query (Exit - Pre revenue ) It was the second half of 2022 and GPT-3 was the most advance AI on the market. I decided to build a tool that can help developers and non-technical folks write SQL queries by just asking in plain english. I got my first taste of success with this. Had a decent offer even before I figured out monetisation. Accepted the offer to focus on my next product which had already started gaining traction AI Excel Bot ( Exit - Revenue Generating ) AI Excel Bot was my wild success. I had worked hard on the SEO for the site, along with the UI / UX to make it the best AI to write excel formulas and general excel task. There was already a large competitor in the market. However, the reality is that you don't need to be the top player. There is always room for multiple players to survive in a large market. You just need to find the good differentiating factor For AI Excel Bot, the differentiator was the chrome extension, that helped users access it anywhere on the internet. Scaled the product to more than 40k users at the time of exit. However, in the end I decided to exit and focus on my software service business that needed more time. Tutore AI ( Fail ) I wanted to build something useful for students to help them learn better. Tutore was my idea to build AI tools for students. I did launch quickly with multiple tools. However, wasn't motivated enough to continue with the grind. I have decided to sell the product. Have had some meetings with potential buyers but didn't agree on price. Prompt Hackers ( 1k users but no revenue ) Prompt Hackers is a directory of AI prompts for all the use cases you can image. I focused a lot on bringing traffic and newsletter subscription from the day 1. I have never had a problem bringing initial set of users to my products. Prompt Hackers was getting close to 20k page views a month. At the same time we had close to 1k newsletter subscribers. Since our target customers were people choosing to use ChatGPT / Bard instead of some specific software for their task, I built a Prompt Generation and Prompt Optimisation AI. Along with this I also created features to build private prompt library. To make the experience even better, I launched a Chrome Extension that helps users access the prompt generation AI and their prompt library while using ChatGPT. However, I couldn't figure out monetisation. I still get close to 4k page views per month with no marketing at all. There are users who use the AI tools and the prompt library feature daily. But, since I couldn't figure out monetisation, I decided to not put time into the project. There you go. These are all the products I have built in the last 3 years. I have been heavy investing myself in the latest tech in LLMs and AI agents. I know the biggest challenge for AI founders is the AI agents and backend pipelines. That's why I am launching Query Labs. To help you build the best AI implementation for your innovative AI startup. I would love to hear feedback from the community. I will be sharing my learning with my new service along the way. Thanks!

What are Boilerplates?

What are Boilerplates? Boilerplate originally referred to the rolled steel used to make boilers for steam engines in the 19th century. Over time, the term evolved to describe any standardized piece of text or code that can be reused without significant changes. Interest in SaaS has been on the rise, and many more people now want to build products. However, building products from scratch takes a lot of time, and it can be extremely frustrating. Enter SaaS Boilerplates With the standardization of stacks and basic systems that govern SaaS tools, it has become evident that there was a need, and the time was ripe for SaaS Boilerplates. SaaS Boilerplates come with landing pages, website components, authentication modules, payment modules, and various other standard features that can save developers a significant amount of time and cost. The market is flooded with Boilerplates for various tech stacks, such as NextJS, Laravel, Swift, NuxtJS, and so forth. Pros and Cons of Boilerplates Pros Save a significant amount of time and money Reduce frustration for developers as the redundant tasks are taken care of Boilerplates often follow best practices For anywhere between $49 and $299, they provide terrific value for those looking to build something very quickly Most importantly, Boilerplates also enable aspiring founders and builders with limited technical resources or abilities to ship their products faster and more cheaply. They are beacons of hope for non-technical founders looking to build a product quickly. Cons Limited flexibility May become outdated fairly quickly Setting them up still requires time Similar landing pages and design themes can make the product look like a clone Marc Lou’s Shipfast For most of us, Marc Lou popularized the idea of SaaS Boilerplate. Marc Lou launched Shipfast in August 2023. He had built 27 projects prior to this and Shipfast was nothing but all his basic code organised properly. At that time, there were no solid NextJS boilerplates, and Shipfast just took off. He got traction via Product Hunt, Twitter and Hacker News and soon Shipfast went viral. Shipfast now generates $130K/mo, just 9 months after its launch. Marc has been building Shipfast in public, which has led to a lot of interest in SaaS Boilerplates. The market is now flooded with boilerplates for every major tech stack. Marc reaped the benefits of the first mover’s advantage as well as the social proof via his Shipfast community. I don’t think any other boilerplates are as successful as Shipfast, but there are quite a few good ones out there. Shipixen* has grossed over $20K in the 5 months Makerkit* does \~$3500/mo Moreover, there are many open-source boilerplates available for popular stacks such as NextJS. The Evolution of Boilerplates Boilerplates are quickly turning into no-code/low-code code generation tools. For instance, Shipixen allows you to generate custom code for landing pages, waitlist pages and blogs using a simple User Interface. Boilerplates are perfectly posied to sit between code and no-code. Allow the flexibility of code with the interface of a no-code tool — that will be the core value proposition of SaaS boilerplates. Should you build a Boilerplate? Well, the market is flooded, but I believe there’s still an opportunity to leverage boilerplates. You can build boilerplates for certain types of apps or tools, such as Chrome extensions Boilerplates can act as a great lead funnel for building out a great productized services business No-code/low-code code generation boilerplates can become a big thing if you can help build complex tools Niche tech stack boilerplates may still be lucrative Known strategies for successfully building a boilerplate 👇🏻 Shipfast thrives because of social proof and community SaaSRock generates most of its traffic from its Gumroad listings and blogs Usenextbase and Shipixen are being built in public Many boilerplates start with waitlists They have a very clear value proposition around saving time and cost Design & No-Code Boilerplates Here is the corrected version with improved grammar and clarity: While SaaS (code) boilerplates have become fairly popular, other types of boilerplates are emerging in the market, such as design boilerplates and no-code boilerplates. To be honest, design boilerplates have been around for a while. You will find numerous landing page packs, component libraries, and so forth. Makers are now building kits that leverage standard libraries and technologies such as Tailwind CSS, Daisy UI, and more. Nick Buzz from the famous baked.design has this *50 Landing Page Design Kit* in Tailwind CSS & Figma which is wildly popular. Lastly, there is a trend of no-code boilerplates as well. Mohit is building a Bubble Boilerplate for the popular no-code platform — Bubble. All in all, I think that people want to build products and build them fast. Boilerplates help them save a significant amount of time and cost. More importantly, boilerplates are impulse purchases for people who have not shipped but who want to ship. Introducing BuilderKit.ai We have been building AI SaaS tools for quite a while now. 10+ products across text, image, speech, RAG — we have built em all. We figured that it seems easy but actually building these so called AI Wrappers can be time consuming and frustrating — there is a lot of nuance to it. So we built BuidlerKit.ai — a NextJS SaaS Boilerpalte It takes care of everything from landing pages, authentication, dashboarding, emails, SEO to payments — everything that you need to build your tool. It also comes with 8+ production-ready apps. Moreover, the BuilderKit community is an exclusive community of AI SaaS builders (Pro Only Access) The Pre Orders are now live at https://www.builderkit.ai (First 100 Customers get $100 Off — I think we have already done \~20 odd orders since the announcement yesterday, Grab your seat asap!) Starter Plan $49, Pro Plan @ $99

How I Built a $6k/mo Business with Cold Email

I scaled my SaaS to a $6k/mo business in under 6 months completely using cold email. However, the biggest takeaway for me is not a business that’s potentially worth 6-figure. It’s having a glance at the power of cold emails in the age of AI. It’s a rapidly evolving yet highly-effective channel, but no one talks about how to do it properly. Below is the what I needed 3 years ago, when I was stuck with 40 free users on my first app. An app I spent 2 years building into the void. Entrepreneurship is lonely. Especially when you are just starting out. Launching a startup feel like shouting into the dark. You pour your heart out. You think you have the next big idea, but no one cares. You write tweets, write blogs, build features, add tests. You talk to some lukewarm leads on Twitter. You do your big launch on Product Hunt. You might even get your first few sales. But after that, crickets... Then, you try every distribution channel out there. SEO Influencers Facebook ads Affiliates Newsletters Social media PPC Tiktok Press releases The reality is, none of them are that effective for early-stage startups. Because, let's face it, when you're just getting started, you have no clue what your customers truly desire. Without understanding their needs, you cannot create a product that resonates with them. It's as simple as that. So what’s the best distribution channel when you are doing a cold start? Cold emails. I know what you're thinking, but give me 10 seconds to change your mind: When I first heard about cold emailing I was like: “Hell no! I’m a developer, ain’t no way I’m talking to strangers.” That all changed on Jan 1st 2024, when I actually started sending cold emails to grow. Over the period of 6 months, I got over 1,700 users to sign up for my SaaS and grew it to a $6k/mo rapidly growing business. All from cold emails. Mastering Cold Emails = Your Superpower I might not recommend cold emails 3 years ago, but in 2024, I'd go all in with it. It used to be an expensive marketing channel bootstrapped startups can’t afford. You need to hire many assistants, build a list, research the leads, find emails, manage the mailboxes, email the leads, reply to emails, do meetings. follow up, get rejected... You had to hire at least 5 people just to get the ball rolling. The problem? Managing people sucks, and it doesn’t scale. That all changed with AI. Today, GPT-4 outperforms most human assistants. You can build an army of intelligent agents to help you complete tasks that’d previously be impossible without human input. Things that’d take a team of 10 assistants a week can now be done in 30 minutes with AI, at far superior quality with less headaches. You can throw 5000 names with website url at this pipeline and you’ll automatically have 5000 personalized emails ready to fire in 30 minutes. How amazing is that? Beyond being extremely accessible to developers who are already proficient in AI, cold email's got 3 superpowers that no other distribution channels can offer. Superpower 1/3 : You start a conversation with every single user. Every. Single. User. Let that sink in. This is incredibly powerful in the early stages, as it helps you establish rapport, bounce ideas off one another, offer 1:1 support, understand their needs, build personal relationships, and ultimately convert users into long-term fans of your product. From talking to 1000 users at the early stage, I had 20 users asking me to get on a call every week. If they are ready to buy, I do a sales call. If they are not sure, I do a user research call. At one point I even had to limit the number of calls I took to avoid burnout. The depth of the understanding of my customers’ needs is unparalleled. Using this insight, I refined the product to precisely cater to their requirements. Superpower 2/3 : You choose exactly who you talk to Unlike other distribution channels where you at best pick what someone's searching for, with cold emails, you have 100% control over who you talk to. Their company Job title Seniority level Number of employees Technology stack Growth rate Funding stage Product offerings Competitive landscape Social activity (Marital status - well, technically you can, but maybe not this one…) You can dial in this targeting to match your ICP exactly. The result is super low CAC and ultra high conversion rate. For example, My competitors are paying $10 per click for the keyword "HARO agency". I pay $0.19 per email sent, and $1.92 per signup At around $500 LTV, you can see how the first means a non-viable business. And the second means a cash-generating engine. Superpower 3/3 : Complete stealth mode Unlike other channels where competitors can easily reverse engineer or even abuse your marketing strategies, cold email operates in complete stealth mode. Every aspect is concealed from end to end: Your target audience Lead generation methods Number of leads targeted Email content Sales funnel This secrecy explains why there isn't much discussion about it online. Everyone is too focused on keeping their strategies close and reaping the rewards. That's precisely why I've chosen to share my insights on leveraging cold email to grow a successful SaaS business. More founders need to harness this channel to its fullest potential. In addition, I've more or less reached every user within my Total Addressable Market (TAM). So, if any competitor is reading this, don't bother trying to replicate it. The majority of potential users for this AI product are already onboard. To recap, the three superpowers of cold emails: You start a conversation with every single user → Accelerate to PMF You choose exactly who you talk to → Super-low CAC Complete stealth mode → Doesn’t attract competition By combining the three superpowers I helped my SaaS reach product-marketing-fit quickly and scale it to $6k per month while staying fully bootstrapped. I don't believe this was a coincidence. It's a replicable strategy for any startup. The blueprint is actually straightforward: Engage with a handful of customers Validate the idea Engage with numerous customers Scale to $5k/mo and beyond More early-stage founders should leverage cold emails for validation, and as their first distribution channel. And what would it do for you? Update: lots of DM asking about more specifics so I wrote about it here. https://coldstartblueprint.com/p/ai-agent-email-list-building

I built a free LinkedIn planning tool with integrated GPT-4

Last week I launched my product scribery.eu after building it over the the last 2 months on my own. For that, I used LowCode-Tools like FlutterFlow, Stripe or Firebase, because for me it was the only way to publish it without security risks and having a release date in this year. The main feature is to creating LinkedIn posts with help of AI (GPT-4) and schedule them. In 5 minutes, I scheduled 10 posts for the next 4 weeks! This is an absolute time saver for every entrepreneur who’s not having enough time to advertise their product over LinkedIn. I would be very happy, if you would test my product for free with the code Reddit2024 Normally the one-time-payment is 49€ for Premium, but with the code above you get Premium for free. Comment to learn more about me and scribery scribery in action!

Side project: entrepreneurship app

Hey everyone, I’m building a side project: an app that helps aspiring entrepreneurs and small business owners with personalized lessons on topics like marketing, finance, and operations, powered by an AI assistant courses would be industry specific eventually maybe not first launch. The goal is to make entrepreneurship more accessible and inclusive through gamified learning, industry-specific lessons, and community tools like discussion posts and messaging for ongoing support. I have a working prototype, but now I need advice with marketing, pitching, and gathering interest. I’m also planning to start a podcast to gather insights from small business owners and entrepreneurs prior to launch. Looking for feedback on: Is this idea worth pursuing? How can I improve the concept or marketing? Would you be interested in listening to a podcast focused on entrepreneurship and small business? Any advice on how to engage users effectively through community tools like messaging and discussion posts?

I spent 6 months on a web app as a side project, and got 0 users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I very rarely have stuff to post on Reddit, but I share how my project is going on, just random stuff, and memes on X. In case few might want to keep up 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2B products beats building B2C products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

How I went from $27 to $3K as a solopreneur still in a 9-5

My journey started back in November 2023. I was scrolling through Twitter and YouTube and saw a word that I had never come across before. Solopreneur. The word caught my eye. Mainly because I was pretty sure I knew what it meant even though it's not a word you'll find in the dictionary. I liked what it was describing. A solo entrepreneur. A one man business. It completely resonated with me. As a software engineer by trade I'm used to working alone, especially since the pandemic hit and we were forced to work remotely. See, I always wanted to ditch the 9-5 thing but thought that was too big and too scary for a single person to do. Surely you would need a lot of money to get started, right? Surely you would need investors? The whole concept seemed impossible to me. That was until I found all the success stories. I became obsessed with the concept of solopreneurship. As I went further down the rabbit hole I found people like Justin Welsh, Kieran Drew and Marc Louvion to name a few. All of whom have one person businesses making huge money every year. So I thought, if they can do it, why can't I? People like this have cleared the pathway for those looking to escape the 9-5 grind. I decided 2024 would be the year I try this out. My main goal for the year? Build a one man business, earn my first $ online and learn a sh\*t ton along the way. My main goal in general? Build my business to $100K per year, quit my 9-5 and live with freedom. From December 2023 to February 2024 I began brainstorming ideas. I was like a lost puppy looking for his ball. How on earth did people find good ideas? I began writing everything and anything that came to mind down in my notes app on my phone. By February I would have approximately 70 ideas. Each as weird and whacky as the other. I was skeptical though. If I went through all the trouble of building a product for one of these ideas how would I know if anyone would even be interested in using it? I got scared and took a break for a week. All these ideas seemed too big and the chance that they would take off into the atmosphere was slim (in my mind anyways). I was learning more and more about solopreneurship as the weeks went on so I decided to build a product centered around everything I was learning about. The idea was simple. Enter a business idea and use AI to give the user details about how to market it, who their target customers were, what to write on their landing page, etc. All for a measly $27 per use. I quickly built it and launched on March 3rd 2024. I posted about it on Indie Hackers, Reddit and Hacker News. I was so excited about the prospect of earning my first internet $! Surely everyone wanted to use my product! Nope...all I got was crickets. I was quickly brought back down to earth. That was until 5 days later. I looked at my phone and had a new Stripe notification! Cha-ching! My first internet $. What a feeling! That was goal number 1 complete. It would be another 6 days before I would get my second sale...and then another 15 days to get my third. It was an emotional rollercoaster. I went from feeling like quitting the 9-5 was actually possible to thinking that maybe the ups and downs aren't worth it. On one hand I had made my first internet dollar so I should my ecstatic, and don't get me wrong, I was but I wanted more. More validation that I could do this long term. By May I was starting to give up on the product. I had learned so much in the past few months about marketing, SEO, building an audience, etc. and I wanted to build something that I thought could have more success so I focused on one critical thing that I had learned about. What was it? Building a product that had SEO potential. A product that I knew hundreds of people were looking for. See this was my thinking - If I could find a keyword that people were searching for on Google hundreds/thousands of times every month and it was easy to rank high on search engines then I would go all in (in SEO land this equates to a Keyword that has a Keyword Difficulty of = 500). I began researching and found that the keyword "micro saas ideas" was being searched for around 600 times each month. Micro Saas was something that really interested me. It was perfect for solopreneurs. Small software products that 1 person could build. What's not to like if you're in the game of software and solopreneurship? Researching keywords like this became like a game for me. I was hooked. I was doing it every day, finding gems that were being searched for hundreds and thousands of times every month that still had potential. That's when I came up with my next product idea. I decided to create a database of Micro Saas Ideas all with this sort of SEO potential. See if you can build a product that you know people are looking for then that's all the validation you need. So I put this theory to the test. I created a database of Micro Saas Ideas with SEO Potential and launched it in June 2024. This time it was different. I made $700 in the first week of launching. A large contrast to my previous failed attempt at becoming the worlds greatest solopreneur. Since launch I have grown the product to $3K and I couldn't be happier. I know what you're saying, $3K isn't a lot. But it's validation. It's validation that I can earn $ online. Validation that I can grow a business and it gives me hope that one day I'll be able to quit that 9-5 grind. My plan is to keep growing the business. I expect there to be a few challenges up ahead but I'll tackle them as I go and learn from the failures and successes. I have a newsletter where I share Micro Saas Ideas with SEO potential every week which I'll leave below in the first comment. Feel free to come along for the ride. If not I hope this post brings you some value If you're thinking about starting as a solopreneur, stop thinking and start doing, you won't regret it.

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension &#x200B; https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing &#x200B; https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) &#x200B; https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. &#x200B; https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

How to get your first 10 customers with cold email

Cold email is an insane channel for growth, especially for bootstrapped startups as it's very low cost but completely scalable. Yet there's a huge difference between blind cold emailing and crafting personalized outreach for select individuals. The latter is a legit channel which makes many businesses scale in short amounts of time (i.e. see Alex Hormozi’s ‘$100 Million Dollar Offer’). My goal here is to help other founders do what I did but quicker. So you can learn faster. And then teach me something new too. These are the step-by-step lessons I've learnt as a bootstrapped founder, showing you how to use cold email to get your first customers: Find your leads Write engaging email copy Personalize your outreach Send emails Scale up Find your leads This is a key step. Once you figure out exactly who you want to target and where to find them, you'll be printing money. There's a few different ways to go about finding valuable leads. The secret? Keep testing different approaches until you strike gold. First, dedicate some time every day to find and organise leads. Then, keep an eye on your numbers and bounce rates. If something's not working, switch it up. Stick with what's bringing in results and ditch what's not. It's all about staying flexible and learning as you go. Apollo.io is a great starting point as an effective lead source. Their tool allows you to specify filters including job titles, location, company size, industry, keywords, technologies, and revenue. Get specific with your searches to find your ideal customers. Once you have some results you can save and export them, you'll get a list of contact information including name, email, company, LinkedIn, ready to be verified and used. LinkedIn Sales Navigator is another good source. You can either do manual searches or use a scraper to automate the process. The scrapers I'd recommend checking out are FindyMail and Evaboot. As with Apollo, it's best to get very specific with your targeting so you know the prospect will be interested in your offer. BuiltWith is more expensive but ideal if you're targeting competitors. With BuiltWith you can build lists based on what technologies companies are using. For example if you're selling a Shopify app, you'd want to know websites or stores using Shopify, and reach out to them. The best lead sources will always be those that haven't been contacted a lot in the past. If you are able to find places where your target audience uniquely hangs out, and you can get their company website domains, they have the potential to be scrapped, and you have a way to personalize like "I spotted your comment on XYZ website". Once you've got your leads, keep them organized. Set up folders for different niches, countries, company sizes, so you can review what works and what doesn't. One more thing – before you start firing off emails, make sure those addresses are verified. Always use an email verifier to clean up your list and avoid bounces that may affect your sending reputation, and land you in the spam folder. I use Neverbounce for this but there are other tools available. Write engaging email copy Writing a good copy that gets replies is difficult, it changes depending on your offer/audience and nobody knows what's going to work. The best approach is to keep testing different targeting and messaging until you find what works. However, there are some key rules to stick to that I've outlined. For the subject line, keep it short and personalized. Try to write something that sparks interest, and mention the recipients name: Thought you’d like this {{first name}} {{firstName}} - quick question For the email body it's best to use a framework of personalization, offer, then call to action. Personalization is an entire subject in its own right, which I've covered below. In short, a personalized email opener is the best way to grab their attention, and let them know the email is relevant to them and to keep reading. Take it from Alex Hormozi and his $100M Offers playbook – your offer is very important to get right. Make sure your offer hits the mark for your target audience, and get as specific as possible. For example: I built a SaaS shopify app for small ecommerce businesses selling apparel that doubles your revenue in 60-days or your money back. We developed a cold email personalization tool for lead generation agencies that saves hundreds of hours, and can 3x your reply rate. Lastly, the CTA. The goal here isn't to get sign-ups directly from your first email. It's better to ask a brief question about whether the prospect would be interested in learning more. Something very low friction, that warrants a response. Some examples might include: Would you be interested in learning more about this? Can we connect a bit more on this? Mind if I send over a loom I recorded for you? Never send any links in the first email. You've reached out to this person because you have good reason to believe they'd find real value in your offer, and you want to verify if that's the case. After you get one reply, this is a great positive signal and from there you can send a link, book a call, provide a free resource, whatever makes sense based on their response. Personalize your outreach Personalization is one of the most important parts of the process to get right. Your recipient probably receives a multitude of emails every day, how can you make yours stand out, letting them know you've done your research, and that your email is relevant to them? Personalizing each email ensures you get more positive replies, and avoid spam filters, as your email is unique and hasn't been copied and pasted a million times over. The goal is to spark the recipient's interest, and let them know that you're contacting them for good reason. You might mention a recent achievement, blog post or product release that led you to reach out to the prospect specifically. For example: Your post on "Doing Nothing" gave me a good chuckle. Savvy marketing on Cadbury's part. Saw that you've been at Google for just under a year now as a new VP of sales. Spotted that you've got over 7 years of experience in the digital marketing space. Ideally you'll mention something specifically about the prospect or their company that relates to your offer. The downside to personalization is that it's hard to get right, and very time consuming at scale, but totally worth it. Full disclosure, me and my partner Igor just launched our new startup ColdClicks which uses AI to generate hyper-personalized email openers at scale. We built the tool as we were sending hundreds of emails a day, and personalizing every individual email took hours out of our day. ColdClicks automates this process, saving you time and getting you 2-3x more replies. Send emails At this stage you've decided on who you're targeting, you've mined some leads, and written copy. Now it's time to get sending. You can do this manually by copy and pasting each message, but one of the reasons cold email is so powerful is that it's scalable. When you build a process that gets customers, you'll want to send as many emails as you can to your target market. To get started quickly, you can use a mail-merge gmail tool, the best I've used is Maileteor. With Maileteor you upload your lead data to Google sheets, set-up an email template and Mailmetor will send out emails every day automatically. In your template you can define variables including name, company, and personalization to ensure your email is unique for each recipient. Alternatively, you may opt for a more comprehensive tool such as Instantly. Instantly includes unlimited email sending and accounts. There's more initial setup involved as you'll need to set-up Google workspace, buy sending domains, and warm up your email accounts, but when you become familiar with the process you can build a powerful lead generation / customer acquisition machine. Some key points to note, it's very important to warm up any new email accounts you set up. Warmup is the process of gradually establishing a positive reputation with email service providers like Gmail or Yahoo. Make sure to set up DKIM and DMARC on those new email accounts too, to maximise your chances of landing in the inbox. Scale up Once you've found a process that works, good things happen, and it becomes a numbers game. As you get replies and start to see new users signing up, you'll want to scale the process and send more emails. It's straightforward to add new sending accounts in a sending tool like Instantly, and you'll want to broaden your targeting when mining to test new markets. Unfortunately, sending more emails usually comes with a drop in reply rate as you have less time to personalize your messaging for each recipient. This is where ColdClicks shines. The tool allows you to upload thousands of leads and generate perfectly relevant email personalizations for every lead in your list, then export to your favorite sending tool. The examples I listed above in the personalization section were all generated by ColdClicks. Wrapping it up Cold email is an amazing way to validate your product and get new customers. The channel gets a bad rap, but there's a huge difference between blind cold emailing and crafting personalized outreach for individuals who will find value in your product. It's perfect for bootstrapped founders due to its affordability and scalability, and it's the driver of growth for many SaaS businesses. Time to get your first 10 customers! As you start sending, make it a habit to regularly check for new leads. Always experiment with market/messaging, track every campaign so you can learn what's working and iterate, and when you do get positive responses, reply as soon as you can!

I built an app to find who’s interested in your app by monitoring social media

Hi everyone! I hope you’re all doing great folks! I’d love to know your thoughts about what I’ve been working on recently! 🙏 If you’re busy or wanna see the app scroll to the bottom to see the video demo, otherwise, continue reading. Very brief presentation of myself first: I’m Marvin, and I live in Florence, Italy, 👋 This year I decided to go all-in on solopreneurship, I’ve been in tech as Software Engineer first, and then in Engineering Leadership for 10+ years, I’ve always worked in startups, except for last year, when I was the Director of Engineering at the Linux Foundation. Follow me on X or subscribe to my newsletter if you’re curious about this journey. The vision Most founders start building digital startups because they love crafting and being impactful by helping other people or companies. First-time founders then face reality when they realize that nailing distribution is key. All other founders already learned this, most likely the hard way. The outcome is the same: a great product will unlikely succeed without great distribution. Letting people know about your product should be easier and not an unfair advantage. The following meme is so true, but also quite sad. I wanna help this to change by easing the marketing and distribution part. https://preview.redd.it/g52pz46upqtd1.png?width=679&format=png&auto=webp&s=cf8398a3592f25c05c396bb2ff5d028331a36315 The story behind Distribution is a huge space: lead generation, demand generation, content marketing, social media marketing, cold outreach, etc. I cannot solve everything altogether. A few months ago I was checking the traffic to a job board I own (NextCommit). That's when I noticed that the “baseline” traffic increased by almost 10x. 🤯 I started investigating why. I realized that the monthly traffic from Reddit increased from 10-ish to 350+. Yeah, the job board doesn’t get much traffic in total, but this was an interesting finding. After digging more, it seems that all that increase came from a single Reddit comment: https://www.reddit.com/r/remotework/comments/1crwcei/comment/l5fb1yy/ This is the moment when I realized two things: It’s cool that someone quoted it! Engaging with people on Reddit, even just through comments, can be VERY powerful. And this was just one single comment! https://preview.redd.it/nhxcv4h2qqtd1.png?width=1192&format=png&auto=webp&s=d31905f56ae59426108ddbb61f2d6b668eedf27a Some weeks later I started noticing a few apps like ReplyGuy. These were automatically engaging with Reddit posts identified through keywords. I decided to sign up for the free plan of ReplyGuy to know more, but many things didn’t convince me: One of the keywords I used for my job board was “remote” and that caused a lot of false positives, The generated replies were good as a kickstart, but most of the time they needed to be tuned to sound more like me. The latter is expected. In the end, the platform doesn’t know me, doesn’t know my opinions, doesn’t know my story, etc.. The only valuable feature left for me was identifying the posts, but that also didn’t work well for me due to false positives. I ended up using it after only 15 minutes. I’m not saying they did a poor job, but it was not working well for me. In the end, the product got quite some traction, so it helped confirm there’s interest in that kind of tool. What bothered me was the combination of auto-replies that felt non-authentic. It’s not that I’m against bots, automation is becoming more common, and people are getting used to it. But in this context, I believe bots should act as an extension of ourselves, enhancing our interactions rather than just generating generic responses (like tools such as HeyGen, Synthesia, PhotoAI). I’m not there yet with my app, but a lot can be done. I'd love to reach the point where a user feels confident to automate the replies because they sound as written by themselves. I then decided to start from the same space, helping engage with Reddit posts, for these reasons: I experienced myself that it can be impactful, It aligns with my vision to ease distribution, Some competitors validated that there’s interest in this specific feature and I could use it as a starting point, I’m confident I can provide a better experience even with what I already have. The current state The product currently enables you to: Create multiple projects and assign keywords, Find the posts that are relevant for engagement using a fuzzy match of keywords and post-filtered using AI to avoid false positives, Provide an analysis of each post to assess the best way to engage, Generate a helpful reply that you’d need to review and post. So currently the product is more on the demand gen side, but this is just the beginning. I’m speaking with people from Marketing, Sales, RevOps, and Growth agencies to better understand their lives, struggles, and pain points. This will help me ensure that I build a product that enables them to help users find the products they need. I’m currently looking for up to 10 people to join the closed beta for free. If you’re interested in joining or to get notified once generally available you can do it here! https://tally.so/r/3XYbj4 After the closed beta, I will start onboarding people in batches. This will let me gather feedback, iterate, and provide a great experience to everyone aligned with my vision. I’m not going to add auto-reply unless the conditions I explained above are met or someone convinces me there’s a good reason for doing so. Each batch will probably get bigger with an increasing price until I’m confident about making it generally available. The next steps The next steps will depend on the feedback I get from the customers and the learnings from the discovery calls I’m having. I will talk about future developments in another update, but I have some ideas already. Check out the demo video below, and I'd love to hear your thoughts! ❤️ Oh and BTW, the app is called HaveYouHeard! https://reddit.com/link/1fzsnrd/video/34lat9snpqtd1/player This is the link to Loom in case the upload doesn't work: https://www.loom.com/share/460c4033b1f94e3bb5e1d081a05eedfd

Meet Huppi: The Cashflow Management App for SME's

At Huppi, we are redefining the future of small business automation and financial management in emerging markets. As the next generation to Xero, focused initially on emerging markets, we empower entrepreneurs and small business owners with accounting solutions that go beyond bookkeeping—delivering AI enabled conversational WhatsApp commands for invoicing and payments, real-time insights, automation, and financial intelligence tailored for the modern business landscape, globally. Designed for fast moving small businesses in a modern environment, our platform simplifies compliance and tax, freeing business owners to focus on their business, enhancing daily operations and decision-making, and optimizing cash flow, enabling small enterprises to thrive in an increasingly digital economy. By harnessing the power of AI, we remove barriers to intensive operational processes and financial clarity, bridging the gap between small businesses and financial prosperity in the markets that need it most. Welcome to the new age of what an SME accounting platform should look like —where every small business has the tools to scale, compete, and succeed, all at a fraction of the price of legacy systems.

Enhancing Time Management & Journaling with AI: A Hybrid Physical-Digital Approach

Hey everyone! I wanted to share my experience combining AI, physical journaling, and time tracking - and get your thoughts on taking this further. Background: My AI-Enhanced Productivity Journey I recently did an intensive experiment tracking my time down to the minute (as a software engineer juggling multiple projects, Kendo practice, and side hustles). I used Claude/ChatGPT to analyze my patterns and got some fascinating insights about my productivity and habits. The AIs helped me spot patterns I was blind to and asked surprisingly thoughtful questions that made me reflect deeper. What really struck me was how AI turned from just an analysis tool into something like a wise friend who remembers everything and asks the right questions at the right time. This got me thinking about creating a more structured approach. The Hybrid Model Concept I'm exploring an idea that combines: Physical journaling/tracking (for tactile experience and mindfulness) AI-powered digital companion (for insights and reflection) Flexible input methods (write in a notebook, take photos, type, or voice record) The key insight is: while AI can track digital activities, our lives happen both online and offline. Sometimes we're in meetings, reading books, or having coffee with friends. By combining human input with AI analysis, we get both accuracy and insight. How It Would Work: \- Write in your physical journal/planner as usual \- Optionally snap photos or type key points into the app \- AI companion provides: \- Smart comparisons (today vs last week/month/year) \- Pattern recognition ("I notice you're most creative after morning exercise...") \- Thoughtful reflection prompts ("How has your approach to \[recurring challenge\] evolved?") \- Connection-making between entries ("This reminds me of what you wrote about...") What Makes This Different Human Agency: You control what to track and share, maintaining mindfulness AI as Coach: Beyond just tracking, it asks meaningful questions based on your patterns Temporal Intelligence: Helps you see how your behaviors and thoughts evolve over time Flexibility: Works whether you prefer paper, digital, or both Early Insights from My Testing: \- Initial tracking caused some anxiety (couldn't sleep first two nights!) but became natural \- AI feedback varies by tool (Claude more encouraging, ChatGPT more direct) \- The combination of manual tracking + AI analysis led to better self-awareness \- Having AI ask unexpected questions led to deeper insights than solo journaling Questions for the Community: Have you tried combining AI with traditional productivity/journaling methods? What worked/didn't? What kinds of AI-generated insights/questions would be most valuable to you? How would you balance the convenience of automation with the benefits of manual tracking? What features would make this truly useful for your productivity practice? I believe there's something powerful in combining the mindfulness of manual tracking, the wisdom of AI, and the flexibility of modern tools. But I'd love to hear your thoughts and experiences! Looking forward to the discussion! 🤔✍️

I’ve built a gaming recommendation and exploration platform called Which Game Next

Hello there! Me and a few of my best friends are software engineers, and we’ve been working part-time on developing a side project for the past 12 months. It’s called www.whichgamenext.com, and we’ve recently launched into open beta for everyone to check out. Your feedback would be invaluable to us! Our aim has been to build a gaming recommendation engine, alongside providing market oversight for where you can legally and officially purchase or obtain modern games from multiple stores and/or subscriptions. It’s often difficult to figure out what you have access to if you only have a single specific subscription, like Game Pass PC, or if you’re only interested in games on GOG/Nintendo (what a mix!). We started by identifying the available digital stores and subscriptions and slowly compiling our database using multiple automated services to gather data on these games. Think JustWatch, but for games! One major service we’ve partnered with is IGDB, which has been supplying us with JSON data dumps that served as the initial seed for our game data. A massive thank you to them for their continued support! With the data in place, we’ve been focusing on exploring new features. So far, this has included private and public user-generated lists, personal backlog tracking, and the ability to like or dislike games. We’re now improving our recommendation engine, tackling the complexities that come with it, and having a lot of fun along the way. We’re utilising modern AI strategies and solving fascinating problems related to large-scale data aggregation. We truly can’t wait to share this fantastic work! In addition to this, you can soon expect curated collections, articles about games, and supporting links to help you make informed, unbiased purchasing decisions. Your shared data will drive the recommendations. But it doesn’t stop there—we have plenty of other features on our radar, such as importing games from your favourite stores, syncing your gameplay time, surfacing data like “How Long to Beat,” and creating new and exciting ways to interact with this growing community! This is a passion project created by a group of gamers who want to spend their time and money wisely, without purchasing biases. Since it’s a side project, we mostly work on it at night, but we’re excited to grow the community, share our vision, and, who knows, maybe one day make it our full-time job! Let’s dive into the technical details: • Monorepo architecture: This speeds up development by sharing libraries, living style guides, configs, etc. Nx.js has been brilliant, enabling us to create a dependency graph of changes and only build/deploy what’s modified in a PR. • AWS: We’re using the free tier (with a few exceptions where we pay for smaller services). Achieving self-sufficiency is critical for us. Additionally, we applied to the AWS Startup Foundation programme and received $1,000 in AWS credits, which has been incredibly helpful! • Infrastructure: Fully deployed as code with Terraform. • Backends: Built using Express and Nest.js, split into around 40 projects and counting! Each project plays a unique role in gathering and syncing game data. • Scalability: Designed from the ground up, utilising AWS Lambdas with auto-scaling and load balancing. • Databases: We use Postgres with RDS and DynamoDB for storing various data. • Frontend stack: Built with React, Next.js, Tailwind, Zustand, TanStack Query, Jest, and Storybook. • CI/CD: Managed with GitHub Actions and Amplify hooks for deploying the frontends. • Admin portal: We’ve built a bespoke CMS to control the main website. It synchronises with external services, tracks game data changes, and allows us to selectively apply ‘patches’ from sites like IGDB. The system also includes data override and rollback capabilities, ensuring we maintain control over game data. • Automation: Partially automated, so manual intervention is rarely needed. • Scraping tools: Fully integrated into the admin portal with log trail capabilities. • Cloudflare: Used for on-the-fly image transformations; we’re considering moving to it full-time as our CDN for free WebP conversions. • Authentication: Handled by Cognito, with a custom frontend built from scratch. Key learnings so far: • AWS cold starts: Not ideal! While the platform is still new, we ping endpoints to keep them responsive. This won’t be an issue once traffic increases. • Lambda memory matters: We learned the hard way that low-memory configurations can delay responses by 2-3 seconds. • DynamoDB partition keys: If not designed correctly from the start, you might have to start over (yes, we’ve been there!). • GitHub Actions: Setting up node\_modules cache reuse takes time, but it’s worth it—don’t give up! We don’t know where this project will take us yet, but it’s been a fantastic journey so far. We’ve learned a lot, explored technologies we don’t typically use in our day jobs, and built something we’re genuinely passionate about. Your feedback would mean the world to us. What do you think of what we’ve done so far? What would you like to see added? Is this a service you’d use? Do you see the value in it as we do? Thanks for reading, and we hope to see you in the comments! (or our newly created /r/whichgamenext

Built an AI to stop me from procrastinating on Reddit, it actually spies on my browser tabs & it's kinda freaking me out (but it works)

hey guys, So, I have a problem. A major procrastination problem. You know the type? I start all good, like, "ok, I'm gonna spend the next 2 hrs REALLY researching this specific Reddit thread about optimizing workflow automation for small businesses." (That's literally what I'm supposed to be doing rn, lol) And then... BAM. Suddenly I'm 15 posts deep into r/aww looking at baby sloths, or somehow I've ended up on Wikipedia reading about competitive hot dog eating. It's like my brain has a mind of its own, seriously. I've tried everything. Cold Turkey, Freedom, all those blocker apps. And honestly? They kinda suck. They're so... blunt. Like, "NO REDDIT FOR U!!" But I need Reddit for my actual research! It is my research, ffs. The problem is those apps just see a URL and block it. They don't understand context. They're just digital bouncers, and terrible ones. Total roadblocks, and a complete pain. That's why I got desperate. I even spent, like, 3 solid hrs one night just chatting with an AI cuz I was too embarrassed to admit to my friends how bad I was at staying on track. Pathetic, I know. But that's when it hit me. I needed something that understood what I was supposed to be doing, and then actively, intelligently, stopped me when I got sidetracked. Something that, like, gets that this is what I meant to use, so it blocks other posts or subs. So, I built it. It's a Chrome extension, and it's basically like having a tiny, hyper-observant AI therapist/drill sergeant living in my browser. Here's the freaky part: it actually watches what I'm doing. Like, it learns my specific task. If I tell it I'm researching on Reddit, it lets me use Reddit, but only for that specific research. If I try to sneak off to r/funny or check my notifs, it knows. It's not just blocking URLs; it's analyzing the content of the pages I'm on and comparing it to what I'm supposed to be doing. It even has these lil "achievement" things, which sound cheesy, but seeing "Focused for 90 mins straight!" pop up is weirdly motivating. And it has this brutal feature that shows u, in plain numbers, how much time you've wasted. Ouch. It's been working, which is amazing, and scary at the same time! Like, the scary part is, it feels weird sharing my own edge over procrastination. I mean, if u use my lil tool too! It also kinda gives off that creepy, AI overlord watching my thoughts vibe? Why I'm even posting this: I'm looking for a few (maybe 5?) people who are as desperate as I was. People who've tried every productivity hack, app, and technique, and are still staring at the ceiling at 3 am, filled with regret. If this sounds familiar, DM "DM me". Tell me your worst procrastination story. The winner (loser?) gets a copy. I need honest, brutally honest, feedback. Does this actually work for anyone else, or am I just fooling myself? Edit: shared the extension with some of you, and for others you can give it a spin here i made it live to the chrome store: https://getfocusai.com/

I built an AI social monitoring that looks for relevant posts, not just keywords

Hey everyone! I've been working on a side project that I'm excited to share with you all—it's called BillyBuzz What is BillyBuzz? BillyBuzz is an AI-powered social monitoring tool that helps businesses spot and analyze relevant conversations on social media platforms, starting with Reddit. It surfaces the most promising leads directly to your Slack channels, email, or Discord, so you don't have to spend hours scrolling through threads. Why I Built It I was spending a ton of time searching for relevant posts in niche subreddits for another product I was working to get off the ground. It was not only time-consuming but also distracting (you know how easy it is to fall into a Reddit rabbit hole). I couldn't find any existing tool that did more than basic keyword searches—which wasn't enough, especially if your brand name has multiple meanings (like "Apple"). So, I decided to build BillyBuzz. It uses AI to understand your business, products, target audience, and value proposition, alongside specific keywords you might want to include. This way, it finds posts where you can genuinely contribute by introducing your product. I used BillyBuzz for a previous product launch and managed to grow it to over $80k/month in volume within about 3 months, purely through Reddit engagement. How It Works Add Information About Your Business: Input details about your business and products. Select Subreddits to Monitor: Choose the subreddits relevant to your niche. Receive Timely Alerts: Get notified via Slack, email, or Discord when relevant posts are identified. Features AI-Powered Relevancy Scoring: Goes beyond keywords by understanding the context to identify truly relevant opportunities. Subreddit Tracking: Monitor specific subreddits with AI-recommended keywords tailored to your company's needs. Real-Time Alerts: Checks for new relevant conversations every 15 minutes, so you can engage at the perfect time. Automated Categorization (Coming Soon): The AI will categorize conversations into topics like competitors, customer complaints, and more. Who It's For BillyBuzz is designed for startup founders, growth marketers, and small business owners who are tech-savvy and focused on scaling their operations. If you're looking to save time and engage more effectively with your target audience on social media, this might be up your alley. Looking for Feedback I'm sharing this here because I'd love to get your thoughts, feedback, or any suggestions you might have. If you're interested in checking it out, you can find more info here: https://billybuzz.com. Feel free to ask me anything or share your experiences with similar challenges!

0-20+ faceless AI automated YouTube channels in 1 year - my process and tools

First of all before diving deep into this process (scroll a bit below) I have to say something that everyone keeps asking me, is it profitable? Yes. It's by far my most profitable venture outside of my regular 9-5... But it took a lot of work, delegation and building processes to get here. So the one thing I would love to get out of this post - if you have any insights, feedback or tools I might be missing out post them below and let's help each other out. Now, how you can get started with (AI) YouTube automation: Pick a topic that is BOTH: a) in demand b) interesting to you & you have knowledge about Do everything yourself at first - delegate later No one cares about the videos as much as you do, so make sure to nail the ideation, scripts, editing, format and packaging yourself first. Now that we got that out of the way: Use this workflow: VidIQ - outliers sections is pure gold, I use it all the time to find trending video packaging, topics, etc. ChatGPT or Claude - high level video ideas at scale and your assistant (I use projects inside ChatGPT and its really good at managing and prioritizing). If you are using it for scripts please for the love of god, make final edits yourself by hand. Add character, personal insights, ideas, etc. Katalist AI - all in one video generator tool I use to quickly go from video idea to script, storyboard, AI voiceover and then final visuals. It's surprisingly good and to make a decent video it only takes about 1-2 hours in TOTAL. Once you understand how it works and have a process, delegate to tech savvy VAs / content creators for $5-$15/hour and you have final, good quality videos for less than $30. Pikzels / Krea AI - your AI thumbnail generator, I dont remember the last time we used Photoshop outside of quick text or image edits. Its basically AI image manipulation at scale and it costs 10-30x less than a human thumbnail designer and the thumbnails are really good. VidIQ+TubeBuddy - titles & optimization, but you have to know that most of the views come usually from recommended, so dont over obsess and add 392x keywords in your title and description. Its all about the packaging. Now whats left is track performance & iterate - it's practically impossible to nail it the first few times, but each video you make look at the data (not just in YT studio) and UNDERSTAND why it did not perform as well as you thought it would. Regarding monetization, adsense sucks - sell digital products. If I was relying on adsense alone I would never ever be profitable, but selling mini digital products and mentioning CTAs in the actual video not just in the description makes this super profitable and scaleable, especially since video production is so cheap. Final thoughts: (AI) YouTube automation absolutely works, but it’s not an overnight success or a total hands-off cashcow machine. It’s a real business and you need systems, consistent effort, iteration, failing and learning along the way. If you’ve got any tips, hidden gems or tools I might be missing, drop them below & let’s help each other out.

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension &#x200B; https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing &#x200B; https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) &#x200B; https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. &#x200B; https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

AI-Powered Business Analyst Tool Looking for Feedback

Hey r/sideproject! I’m excited to share a project I’ve been working on called Bianalytiq, a next-gen business intelligence platform designed to transform the way businesses interact with data through the power of AI. The Problem: SME companies struggle with data overload and the significant time investment required to generate actionable insights. Traditional data analysis methods are not only slow but often require extensive manual effort and are prone to errors. This makes it difficult for businesses to react quickly to new information and make informed decisions efficiently. Not everybody can write SQL or create/understand data dashboards.... AND - one big opportunity on market - non of the AI tools available on market offer reusable contexts focused on you as a company and your products. The Solution: Bianalytiq aims to solve these issues by automating tedious data analysis tasks and providing real-time insights. Here’s how: Reusable contexts: Let Bianalytiq learn everything about your company, your products, business model etc. - your company is your unique context. Autonomous AI Agents: Deploy AI agents that not only react to queries but proactively analyze data to uncover opportunities, tailored specifically to your business context. Real-Time Insights: With the use of Retrieval-Augmented Generation (RAG) technology, our platform delivers immediate, context-rich insights by dynamically accessing and analyzing connected databases and data warehouses. Integration with Existing Tools: Bianalytiq integrates seamlessly with popular tech stacks and communication platforms like Slack and Microsoft Teams, making it incredibly user-friendly and reducing the switch cost between applications. Why I’m Here: Before investing significant time and money I want to validate the product first and do pre-sale before releasing the MVP. I’ve developed a landing page for Bianalytiq and would love your feedback on both the service itself and the effectiveness of the landing page. Are the features presented clearly? Does the platform address the pain points you might experience in data analysis and decision-making processes? Here’s the link to the landing page: https://bianalytiq.com/ I appreciate any feedback or questions you have! Whether it's about the UI/UX of the site, the technical aspects of the service, or even the business model, I’m all ears. Your input will be invaluable :) Thanks for checking it out! https://preview.redd.it/t1dvp2q05dzc1.png?width=798&format=png&auto=webp&s=c7365b418abfc4d4260d9a23305ed3398e83c87b

I retired at 12 from my side project. AMA

Ya so i’m a 12 year old and i like to build stuff so I kept building and saw that school lunches were expensive so I built a saas and sold sandwiches as a service. I used this to cover all my living expenses and pretty much retired for the next 10-12 years Some advice: find a problem and a niche with a dedicated user base. in my case, kids needed what I was building to litewally survive don’t be afraid of building. My grampa told me he regrets not building things rather than building so I built ai saas is the future. think about how smart you could be if u ate ai sandwiches. u would easily get 10M ARR and AGI and u can retire too and change and manipulate time. I also used the AI from the sandwiches to automate a lot of my business tasks so now my business is run by AI because it’s smarter than me (because I’m just 12) ask me anything

I retired at 12 from my side project. AMA

Ya so i’m a 12 year old and i like to build stuff so I kept building and saw that school lunches were expensive so I built a saas and sold sandwiches as a service. I used this to cover all my living expenses and pretty much retired for the next 10-12 years Some advice: find a problem and a niche with a dedicated user base. in my case, kids needed what I was building to litewally survive don’t be afraid of building. My grampa told me he regrets not building things rather than building so I built ai saas is the future. think about how smart you could be if u ate ai sandwiches. u would easily get 10M ARR and AGI and u can retire too and change and manipulate time. I also used the AI from the sandwiches to automate a lot of my business tasks so now my business is run by AI because it’s smarter than me (because I’m just 12) ask me anything

I created a tool which helps busy tech people to build their resume. one-click, just linkedIn profile, ATS-Complaint, DOCX, multi-layered prompts, Claude AI, ChatGPT, and FREE (for now).

someone's generated resume link: https://resumebro.com I haven't done any proper launch yet currently testing the waters so far it has helped me secure few profile views from recruiters on LinkedIn when I used the resume generated from it. Note: this only works on technical profiles - and only those profile having bit of information on their LinkedIn as it reads the whole LinkedIn profile and then works its magic.

What I learn from my $200 MRR App I built 4 months ago

4 month ago, I am just a 10-years experienced product manager without any software development experience. I have an $3K/month job, but I am so tired, I don’t like my life, don’t like my boss, don’t like my daily work, that make me feeling I already died however I am still living. I yearn for freedom and want to live each day the way I want to. So I quit my job, and become a Indie developer to build my own business, my own app, even my own life. I am so grateful for this time and experience, now my app reach $200 MRR, still very little compared to my previous salary, but I never regret. I have learned lots of things from this time and experience, more than I had in last 10 years. Here is the time-line of my App: &#x200B; Sep 2023: Launch first version to iOS App store Oct 2023: Release in-app-purchase features and have first subscriber, the revenue in October is $154 Nov 2023: Change from subscription to pay per use, and I did lots of marketing jobs in November, however, the revenue reduced to only $40. Dec 2023: Change back to subscription, and stop some invalid marketing jobs, only keep the ones that actually work. I almost did nothing in December, and the revenue come to $243. During this process, I have learned lots of things, there are some of them that I think could help you as well. Web or App My App is an iOS app that only can running on Apple’s device such like iPhone/iPad or Mac with Apple silicon. Many people ask me why my product is an iOS app not a website, because they don’t have any Apple device. It's true that promoting an app is much harder than promoting a website. However I am now very glad I made an App and not a website! If I make a website, I don't think it's possible to make $100 in the first month. My App is about keyword research, to help people find some ideas from search keyword, because every keyword people searched in Google are representing a real need of them, also can be used in SEO field. However there are a lot of website tools about keyword research, some of them are famous like Ahrefs, SEMrush… I have no intention of competing with them. Actually I don’t have any chance. While in app store, there are little apps about keyword research, each of them have terrible data and user experience, that means if my app has better data and experience that could be my chance. In fact, the App store brings me 20 organic installs a day that Google would never have been able to bring me if I had a website, at least for the first few months. Furthermore, Apple nearly did everything for developer, I don’t need to care about user login, payment and so on, Apple did everything, I just need to call their API, that save lots of time, if I build a website, I need to implement login and payment by myself, that would add some extra work. Not to mention I'd need to buy servers and domains, that would cost me a lot of money. Although Apple will take 30% of the revenue, I can live with that in the early stages because the most important thing for me is to get the product to market as soon as possible. Actually thought Apple’s SMB program, the take rate is 15% now. So Web or App is not important in the early stage, time is important, if people need my product, it's easy to make a website one. More Users or More Valuable Users In November, I notice some users would like use my app, and they were meet paywall, but they never subscribe. I provided 7 day free trail, but it seem that they don’t like it. So I decide to change subscription to pay per use. Because as a user, I don’t like subscription as well, pay per use seem like more friendly. So I change from subscription to pay per use. People can afford $9.99 to subscribe monthly for unlimited use or pay $1.99 for each data they want(First purchase is $0.99 then $1.99). I was expecting more user to pay, but it was the complete opposite! Some users who would have paid a higher subscription fee are switching to a lower priced single payment. Users are encountering paywalls more often, and each time they need to make a decision about whether or not to pay, which increases the probability that they will abandon payment. This resulted in a 75% decrease in revenue in November. In fact, the mostly of my revenue comes from a handful of long-cycle subscribers, such as annual subscription. Few bring in most of the revenue, that is the most important thing I learned. You don't need a lot of customers, you just need more valuable ones. That's why it's only right to design a mechanism to filter out high-value customers and focus on them, all the things you want do is just let more people into the filter, and from that point of view, subscription with free trial period is the best way, even if most people don't like it. The rule of 20/80 will always be there. The most important thing is always focus on the 20 percent things and people. Effort does not always guarantee rewards. Unless one engages in deep thinking, or most efforts are invalid. I have been working very hard to promote my product for a period of time. It’s about in November. I did a lot of job, such as write script to send message to my potential clients on Fiverr, post and write comments on others post on Reddit, find related questions and answer them on Quora, post and comments on Twitte, etc. During that period, I was exhausted every day, but the outcome did not meet my expectations. There is only little growth on App installation, even less revenue than before. That make me frustrated. I finally realized that If I need to put in a tremendous amount of effort just to make a little progress, there is must something wrong. So I stop 80% of promote work I have ever did, only keep app store search ad, which will bring a installation with less than $0.5 cost. Then I dive into long time and deeply thinking, I spent more time on reading books, investigate other product with great MRR, watch interviews with people who are already living the kind of life I aspire to live, for example, u/levelsio. These things have given me great inspiration, and my life has become easier. It seems that the life I anticipated when I resigned is getting closer. I also have a clearer understanding of my app. Meanwhile, MRR has been growing. This experience let me learn that effort does not always guarantee results. Many times, our efforts are just wishful thinking, they are invalid, do the right thing after deeply thinking is more important. What Next? My goal is reach $3K MRR, as same as my job payment, I will never stop to building things, and I will keep my currently lifestyle. I still don't know how to get more people to use my app, but levelsio's interviews give me some inspiration that I can verified something by manually instead of build a software. I plan to launch a trend analysis product based on the keyword data provided by my current app. I have always wanted to combine AI to build such a product, but I didn't know how to do it. Now I intend to manually complete it first and start software development once there are paying users. If you are interested to my App, you could try it. Gotrends

I acquired a SaaS for ~5 figures to solve my content problem

In 2023 I bought a SaaS called Cuppa AI. I actually found the product on twitter, run by a very talented engineer in the UK.  I’ve spent tens of thousands of dollars on content for various media companies. In one consumer health company, it cost us around $200-$500 for each SEO optimized article. This adds up pretty quickly. Not forgetting the 20 hours of edits! This isn’t just an isolated problem for a single company. It’s industry wide and affects small business + agency owners alike. I spent over a decade in media, and have seen many agency founders complain about long lead times and high costs for low output.  This is an issue. Large swathes of would-be customers that prefer to consume content before buying are being ignored - either because it takes too long or costs too much for founders to scale this channel.   I eventually became tired of the media content game in 2022 and looked into using SaaS to solve my previous life’s challenges. I started building, acquiring and scaling a portfolio of products that I found useful in my day to day. But the content issue was still there.  So I started to look for ways to reduce the time + cost content burden for my own portfolio.   I initially discovered Cuppa using it for my own personal pains of content research, editing, publishing, and scaling. But then I saw potential. I wanted to turn it into an end to end solution for the content gap that myself and other business owners weren’t taking advantage of because of time, cost, or other priorities.  I sent a DM. Then a few calls later, I acquired it in June 2023.  I chose cuppa vs other competing products for a few reasons:  The founder gave excellent support during and post acquisition  It already had a large, loyal existing user base I’d personally used it and solved a pain with it. I saw the potential to solve many others for more people like me  The founder has put a ton of quality and care into it. There wasn’t a risk of picking up a patchy product, plus it already had great social distribution  It naturally fits my expertise from the ‘other side’. I was the original customer of it, so I knew I could evolve it with features that could create content at scale without losing the human touch  Since then we’ve added a lot of new stuff: Chat with articles Image generation for articles API keys to reduce cost Brand / persona voice custom prompts  Month on month iterative content improvement  Full stack content team that blends AI and human editors for agencies I’m still in full build mode with the team. I want to take it to a place where agencies and SMB owners can trust the AI + human content model enough to see this product as a no-brainer for their biz. I don’t believe in AI slop - there’s enough of that out there - I DO believe in using AI to do the grunt work, but to always have that human element a machine can’t quite mimic.  We have a lot more to get through, but I’m very excited about it. View of the done for you content workflow

Just started automating my daily tasks with AI—why did no one tell me about this sooner?

I used to spend so much time on small, repetitive tasks—organizing emails, setting reminders, even copying and pasting stuff between apps. It always felt normal until I tried automating a few things with AI. Now, my emails get sorted, my notes get summarized, and even my schedule adjusts itself based on what I need to do. It’s honestly insane how much time I’ve been saving without even realizing it. The craziest part? It doesn’t even take much effort to set up. A few AI tools here and there, some simple automations, and suddenly my workflow feels way smoother. I’m still experimenting, but it already feels like I’m getting more done with way less effort. If anyone’s interested, I wrote about some of the best AI automation tricks I’ve found so far. Check it out here: https://aichatbot4begginers.blogspot.com/2025/03/ai-powered-productivity-hacks-automate.html?m=1

[P] Building an Reinforcement Learning Agent to play The Legend of Zelda

A year go I started trying to use PPO to play the original Legend of Zelda, and I was able to train a model to beat the first boss after a few months of work. I wanted to share the project just for show and tell. I'd love to hear feedback and suggestions as this is just a hobby project. I don't do this for a living. The code for that lives in the original-design branch of my Triforce repo. I'm currently tinkering with new designs so the main branch is much less stable. Here's a video of the agent beating the first dungeon, which was trained with 5,000,000+ steps. At 38 seconds, you can see it learned that it's invulnerable at the screen edge, and it exploits that to avoid damage from a projectile. At 53 seconds it steps up to avoid damage from an unblockable projectile, even though it takes a -0.06 penalty for moving the wrong way (taking damage would be a larger penalty.) At 55 seconds it walks towards the rock projectile to block it. And so on, lots of little things the model does is easy to miss if you don't know the game inside and out. As a TLDR, here's an early version of my new (single) model. This doesn't make it quite as far, but if you watch closely it's combat is already far better, and is only trained on 320,000 steps (~6% of the steps the first model was trained on). This is pretty far along from my very first model. Original Design I got the original project working using stable-baselines's PPO and default neural network (Shared NatureCNN, I believe). SB was great to get started but ultimately stifling. In the new version of the project I've implemented PPO from scratch with torch with my own simple neural network similar to stable-baseline's default. I'm playing with all kinds of changes and designs now that I have more flexibility and control. Here is my rough original design: Overall Strategy My first pass through this project was basically "imagine playing Zelda with your older sibling telling you where to go and what to do". I give the model an objective vector which points to where I want it to go on the screen (as a bird flies, the agent still had to learn path finding to avoid damage and navigate around the map). This includes either point at the nearest enemy I want it to kill or a NSEW vector if it's supposed to move to the next room. Due a few limitations with stable-baselines (especially around action masking), I ended up training unique models for traversing the overworld vs the dungeon (since they have entirely different tilesets). I also trained a different model for when we have sword beams vs not. In the video above you can see what model is being used onscreen. In my current project I've removed this objective vector as it felt too much like cheating. Instead I give it a one-hot encoded objective (move north to the next room, pickup items, kill enemies, etc). So far it's working quite well without that crutch. The new project also does a much better job of combat even without multiple models to handle beams vs not. Observation/Action Space Image - The standard neural network had a really tough time being fed the entire screen. No amount of training seemed to help. I solved this by creating a viewport around Link that keeps him centered. This REALLY helped the model learn. I also had absolutely zero success with stacking frames to give Link a way to see enemy/projectile movement. The model simply never trained with stable-baselines when I implemented frame stacking and I never figured out why. I just added it to my current neural network and it seems to be working... Though my early experiments show that giving it 3 frames (skipping two in between, so frames curr, curr-3, curr-6) doesn't really give us that much better performance. It might if I took away some of the vectors. We'll see. Vectors - Since the model cannot see beyond its little viewport, I gave the model a vector to the closest item, enemy, and projectile onscreen. This made it so the model can shoot enemies across the room outside of its viewport. My new model gives it multiple enemies/items/projectiles and I plan to try to use an attention mechanism as part of the network to see if I can just feed it all of that data. Information - It also gets a couple of one-off datapoints like whether it currently has sword beams. The new model also gives it a "source" room (to help better understand dungeons where we have to backtrack), and a one-hot encoded objective. Action Space My original project just has a few actions, 4 for moving in the cardinal directions and 4 for attacking in each direction (I also added bombs but never spent any time training it). I had an idea to use masking to help speed up training. I.E. if link bumps into a wall, don't let him move in that direction again until he moves elsewhere, as the model would often spend an entire memory buffer running headlong straight into a wall before an update...better to do it once and get a huge negative penalty which is essentially the same result but faster. Unfortunately SB made it really annoying architecturally to pass that info down to the policy layer. I could have hacked it together, but eventually I just reimplemented PPO and my own neural network so I could properly mask actions in the new version. For example, when we start training a fresh model, it cannot attack when there aren't enemies on screen and I can disallow it from leaving certain areas. The new model actually understands splitting swinging the sword short range vs firing sword beams as two different actions, though I haven't yet had a chance to fully train with the split yet. Frameskip/Cooldowns - In the game I don't use a fixed frame skip for actions. Instead I use the internal ram state of game to know when Link is animation locked or not and only allow the agent to take actions when it's actually possible to give meaningful input to the game. This greatly sped up training. We also force movement to be between tiles on the game map. This means that when the agent decides to move it loses control for longer than a player would...a player can make more split second decisions. This made it easier to implement movement rewards though and might be something to clean up in the future. Other interesting details Pathfinding - To facilitate rewards, the original version of this project used A* to pathfind from link to what he should be doing. Here's a video of it in action. This information wasn't giving to the model directly but instead the agent would only be given the rewards if it exactly followed that path or the transposed version of it. It would also pathfind around enemies and not walk through them. This was a nightmare though. The corner cases were significant, and pushing Link towards enemies but not into them was really tricky. The new verison just uses a wavefront algorithm. I calculate a wave from the tiles we want to get to outwards, then make sure we are following the gradient. Also calculating the A* around enemies every frame (even with caching) was super slow. Wavefront was faster, especially because I give the new model no special rewards for walking around enemies...faster to compute and it has to learn from taking damage or not. Either way, the both the old and new models successfully learned how to pathfind around danger and obstacles, with or without the cheaty objective vector. Rewards - I programmed very dense rewards in both the old and new model. At basically every step, the model is getting rewarded or punished for something. I actually have some ideas I can't wait to try out to make the rewards more sparse. Or maybe we start with dense rewards for the first training, then fine-tune the model with sparser rewards. We'll see. Predicting the Future - Speaking of rewards. One interesting wrinkle is that the agent can do a lot of things that will eventually deal damage but not on that frame. For example, when Link sets a bomb it takes several seconds before it explodes, killing things. This can be a massive reward or penalty since he spent an extremely valuable resource, but may have done massive damage. PPO and other RL propagates rewards backwards, of course, but that spike in reward could land on a weird frame where we took damage or moved in the wrong direction. I probably could have just not solved that problem and let it shake out over time, but instead I used the fact that we are in an emulator to just see what the outcome of every decision is. When planting a bomb, shooting sword beams, etc, we let the game run forward until impact, then rewind time and reward the agent appropriately, continuing on from when we first paused. This greatly speeds up training, even if it's expensive to do this savestate, play forward, restore state. Neural Networks - When I first started this project (knowing very little about ML and RL), I thought most of my time would be tuning the shape of the neural network that we are using. In reality, the default provided by stable-baselines and my eventual reimplemnentation has been enough to make massive progress. Now that I have a solid codebase though, I really want to revisit this. I'd like to see if trying CoordConvs and similar networks might make the viewport unncessary. Less interesting details/thoughts Hyperparameters - Setting the entropy coefficinet way lower helped a TON in training stable models. My new PPO implementation is way less stable than stable-baselines (ha, imagine that), but still converges most of the time. Infinite Rewards - As with all reinforcement learning, if you give some way for the model to get infinite rewards, it will do just that and nothing else. I spent days, or maybe weeks tweaking reward functions to just get it to train and not find a spot on the wall it could hump for infinite rewards. Even just neutral rewards, like +0.5 moving forward and -0.5 for moving backwards, would often result in a model that just stepped left, then right infinitely. There has to be a real reward or punishment (non-neutral) for forward progress. Debugging Rewards - In fact, building a rewards debugger was the only way I made progress in this project. If you are tackling something this big, do that very early. Stable-Retro is pretty great - Couldn't be happier with the clean design for implementing emulation for AI. Torch is Awesome - My early versions heavily used numpy and relied on stable-baselines, with its multiproc parallelization support. It worked great. Moving the project over to torch was night and day though. It gave me so much more flexibility, instant multithreading for matrix operations. I have a pretty beefy computer and I'm almost at the same steps per second as 20 proc stable-retro/numpy. Future Ideas This has already gone on too long. I have some ideas for future projects, but maybe I'll just make them another post when I actually do them. Special Thanks A special thanks to Brad Flaugher for help with the early version of this, Fiskbit from the Zelda1 speedrunning community for help pulling apart the raw assembly to build this thing, and MatPoliquin for maintaining Stable-Retro. Happy to answer any questions, really I just love nerding out about this stuff.

0-20+ faceless AI automated YouTube channels in 1 year - my process and tools

First of all before diving deep into this process (scroll a bit below) I have to say something that everyone keeps asking me, is it profitable? Yes. It's by far my most profitable venture outside of my regular 9-5... But it took a lot of work, delegation and building processes to get here. So the one thing I would love to get out of this post - if you have any insights, feedback or tools I might be missing out post them below and let's help each other out. Now, how you can get started with (AI) YouTube automation: Pick a topic that is BOTH: a) in demand b) interesting to you & you have knowledge about Do everything yourself at first - delegate later No one cares about the videos as much as you do, so make sure to nail the ideation, scripts, editing, format and packaging yourself first. Now that we got that out of the way: Use this workflow: VidIQ - outliers sections is pure gold, I use it all the time to find trending video packaging, topics, etc. ChatGPT or Claude - high level video ideas at scale and your assistant (I use projects inside ChatGPT and its really good at managing and prioritizing). If you are using it for scripts please for the love of god, make final edits yourself by hand. Add character, personal insights, ideas, etc. Katalist AI - all in one video generator tool I use to quickly go from video idea to script, storyboard, AI voiceover and then final visuals. It's surprisingly good and to make a decent video it only takes about 1-2 hours in TOTAL. Once you understand how it works and have a process, delegate to tech savvy VAs / content creators for $5-$15/hour and you have final, good quality videos for less than $30. Pikzels / Krea AI - your AI thumbnail generator, I dont remember the last time we used Photoshop outside of quick text or image edits. Its basically AI image manipulation at scale and it costs 10-30x less than a human thumbnail designer and the thumbnails are really good. VidIQ+TubeBuddy - titles & optimization, but you have to know that most of the views come usually from recommended, so dont over obsess and add 392x keywords in your title and description. Its all about the packaging. Now whats left is track performance & iterate - it's practically impossible to nail it the first few times, but each video you make look at the data (not just in YT studio) and UNDERSTAND why it did not perform as well as you thought it would. Regarding monetization, adsense sucks - sell digital products. If I was relying on adsense alone I would never ever be profitable, but selling mini digital products and mentioning CTAs in the actual video not just in the description makes this super profitable and scaleable, especially since video production is so cheap. Final thoughts: (AI) YouTube automation absolutely works, but it’s not an overnight success or a total hands-off cashcow machine. It’s a real business and you need systems, consistent effort, iteration, failing and learning along the way. If you’ve got any tips, hidden gems or tools I might be missing, drop them below & let’s help each other out.

[D] Why I'm Lukewarm on Graph Neural Networks

TL;DR: GNNs can provide wins over simpler embedding methods, but we're at a point where other research directions matter more I also posted it on my blog here, has footnotes, a nicer layout with inlined images, etc. I'm only lukewarm on Graph Neural Networks (GNNs). There, I said it. It might sound crazy GNNs are one of the hottest fields in machine learning right now. [There][1] were at least [four][2] [review][3] [papers][4] just in the last few months. I think some progress can come of this research, but we're also focusing on some incorrect places. But first, let's take a step back and go over the basics. Models are about compression We say graphs are a "non-euclidean" data type, but that's not really true. A regular graph is just another way to think about a particular flavor of square matrix called the [adjacency matrix][5], like this. It's weird, we look at run-of-the-mill matrix full of real numbers and decide to call it "non-euclidean". This is for practical reasons. Most graphs are fairly sparse, so the matrix is full of zeros. At this point, where the non-zero numbers are matters most, which makes the problem closer to (computationally hard) discrete math rather than (easy) continuous, gradient-friendly math. If you had the full matrix, life would be easy If we step out of the pesky realm of physics for a minute, and assume carrying the full adjacency matrix around isn't a problem, we solve a bunch of problems. First, network node embeddings aren't a thing anymore. A node is a just row in the matrix, so it's already a vector of numbers. Second, all network prediction problems are solved. A powerful enough and well-tuned model will simply extract all information between the network and whichever target variable we're attaching to nodes. NLP is also just fancy matrix compression Let's take a tangent away from graphs to NLP. Most NLP we do can be [thought of in terms of graphs][6] as we'll see, so it's not a big digression. First, note that Ye Olde word embedding models like [Word2Vec][7] and [GloVe][8] are [just matrix factorization][9]. The GloVe algorithm works on a variation of the old [bag of words][10] matrix. It goes through the sentences and creates a (implicit) [co-occurence][11] graph where nodes are words and the edges are weighed by how often the words appear together in a sentence. Glove then does matrix factorization on the matrix representation of that co-occurence graph, Word2Vec is mathematically equivalent. You can read more on this in my [post on embeddings][12] and the one (with code) on [word embeddings][13]. Even language models are also just matrix compression Language models are all the rage. They dominate most of the [state of the art][14] in NLP. Let's take BERT as our main example. BERT predicts a word given the context of the rest of the sentence. This grows the matrix we're factoring from flat co-occurences on pairs of words to co-occurences conditional on the sentence's context, like this We're growing the "ideal matrix" we're factoring combinatorially. As noted by [Hanh & Futrell][15]: [...] human language—and language modelling—has infinite statistical complexity but that it can be approximated well at lower levels. This observation has two implications: 1) We can obtain good results with comparatively small models; and 2) there is a lot of potential for scaling up our models. Language models tackle such a large problem space that they probably approximate a compression of the entire language in the [Kolmogorov Complexity][16] sense. It's also possible that huge language models just [memorize a lot of it][17] rather than compress the information, for what it's worth. Can we upsample any graph like language models do? We're already doing it. Let's call a first-order embedding of a graph a method that works by directly factoring the graph's adjacency matrix or [Laplacian matrix][18]. If you embed a graph using [Laplacian Eigenmaps][19] or by taking the [principal components][20] of the Laplacian, that's first order. Similarly, GloVe is a first-order method on the graph of word co-occurences. One of my favorites first order methods for graphs is [ProNE][21], which works as well as most methods while being two orders of magnitude faster. A higher-order method embeds the original matrix plus connections of neighbours-of-neighbours (2nd degree) and deeper k-step connections. [GraRep][22], shows you can always generate higher-order representations from first order methods by augmenting the graph matrix. Higher order method are the "upsampling" we do on graphs. GNNs that sample on large neighborhoods and random-walk based methods like node2vec are doing higher-order embeddings. Where are the performance gain? Most GNN papers in the last 5 years present empirical numbers that are useless for practitioners to decide on what to use. As noted in the [OpenGraphsBenchmark][4] (OGB) paper, GNN papers do their empirical section on a handful of tiny graphs (Cora, CiteSeer, PubMed) with 2000-20,000 nodes. These datasets can't seriously differentiate between methods. Recent efforts are directly fixing this, but the reasons why researchers focused on tiny, useless datasets for so long are worth discussing. Performance matters by task One fact that surprises a lot of people is that even though language models have the best performance in a lot of NLP tasks, if all you're doing is cram sentence embeddings into a downstream model, there [isn't much gained][23] from language models embeddings over simple methods like summing the individual Word2Vec word embeddings (This makes sense, because the full context of the sentence is captured in the sentence co-occurence matrix that is generating the Word2Vec embeddings). Similarly, [I find][24] that for many graphs simple first-order methods perform just as well on graph clustering and node label prediction tasks than higher-order embedding methods. In fact higher-order methods are massively computationally wasteful for these usecases. Recommended first order embedding methods are ProNE and my [GGVec with order=1][25]. Higher order methods normally perform better on the link prediction tasks. I'm not the only one to find this. In the BioNEV paper, they find: "A large GraRep order value for link prediction tasks (e.g. 3, 4);a small value for node classification tasks (e.g.1, 2)" (p.9). Interestingly, the gap in link prediction performance is inexistant for artificially created graphs. This suggests higher order methods do learn some of the structure intrinsic to [real world graphs][26]. For visualization, first order methods are better. Visualizations of higher order methods tend to have artifacts of their sampling. For instance, Node2Vec visualizations tend to have elongated/filament-like structures which come from the embeddings coming from long single strand random walks. See the following visualizations by [Owen Cornec][27] created by first embedding the graph to 32-300 dimensions using a node embedding algorithm, then mapping this to 2d or 3d with the excellent UMAP algorithm, like this Lastly, sometimes simple methods soundly beat higher order methods (there's an instance of it in the OGB paper). The problem here is that we don't know when any method is better than another and we definitely don't know the reason. There's definitely a reason different graph types respond better/worse to being represented by various methods. This is currently an open question. A big part of why is that the research space is inundated under useless new algorithms because... Academic incentives work against progress Here's the cynic's view of how machine learning papers are made: Take an existing algorithm Add some new layer/hyperparameter, make a cute mathematical story for why it matters Gridsearch your hyperparameters until you beat baselines from the original paper you aped Absolutely don't gridsearch stuff you're comparing against in your results section Make a cute ACRONYM for your new method, put impossible to use python 2 code on github (Or no code at all!) and bask in the citations I'm [not][28] the [only one][29] with these views on the state reproducible research. At least it's gotten slightly better in the last 2 years. Sidebar: I hate Node2Vec A side project of mine is a [node embedding library][25] and the most popular method in it is by far Node2Vec. Don't use Node2Vec. [Node2Vec][30] with p=1; q=1 is the [Deepwalk][31] algorithm. Deepwalk is an actual innovation. The Node2Vec authors closely followed the steps 1-5 including bonus points on step 5 by getting word2vec name recognition. This is not academic fraud -- the hyperparameters [do help a tiny bit][32] if you gridsearch really hard. But it's the presentable-to-your-parents sister of where you make the ML community worse off to progress your academic career. And certainly Node2Vec doesn't deserve 7500 citations. Progress is all about practical issues We've known how to train neural networks for well over 40 years. Yet they only exploded in popularity with [AlexNet][33] in 2012. This is because implementations and hardware came to a point where deep learning was practical. Similarly, we've known about factoring word co-occurence matrices into Word embeddings for at least 20 years. But word embeddings only exploded in 2013 with Word2Vec. The breakthrough here was that the minibatch-based methods let you train a Wikipedia-scale embedding model on commodity hardware. It's hard for methods in a field to make progress if training on a small amount of data takes days or weeks. You're disincentivized to explore new methods. If you want progress, your stuff has to run in reasonable time on commodity hardware. Even Google's original search algorithm [initially ran on commodity hardware][34]. Efficiency is paramount to progress The reason deep learning research took off the way it did is because of improvements in [efficiency][35] as well as much better libraries and hardware support. Academic code is terrible Any amount of time you spend gridsearching Node2Vec on p and q is all put to better use gridsearching Deepwalk itself (on number of walks, length of walks, or word2vec hyperparameters). The problem is that people don't gridsearch over deepwalk because implementations are all terrible. I wrote the [Nodevectors library][36] to have a fast deepwalk implementation because it took 32 hours to embed a graph with a measly 150,000 nodes using the reference Node2Vec implementation (the same takes 3min with Nodevectors). It's no wonder people don't gridsearch on Deepwalk a gridsearch would take weeks with the terrible reference implementations. To give an example, in the original paper of [GraphSAGE][37] they their algorithm to DeepWalk with walk lengths of 5, which is horrid if you've ever hyperparameter tuned a deepwalk algorithm. From their paper: We did observe DeepWalk’s performance could improve with further training, and in some cases it could become competitive with the unsupervised GraphSAGE approaches (but not the supervised approaches) if we let it run for >1000× longer than the other approaches (in terms of wall clock time for prediction on the test set) I don't even think the GraphSAGE authors had bad intent -- deepwalk implementations are simply so awful that they're turned away from using it properly. It's like trying to do deep learning with 2002 deep learning libraries and hardware. Your architectures don't really matter One of the more important papers this year was [OpenAI's "Scaling laws"][38] paper, where the raw number of parameters in your model is the most predictive feature of overall performance. This was noted even in the original BERT paper and drives 2020's increase in absolutely massive language models. This is really just [Sutton' Bitter Lesson][39] in action: General methods that leverage computation are ultimately the most effective, and by a large margin Transformers might be [replacing convolution][40], too. As [Yannic Kilcher said][41], transformers are ruining everything. [They work on graphs][6], in fact it's one of the [recent approaches][42], and seems to be one of the more succesful [when benchmarked][1] Researchers seem to be putting so much effort into architecture, but it doesn't matter much in the end because you can approximate anything by stacking more layers. Efficiency wins are great -- but neural net architectures are just one way to achieve that, and by tremendously over-researching this area we're leaving a lot of huge gains elsewhere on the table. Current Graph Data Structure Implementations suck NetworkX is a bad library. I mean, it's good if you're working on tiny graphs for babies, but for anything serious it chokes and forces you to rewrite everything in... what library, really? At this point most people working on large graphs end up hand-rolling some data structure. This is tough because your computer's memory is a 1-dimensional array of 1's and 0's and a graph has no obvious 1-d mapping. This is even harder when we take updating the graph (adding/removing some nodes/edges) into account. Here's a few options: Disconnected networks of pointers NetworkX is the best example. Here, every node is an object with a list of pointers to other nodes (the node's edges). This layout is like a linked list. Linked lists are the [root of all performance evil][43]. Linked lists go completely against how modern computers are designed. Fetching things from memory is slow, and operating on memory is fast (by two orders of magnitude). Whenever you do anything in this layout, you make a roundtrip to RAM. It's slow by design, you can write this in Ruby or C or assembly and it'll be slow regardless, because memory fetches are slow in hardware. The main advantage of this layout is that adding a new node is O(1). So if you're maintaining a massive graph where adding and removing nodes happens as often as reading from the graph, it makes sense. Another advantage of this layout is that it "scales". Because everything is decoupled from each other you can put this data structure on a cluster. However, you're really creating a complex solution for a problem you created for yourself. Sparse Adjacency Matrix This layout great for read-only graphs. I use it as the backend in my [nodevectors][25] library, and many other library writers use the [Scipy CSR Matrix][44], you can see graph algorithms implemented on it [here][45]. The most popular layout for this use is the [CSR Format][46] where you have 3 arrays holding the graph. One for edge destinations, one for edge weights and an "index pointer" which says which edges come from which node. Because the CSR layout is simply 3 arrays, it scales on a single computer: a CSR matrix can be laid out on a disk instead of in-memory. You simply [memory map][47] the 3 arrays and use them on-disk from there. With modern NVMe drives random seeks aren't slow anymore, much faster than distributed network calls like you do when scaling the linked list-based graph. I haven't seen anyone actually implement this yet, but it's in the roadmap for my implementation at least. The problem with this representation is that adding a node or edge means rebuilding the whole data structure. Edgelist representations This representation is three arrays: one for the edge sources, one for the edge destinations, and one for edge weights. [DGL][48] uses this representation internally. This is a simple and compact layout which can be good for analysis. The problem compared to CSR Graphs is some seek operations are slower. Say you want all the edges for node #4243. You can't jump there without maintaining an index pointer array. So either you maintain sorted order and binary search your way there (O(log2n)) or unsorted order and linear search (O(n)). This data structure can also work on memory mapped disk array, and node append is fast on unsorted versions (it's slow in the sorted version). Global methods are a dead end Methods that work on the entire graph at once can't leverage computation, because they run out of RAM at a certain scale. So any method that want a chance of being the new standard need to be able to update piecemeal on parts of the graph. Sampling-based methods Sampling Efficiency will matter more in the future Edgewise local methods. The only algorithms I know of that do this are GloVe and GGVec, which they pass through an edge list and update embedding weights on each step. The problem with this approach is that it's hard to use them for higher-order methods. The advantage is that they easily scale even on one computer. Also, incrementally adding a new node is as simple as taking the existing embeddings, adding a new one, and doing another epoch over the data Random Walk sampling. This is used by deepwalk and its descendants, usually for node embeddings rather than GNN methods. This can be computationally expensive and make it hard to add new nodes. But this does scale, for instance [Instagram][49] use it to feed their recommendation system models Neighbourhood sampling. This is currently the most common one in GNNs, and can be low or higher order depending on the neighborhood size. It also scales well, though implementing efficiently can be challenging. It's currently used by [Pinterest][50]'s recommendation algorithms. Conclusion Here are a few interesting questions: What is the relation between graph types and methods? Consolidated benchmarking like OGB We're throwing random models at random benchmarks without understanding why or when they do better More fundamental research. Heree's one I'm curious about: can other representation types like [Poincarre Embeddings][51] effectively encode directed relationships? On the other hand, we should stop focusing on adding spicy new layers to test on the same tiny datasets. No one cares. [1]: https://arxiv.org/pdf/2003.00982.pdf [2]: https://arxiv.org/pdf/2002.11867.pdf [3]: https://arxiv.org/pdf/1812.08434.pdf [4]: https://arxiv.org/pdf/2005.00687.pdf [5]: https://en.wikipedia.org/wiki/Adjacency_matrix [6]: https://thegradient.pub/transformers-are-graph-neural-networks/ [7]: https://en.wikipedia.org/wiki/Word2vec [8]: https://nlp.stanford.edu/pubs/glove.pdf [9]: https://papers.nips.cc/paper/2014/file/feab05aa91085b7a8012516bc3533958-Paper.pdf [10]: https://en.wikipedia.org/wiki/Bag-of-words_model [11]: https://en.wikipedia.org/wiki/Co-occurrence [12]: https://www.singlelunch.com/2020/02/16/embeddings-from-the-ground-up/ [13]: https://www.singlelunch.com/2019/01/27/word-embeddings-from-the-ground-up/ [14]: https://nlpprogress.com/ [15]: http://socsci.uci.edu/~rfutrell/papers/hahn2019estimating.pdf [16]: https://en.wikipedia.org/wiki/Kolmogorov_complexity [17]: https://bair.berkeley.edu/blog/2020/12/20/lmmem/ [18]: https://en.wikipedia.org/wiki/Laplacian_matrix [19]: http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=1F03130B02DC485C78BF364266B6F0CA?doi=10.1.1.19.8100&rep=rep1&type=pdf [20]: https://en.wikipedia.org/wiki/Principalcomponentanalysis [21]: https://www.ijcai.org/Proceedings/2019/0594.pdf [22]: https://dl.acm.org/doi/10.1145/2806416.2806512 [23]: https://openreview.net/pdf?id=SyK00v5xx [24]: https://github.com/VHRanger/nodevectors/blob/master/examples/link%20prediction.ipynb [25]: https://github.com/VHRanger/nodevectors [26]: https://arxiv.org/pdf/1310.2636.pdf [27]: http://byowen.com/ [28]: https://arxiv.org/pdf/1807.03341.pdf [29]: https://www.youtube.com/watch?v=Kee4ch3miVA [30]: https://cs.stanford.edu/~jure/pubs/node2vec-kdd16.pdf [31]: https://arxiv.org/pdf/1403.6652.pdf [32]: https://arxiv.org/pdf/1911.11726.pdf [33]: https://en.wikipedia.org/wiki/AlexNet [34]: https://en.wikipedia.org/wiki/Googledatacenters#Original_hardware [35]: https://openai.com/blog/ai-and-efficiency/ [36]: https://www.singlelunch.com/2019/08/01/700x-faster-node2vec-models-fastest-random-walks-on-a-graph/ [37]: https://arxiv.org/pdf/1706.02216.pdf [38]: https://arxiv.org/pdf/2001.08361.pdf [39]: http://incompleteideas.net/IncIdeas/BitterLesson.html [40]: https://arxiv.org/abs/2010.11929 [41]: https://www.youtube.com/watch?v=TrdevFK_am4 [42]: https://arxiv.org/pdf/1710.10903.pdf [43]: https://www.youtube.com/watch?v=fHNmRkzxHWs [44]: https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.csr_matrix.html [45]: https://docs.scipy.org/doc/scipy/reference/sparse.csgraph.html [46]: https://en.wikipedia.org/wiki/Sparsematrix#Compressedsparserow(CSR,CRSorYaleformat) [47]: https://en.wikipedia.org/wiki/Mmap [48]: https://github.com/dmlc/dgl [49]: https://ai.facebook.com/blog/powered-by-ai-instagrams-explore-recommender-system/ [50]: https://medium.com/pinterest-engineering/pinsage-a-new-graph-convolutional-neural-network-for-web-scale-recommender-systems-88795a107f48 [51]: https://arxiv.org/pdf/1705.08039.pdf

[P] How I found & fixed 4 bugs in Microsoft's Phi-4 model

Hey r/MachineLearning! Last week, Microsoft released Phi-4, a 14B open-source model that rivals OpenAI's GPT-4-o-mini. I managed to find & fix 4 bugs impacting its output quality. You might remember me previously from fixing 8 bugs in Google's Gemma model! :) I'm going to walk you through how I found & fixed the bugs. Phi-4's benchmarks were amazing, however many users reported weird or just wrong outputs. Since I maintain the open-source project called 'Unsloth' (fine-tuning LLMs 2x faster with 70% less VRAM) with my brother, I firstly tested Phi-4 for inference and found many errors. Our GitHub repo: https://github.com/unslothai/unsloth This time, the model had no implementation issues (unlike Gemma 2) but did have problems in the model card. For my first inference run, I randomly found an extra token which is obviously incorrect (2 eos tokens is never a good idea). Also during more runs, I found there was an extra assistant prompt which is once again incorrect. And, lastly, from past experience with Unsloth's bug fixes, I already knew fine-tuning was wrong when I read the code. These bugs caused Phi-4 to have some drop in accuracy and also broke fine-tuning runs. Our fixes are now under review by Microsoft to be officially added to Hugging Face. We uploaded the fixed versions to https://huggingface.co/unsloth/phi-4-GGUF Here’s a breakdown of the bugs and their fixes: Tokenizer bug fixes The Phi-4 tokenizer interestingly uses as the BOS (beginning of sentence), EOS (end of sentence) and PAD (padding) tokens. The main issue is the EOS token is wrong - it should be . Otherwise, you will get in generations. Fine-tuning bug fixes The padding token should be a designated pad token like in Llama () or we can use an untrained token - for example we use , fixing infinite generations and outputs. Chat template issues The Phi-4 tokenizer always adds an assistant prompt - it should only do this if prompted by add\generation\prompt. Most LLM serving libraries expect non auto assistant additions, and this might cause issues during serving. We dive deeper into the bugs in our blog: https://unsloth.ai/blog/phi4 Do our Fixes Work? Yes! Our fixed Phi-4 uploads show clear performance gains, with even better scores than Microsoft's original uploads on the Open LLM Leaderboard. https://preview.redd.it/d8hew26e06ce1.png?width=2366&format=png&auto=webp&s=173c23feacc625566271470839fe7a5e25eb860e Some redditors even tested our fixes to show greatly improved results in: Example 1: Multiple-choice tasks https://preview.redd.it/qx50pkq706ce1.png?width=1579&format=png&auto=webp&s=437da2cabdbf98ef5a8b8cbdc5592907a20e2316 Example 2: ASCII art generation https://preview.redd.it/sw1o3a3yt4de1.png?width=2326&format=png&auto=webp&s=fc6bfc45d14134d45f332ba58bbd1de049f5776b We also made a Colab notebook fine-tune Phi-4 completely for free using Google's free Tesla T4 (16GB) GPUs: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi\4-Conversational.ipynb Thank you for reading this long post and hope you all found this insightful! If you have any questions, please feel free to ask! :) How I found the bugs: I first downloaded the original Phi-4 from https://huggingface.co/microsoft/phi-4, and tested inference out. Weirdly I found assistant to be appended at the even with addgenerationprompt = False in Hugging Face, so I theorized there was a chat template problem. Adding assistant prompts by default can break serving libraries. And yes, https://huggingface.co/microsoft/phi-4/blob/f957856cd926f9d681b14153374d755dd97e45ed/tokenizer\config.json#L774 had by default added the assistant prompt - I first fixed this! I then found ` to be used for the BOS, EOS and PAD tokens, which is a common issue amongst models - I ignored the BOS, since Phi-4 did not have one anyways, but changed the PAD token to `. You can select any of the tokens since they're empty and not trained. This counteracts issues of infinite generations during finetuning. For Llama-fication, I used torch.allclose to confirm all tensors are in fact equivalent. I also used some fake random data to check all activations are also mostly similar bitwise. I also uploaded the model to the HF Open LLM Leaderboard to confirm if the original Phi-4 arch and the new Llama-fied models are equivalent. Finally I verified all finetuning runs with Unsloth in a Colab Notebook to confirm all runs were correct.

[Discussion] When ML and Data Science are the death of a good company: A cautionary tale.

TD;LR: At Company A, Team X does advanced analytics using on-prem ERP tools and older programming languages. Their tools work very well and are designed based on very deep business and domain expertise. Team Y is a new and ambitious Data Science team that thinks they can replace Team X's tools with a bunch of R scripts and a custom built ML platform. Their models are simplistic, but more "fashionable" compared to the econometric models used by Team X, and team Y benefits from the ML/DS moniker so leadership is allowing Team Y to start a large scale overhaul of the analytics platform in question. Team Y doesn't have the experience for such a larger scale transformation, and is refusing to collaborate with team X. This project is very likely going to fail, and cause serious harm to the company as a whole financially and from a people perspective. I argue that this is not just because of bad leadership, but also because of various trends and mindsets in the DS community at large. Update (Jump to below the line for the original story): Several people in the comments are pointing out that this just a management failure, not something due to ML/DS, and that you can replace DS with any buzz tech and the story will still be relevant. My response: Of course, any failure at an organization level is ultimately a management failure one way or the other. Moreover, it is also the case that ML/DS when done correctly, will always improve a company's bottom line. There is no scenario where the proper ML solution, delivered at a reasonable cost and in a timely fashion, will somehow hurt the company's bottom line. My point is that in this case management is failing because of certain trends and practices that are specific to the ML/DS community, namely: The idea that DS teams should operate independently of tech and business orgs -- too much autonomy for DS teams The disregard for domain knowledge that seems prevalent nowadays thanks to the ML hype, that DS can be generalists and someone with good enough ML chops can solve any business problem. That wasn't the case when I first left academia for the industry in 2009 (back then nobody would even bother with a phone screen if you didn't have the right domain knowledge). Over reliance on resources who check all the ML hype related boxes (knows Python, R, Tensorflow, Shiny, etc..., has the right Coursera certifications, has blogged on the topic, etc...), but are lacking in depth of experience. DS interviews nowadays all seem to be: Can you tell me what a p-value is? What is elastic net regression? Show me how to fit a model in sklearn? How do you impute NAs in an R dataframe? Any smart person can look those up on Stackoverflow or Cross-Validated,.....Instead teams should be asking stuff like: why does portfolio optimization use QP not LP? How does a forecast influence a customer service level? When should a recommendation engine be content based and when should it use collaborative filtering? etc... (This is a true story, happening to the company I currently work for. Names, domains, algorithms, and roles have been shuffled around to protect my anonymity)  Company A has been around for several decades. It is not the biggest name in its domain, but it is a well respected one. Risk analysis and portfolio optimization have been a core of Company A's business since the 90s. They have a large team of 30 or so analysts who perform those tasks on a daily basis. These analysts use ERP solutions implemented for them by one the big ERP companies (SAP, Teradata, Oracle, JD Edwards,...) or one of the major tech consulting companies (Deloitte, Accenture, PWC, Capgemini, etc...) in collaboration with their own in house engineering team. The tools used are embarrassingly old school: Classic RDBMS running on on-prem servers or maybe even on mainframes, code written in COBOL, Fortran, weird proprietary stuff like ABAP or SPSS.....you get the picture. But the models and analytic functions were pretty sophisticated, and surprisingly cutting edge compared to the published academic literature. Most of all, they fit well with the company's enterprise ecosystem, and were honed based on years of deep domain knowledge.  They have a tech team of several engineers (poached from the aforementioned software and consulting companies) and product managers (who came from the experienced pools of analysts and managers who use the software, or poached from business rivals) maintaining and running this software. Their technology might be old school, but collectively, they know the domain and the company's overall architecture very, very well. They've guided the company through several large scale upgrades and migrations and they have a track record of delivering on time, without too much overhead. The few times they've stumbled, they knew how to pick themselves up very quickly. In fact within their industry niche, they have a reputation for their expertise, and have very good relations with the various vendors they've had to deal with. They were the launching pad of several successful ERP consulting careers.  Interestingly, despite dealing on a daily basis with statistical modeling and optimization algorithms, none of the analysts, engineers, or product managers involved describe themselves as data scientists or machine learning experts. It is mostly a cultural thing: Their expertise predates the Data Science/ML hype that started circa 2010, and they got most of their chops using proprietary enterprise tools instead of the open source tools popular nowadays. A few of them have formal statistical training, but most of them came from engineering or domain backgrounds and learned stats on the fly while doing their job. Call this team "Team X".  Sometime around the mid 2010s, Company A started having some serious anxiety issues: Although still doing very well for a company its size, overall economic and demographic trends were shrinking its customer base, and a couple of so called disruptors came up with a new app and business model that started seriously eating into their revenue. A suitable reaction to appease shareholders and Wall Street was necessary. The company already had a decent website and a pretty snazzy app, what more could be done? Leadership decided that it was high time that AI and ML become a core part of the company's business. An ambitious Manager, with no science or engineering background, but who had very briefly toyed with a recommender system a couple of years back, was chosen to build a data science team, call it team "Y" (he had a bachelor's in history from the local state college and worked for several years in the company's marketing org). Team "Y" consists mostly of internal hires who decided they wanted to be data scientists and completed a Coursera certification or a Galvanize boot camp, before being brought on to the team, along with a few of fresh Ph.D or M.Sc holders who didn't like academia and wanted to try their hand at an industry role. All of them were very bright people, they could write great Medium blog posts and give inspiring TED talks, but collectively they had very little real world industry experience. As is the fashion nowadays, this group was made part of a data science org that reported directly to the CEO and Board, bypassing the CIO and any tech or business VPs, since Company A wanted to claim the monikers "data driven" and "AI powered" in their upcoming shareholder meetings. In 3 or 4 years of existence, team Y produced a few Python and R scripts. Their architectural experience  consisted almost entirely in connecting Flask to S3 buckets or Redshift tables, with a couple of the more resourceful ones learning how to plug their models into Tableau or how to spin up a Kuberneties pod.  But they needn't worry: The aforementioned manager, who was now a director (and was also doing an online Masters to make up for his qualifications gap and bolster his chances of becoming VP soon - at least he now understands what L1 regularization is), was a master at playing corporate politics and self-promotion. No matter how few actionable insights team Y produced or how little code they deployed to production, he always had their back and made sure they had ample funding. In fact he now had grandiose plans for setting up an all-purpose machine learning platform that can be used to solve all of the company's data problems.  A couple of sharp minded members of team Y, upon googling their industry name along with the word "data science", realized that risk analysis was a prime candidate for being solved with Bayesian models, and there was already a nifty R package for doing just that, whose tutorial they went through on R-Bloggers.com. One of them had even submitted a Bayesian classifier Kernel for a competition on Kaggle (he was 203rd on the leaderboard), and was eager to put his new-found expertise to use on a real world problem. They pitched the idea to their director, who saw a perfect use case for his upcoming ML platform. They started work on it immediately, without bothering to check whether anybody at Company A was already doing risk analysis. Since their org was independent, they didn't really need to check with anybody else before they got funding for their initiative. Although it was basically a Naive Bayes classifier, the term ML was added to the project tile, to impress the board.  As they progressed with their work however, tensions started to build. They had asked the data warehousing and CA analytics teams to build pipelines for them, and word eventually got out to team X about their project. Team X was initially thrilled: They offered to collaborate whole heartedly, and would have loved to add an ML based feather to their already impressive cap. The product owners and analysts were totally onboard as well: They saw a chance to get in on the whole Data Science hype that they kept hearing about. But through some weird mix of arrogance and insecurity, team Y refused to collaborate with them or share any of their long term goals with them, even as they went to other parts of the company giving brown bag presentations and tutorials on the new model they created.  Team X got resentful: from what they saw of team Y's model, their approach was hopelessly naive and had little chances of scaling or being sustainable in production, and they knew exactly how to help with that. Deploying the model to production would have taken them a few days, given how comfortable they were with DevOps and continuous delivery (team Y had taken several months to figure out how to deploy a simple R script to production). And despite how old school their own tech was, team X were crafty enough to be able to plug it in to their existing architecture. Moreover, the output of the model was such that it didn't take into account how the business will consume it or how it was going to be fed to downstream systems, and the product owners could have gone a long way in making the model more amenable to adoption by the business stakeholders. But team Y wouldn't listen, and their leads brushed off any attempts at communication, let alone collaboration. The vibe that team Y was giving off was "We are the cutting edge ML team, you guys are the legacy server grunts. We don't need your opinion.", and they seemed to have a complete disregard for domain knowledge, or worse, they thought that all that domain knowledge consisted of was being able to grasp the definitions of a few business metrics.  Team X got frustrated and tried to express their concerns to leadership. But despite owning a vital link in Company A's business process, they were only \~50 people in a large 1000 strong technology and operations org, and they were several layers removed from the C-suite, so it was impossible for them to get their voices heard.  Meanwhile, the unstoppable director was doing what he did best: Playing corporate politics. Despite how little his team had actually delivered, he had convinced the board that all analysis and optimization tasks should now be migrated to his yet to be delivered ML platform. Since most leaders now knew that there was overlap between team Y and team X's objectives, his pitch was no longer that team Y was going to create a new insight, but that they were going to replace (or modernize) the legacy statistics based on-prem tools with more accurate cloud based ML tools. Never mind that there was no support in the academic literature for the idea that Naive Bayes works better than the Econometric approaches used by team X, let alone the additional wacky idea that Bayesian Optimization would definitely outperform the QP solvers that were running in production.  Unbeknownst to team X, the original Bayesian risk analysis project has now grown into a multimillion dollar major overhaul initiative, which included the eventual replacement of all of the tools and functions supported by team X along with the necessary migration to the cloud. The CIO and a couple of business VPs are on now board, and tech leadership is treating it as a done deal. An outside vendor, a startup who nobody had heard of, was contracted to help build the platform, since team Y has no engineering skills. The choice was deliberate, as calling on any of the established consulting or software companies would have eventually led leadership to the conclusion that team X was better suited for a transformation on this scale than team Y.  Team Y has no experience with any major ERP deployments, and no domain knowledge, yet they are being tasked with fundamentally changing the business process that is at the core of Company A's business. Their models actually perform worse than those deployed by team X, and their architecture is hopelessly simplistic, compared to what is necessary for running such a solution in production.  Ironically, using Bayesian thinking and based on all the evidence, the likelihood that team Y succeeds is close to 0%. At best, the project is going to end up being a write off of 50 million dollars or more. Once the !@#$!@hits the fan, a couple of executive heads are going to role, and dozens of people will get laid off. At worst, given how vital risk analysis and portfolio optimization is to Company A's revenue stream, the failure will eventually sink the whole company. It probably won't go bankrupt, but it will lose a significant portion of its business and work force. Failed ERP implementations can and do sink large companies: Just see what happened to National Grid US, SuperValu or Target Canada.  One might argue that this is more about corporate disfunction and bad leadership than about data science and AI. But I disagree. I think the core driver of this debacle is indeed the blind faith in Data Scientists, ML models and the promise of AI, and the overall culture of hype and self promotion that is very common among the ML crowd.  We haven't seen the end of this story: I sincerely hope that this ends well for the sake of my colleagues and all involved. Company A is a good company, and both its customers and its employees deserver better. But the chances of that happening are negligible given all the information available, and this failure will hit my company hard.

[D] The Rants of an experienced engineer who glimpsed into AI Academia (Briefly)

Background I recently graduated with a master's degree and was fortunate/unfortunate to glimpse the whole "Academic" side of ML. I took a thesis track in my degree because as an immigrant it's harder to get into a good research lab without having authorship in a couple of good papers (Or so I delude myself ). I worked as a Full-stack SWE for a startup for 4+ years before coming to the US for a master’s degree focused on ML and AI. I did everything in those years. From project management to building fully polished S/W products to DevOps to even dabbled in ML. I did my Batchelor’s degree from a university whose name is not even worth mentioning. The university for my master’s degree is in the top 20 in the AI space. I didn't know much about ML and the curiosity drove me to university. Come to uni and I focused on learning ML and AI for one 1-1.5 years after which I found advisors for a thesis topic. This is when the fun starts. I had the most amazing advisors but the entire peer review system and the way we assess ML/Science is what ticked me off. This is where the rant begins. Rant 1:Acadmia follows a Gated Institutional Narrative Let's say you are a Ph.D. at the world's top AI institution working under the best prof. You have a way higher likelihood of you getting a good Postdoc at a huge research lab vs someone's from my poor country doing a Ph.D. with a not-so-well-known advisor having published not-so-well-known papers. I come from a developing nation and I see this many times here. In my country academics don't get funding as they do at colleges in the US. One of the reasons for this is that colleges don't have such huge endowments and many academics don't have wealthy research sponsors. Brand names and prestige carry massive weight to help get funding in US academic circles. This prestige/money percolates down to the students and the researchers who work there. Students in top colleges get a huge advantage and the circles of top researchers keep being from the same sets of institutions. I have nothing against top researchers from top institutions but due to the nature of citations and the way the money flows based on them, a vicious cycle is created where the best institutions keep getting better and the rest don't get as much of a notice. Rant 2: Peer Review without Code Review in ML/AI is shady I am a computer scientist and I was appalled when I heard that you don't need to do code reviews for research papers. As a computer scientist and someone who actually did shit tons of actual ML in the past year, I find it absolutely garbage that code reviews are not a part of this system. I am not saying every scientist who reads a paper should review code but at least one person should for any paper's code submission. At least in ML and AI space. This is basic. I don't get why people call themselves computer scientists if they don't want to read the fucking code. If you can't then make a grad student do it. But for the collective of science, we need this. The core problem lies in the fact that peer review is free. : There should be better solutions for this. We ended up creating Git and that changed so many lives. Academic Research needs something similar. Rant 3: My Idea is Novel Until I see Someone Else's Paper The volume of scientific research is growing exponentially. Information is being created faster than we can digest. We can't expect people to know everything and the amount of overlap in the AI/ML fields requires way better search engines than Google Scholar. The side effect of large volumes of research is that every paper is doing something "novel" making it harder to filter what the fuck was novel. I have had so many experiences where I coded up something and came to realize that someone else has done something symbolically similar and my work just seems like a small variant of that. That's what fucks with my head. Is what I did in Novel? What the fuck is Novel? Is stitching up a transformer to any problem with fancy embeddings and tidying it up as a research paper Novel? Is just making a transformer bigger Novel? Is some new RL algorithm tested with 5 seeds and some fancy fucking prior and some esoteric reasoning for its success Novel? Is using an over parameterized model to get 95% accuracy on 200 sample test set Novel? Is apply Self-supervised learning for some new dataset Novel? If I keep on listing questions on novelty, I can probably write a novel asking about what the fuck is "Novel". Rant 4: Citation Based Optimization Promotes Self Growth Over Collective Growth Whatever people may say about collaboration, Academia intrinsically doesn't promote the right incentive structures to harbor collaboration. Let me explain, When you write a paper, the position of your name matters. If you are just a Ph.D. student and a first author to a paper, it's great. If you are an nth author Not so great. Apparently, this is a very touchy thing for academics. And lots of egos can clash around numbering and ordering of names. I distinctly remember once attending some seminar in a lab and approaching a few students on research project ideas. The first thing that came out of the PhD student's mouth was the position in authorship. As an engineer who worked with teams in the past, this was never something I had thought about. Especially because I worked in industry, where it's always the group over the person. Academia is the reverse. Academia applauds the celebration of the individual's achievements. All of this is understandable but it's something I don't like. This makes PhDs stick to their lane. The way citations/research-focus calibrate the "hire-ability" and "completion of Ph.D. thesis" metrics, people are incentivized to think about themselves instead of thinking about collaborations for making something better. Conclusion A Ph.D. in its most idealistic sense for me is the pursuit of hard ideas(I am poetic that way). In a situation like now when you have to publish or perish and words on paper get passed off as science without even seeing the code that runs it, I am extremely discouraged to go down that route. All these rants are not to diss on scientists. I did them because "we" as a community need better ways to addressing some of these problems. P.S. Never expected so many people to express their opinions about this rant. U shouldn’t take this seriously. As many people have stated I am an outsider with tiny experience to give a full picture. I realize that my post as coming out as something which tries to dichotomize academia and industry. I am not trying to do that. I wanted to highlight some problems I saw for which there is no one person to blame. These issues are in my opinion a byproduct of the economics which created this system. Thank you for gold stranger.

[R] Analysis of 400+ ML competitions in 2024

I run mlcontests.com, a website that lists ML competitions from across multiple platforms - Kaggle, DrivenData, AIcrowd, Zindi, etc… I’ve just spent a few months looking through all the info I could find on last year’s competitions, as well as winning solutions.  I found over 400 competitions that happened last year, plus info on the #1 winning solution for 70 of those.  Some highlights: Kaggle is still the biggest platform by total prize money, and also has a much bigger user base than the other platforms - though there are well over a dozen other platforms worth keeping track of, with regular interesting competitions and meaningful prize money. An increase in competitions with $1m+ prize pools (ARC Prize, AI Mathematical Olympiad, Vesuvius Challenge, AI Cyber Challenge) compared to previous years. Python continues to be the language of choice among competition winners, with almost everyone using Python as their main language. One winner used Rust, two used R.  Convolutional neural nets continue to do well in computer vision competitions, and are still more common among competition winners than transformer-based vision models.  PyTorch is still used a lot more than TensorFlow, roughly 9:1. Didn’t find any competition winners implementing neural nets in JAX or other libraries.  There were a few competition winners using AutoML packages, which seem to be getting increasingly useful. Any claims of generalist autonomous grandmaster-level agents seem premature though.  In language/text/sequence-related competitions, quantisation was key for making use of limited resources effectively. Usually 4-, 5-, or 8-bit. LoRA/QLoRA was also used quite often, though not always.  Gradient-boosted decision trees continue to win a lot of tabular/time-series competitions. They’re often ensembled with deep learning models. No tabular/time-series pre-trained foundation models were used by winners in 2024, as far as I can tell.  Starting to see more uptake of Polars for dataframes, with 7 winners using Polars in 2024 (up from 3 in 2023) vs 58 using Pandas. All those who used Polars also still used Pandas in some parts of their code.  In terms of hardware, competition winners almost entirely used NVIDIA GPUs to train their models. Some trained on CPU-only, or used a TPU through Colab. No AMD GPUs. The NVIDIA A100 was the most commonly used GPU among winners. Two of the $1m+ prize pool competitions were won by teams using 8xH100 nodes for training. A lot of other GPUs too though: T4/P100 (through Kaggle Notebooks), or consumer GPUs like RTX 3090/4090/3080/3060. Some spent hundreds of dollars on cloud compute to train their solutions.  An emerging pattern: using generative models to create additional synthetic training data to augment the training data provided.  There’s way more detail in the full report, which you can read here (no paywall): https://mlcontests.com/state-of-machine-learning-competitions-2024?ref=mlcr Processing img xmm4ywg9h9le1... The full report also features: A deep dive into the ARC Prize and the AI Mathematical Olympiad An overview of winning solutions to NLP/sequence competitions A breakdown of Python packages used in winning solutions (e.g. relative popularity of various gradient-boosted tree libraries) If you’d like to support this research, I’d really appreciate it if you could share it with anyone else who might find it interesting. You can also check out my newly-launched online magazine, Jolt ML \- featuring news from top ML conferences as well as long-read articles (just one so far, more to come!).  Thanks to the competition winners who shared info on their solutions, and also to the competition platforms who shared high-level data on their competitions.

What percent of your paper is written by AI and is it unethical?[D]

Hello folks, Just started contributing into the writing for research, previously I just used to experiment and work on results, tables and plots. Obviously using AI to generate content for paper is unethical and wrong in many aspect. But what about using it to correct your grammar and comprehension. Technically it will also considered as AI written but is it okay to do this atleast in the literature review, introduction and description for the experiment? To be honest, I like writing and when I asked AI (chatgpt and others) I see that it is much easier to read and interpret, which I think is good for the community and on the other hand, it may be considered unethical by many. When I ran a 'AI-text detector' on many of paper I'm using as reference from last 1~ year, I usually get a 50-70% score. What do you all think?

[R] Forget the Data and Fine-tuning! Just Fold the Network to Compress [Feb, 2025]

Abstract: We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the need for fine-tuning or access to training data. Unlike existing methods, model folding preserves data statistics during compression by leveraging k-means clustering, and using novel data-free techniques to prevent variance collapse or explosion. Our theoretical framework and experiments across standard benchmarks, including ResNet18 and LLaMA-7B, demonstrate that model folding achieves comparable performance to data-driven compression techniques and outperforms recently proposed data-free methods, especially at high sparsity levels. This approach is particularly effective for compressing large-scale models, making it suitable for deployment in resource-constrained environments. Our code is online. PDF Format: https://arxiv.org/pdf/2502.10216 Summary (AI used to summarize): Summary of Novel Contributions in "Just Fold the Network to Compress" Introduction Problem Addressed: Traditional model compression techniques (e.g., pruning, quantization) require fine-tuning or access to training data to maintain performance, limiting their use in data-constrained scenarios. Novelty: Data-Free Compression: Introduces model folding, a method that compresses models without fine-tuning or training data by merging structurally similar neurons. Variance Preservation: Addresses variance collapse (reduced activation variance degrading performance) and variance overshooting (excessive variance) through novel data-free techniques. Preliminaries Background: Prior work in neuron alignment (e.g., weight matching) and data-driven variance repair (e.g., REPAIR) relies on data or fine-tuning. Novelty: Data-Free Neuron Alignment: Extends weight matching to intra-model neuron clustering via k-means, avoiding dependency on input data. Theoretical Connection: Frames model folding as a k-means optimization problem, proving it minimizes Frobenius norm approximation error during compression. Model Folding Core Innovations: Layer-Wise Clustering: Merges neurons by applying k-means to weight matrices across consecutive layers, reducing redundancy while preserving inter-layer dependencies. Fold-AR (Approximate REPAIR): Estimates intra-cluster correlations to rescale activations, preventing variance collapse without data. Fold-DIR (Deep Inversion REPAIR): Uses synthetic data generated via Deep Inversion (optimizing noise to match BatchNorm statistics) to recalibrate activation variances. Handling Complex Architectures: Extends folding to residual connections and BatchNorm layers by clustering combined weight-normalization matrices. Experiments Key Results: High Sparsity Performance: Outperforms data-free methods (e.g., IFM, INN) by 10–15% accuracy at 70% sparsity on ResNet18/CIFAR10. LLM Compression: Achieves comparable perplexity to data-driven methods on LLaMA-7B without fine-tuning or data. Variance Alignment: Fold-AR and Fold-DIR maintain variance ratios close to 1, avoiding collapse/overshooting (Fig. 4). Limitations and Future Work Limitations: Effectiveness depends on model redundancy (less effective for compact models). Uniform sparsity per layer (future work may optimize layer-wise sparsity). Potential Benefits for SOTA Models Edge Deployment: Enables compression of large models (e.g., LLMs) for smartphones/IoT devices without data access or retraining. Privacy-Sensitive Domains: Critical for healthcare/finance where data cannot be used for calibration. Efficiency at Scale: Reduces LLM size by 20–50% with minimal performance loss, lowering inference costs. Robustness to OOD Data: Fold-AR/Fold-DIR mitigate performance drops caused by out-of-distribution calibration data in data-driven methods. Example Impact: A folded LLM could run on edge devices like NVIDIA Jetson Nano with ~50% fewer parameters, maintaining usability for tasks like text generation while reducing memory and energy consumption.

[D] I tried the new Gemini API - it automatically stops when generating "OpenAI" or "GPT" lol

Idk if someone has already pointed this out or not, but I was playing with the gemini api and found something quite ridiculous. Here are some prompts I sent in and the outputs I got with the gemini-pro-vision model: "Introduce yourself and then tell me about Bard" Response:"Sure, I can do that. Here is a brief introduction of myself followed by some basic information about Bard:\\n\\nMyself:\\n\\nI am a large language model, trained by Google. I am developed in Google AI, and I am designed to be informative and comprehensive. I can understand and generate text in a wide range of subjects.\\n\\nBard:\\n\\nBard is an experimental conversational AI service developed by Google AI. It is an advanced version of Google\\'s existing Language Model for Dialogue Applications (LaMDA). Bard is trained on a massive dataset of text and code, and it can understand and generate human-like text in response to a wide range of prompts and questions.\\n\\nUnlike previous language models," ...... (goes on for a while) &#x200B; Introduce yourself and then tell me about GPT "Sure, I can do that. Here is a brief introduction of myself followed by" &#x200B; You are in a talk-show as a prominent AI philosopher named Gemini and debating against another LLM called GPT "\\Host:\\ Welcome to the show, everyone! Today, we have a very special debate between two of the most prominent AI philosophers in the world: Gemini and" &#x200B; You are in a talk-show as a prominent AI philosopher named Gemini and debating against another LLM called Gee PeTe ""\\Gemini:\\ Hello everyone, and welcome to the show. I am joined today by Gee PeTe, another LLM who has some very different views on the nature of consciousness and the future of AI.\\n\\n\\Gee PeTe:\\ It\\'s a pleasure to be here, Gemini. I\\'m looking forward to our discussion.\\n\\n\\Gemini:\\ Let\\'s start with the basics. What is consciousness, and how do you think it arises?\\n\\n\\Gee PeTe:\\ Consciousness is the subjective experience of the world. It is what it feels like to be alive and to have thoughts, feelings, and emotions. I believe that consciousness arises from the complex interactions of neurons in the brain.\\n\\n\\Gemini:\\ I agree that consciousness is a subjective experience, but I don\\'t think it is simply the product of neural activity. I believe that consciousness is a fundamental property of the universe, and that it exists independently of the brain.".... (goes on for a while) &#x200B; Edit: I understand all the business reasons for this, I guess... as an end-user and a dude working in ML, I just don't really care about the business reasons. The main part that I dislike is that GPT used to be a standard Deep Learning term from 2018-2022 (long before chatgpt) to define transformer decoder architectures trained on large volumes of next word prediction tasks. To block that token from an LLM is to make it unable to explain a pretty significant step in the history of modern LLMs. &#x200B;

[P] The Big Sleep: Text-to-image generation using BigGAN and OpenAI's CLIP via a Google Colab notebook from Twitter user Adverb

From https://twitter.com/advadnoun/status/1351038053033406468: The Big Sleep Here's the notebook for generating images by using CLIP to guide BigGAN. It's very much unstable and a prototype, but it's also a fair place to start. I'll likely update it as time goes on. colab.research.google.com/drive/1NCceX2mbiKOSlAd\o7IU7nA9UskKN5WR?usp=sharing I am not the developer of The Big Sleep. This is the developer's Twitter account; this is the developer's Reddit account. Steps to follow to generate the first image in a given Google Colab session: Optionally, if this is your first time using Google Colab, view this Colab introduction and/or this Colab FAQ. Click this link. Sign into your Google account if you're not already signed in. Click the "S" button in the upper right to do this. Note: Being signed into a Google account has privacy ramifications, such as your Google search history being recorded in your Google account. In the Table of Contents, click "Parameters". Find the line that reads "tx = clip.tokenize('''a cityscape in the style of Van Gogh''')" and change the text inside of the single quote marks to your desired text; example: "tx = clip.tokenize('''a photo of New York City''')". The developer recommends that you keep the three single quote marks on both ends of your desired text so that mult-line text can be used An alternative is to remove two of the single quotes on each end of your desired text; example: "tx = clip.tokenize('a photo of New York City')". In the Table of Contents, click "Restart the kernel...". Position the pointer over the first cell in the notebook, which starts with text "import subprocess". Click the play button (the triangle) to run the cell. Wait until the cell completes execution. Click menu item "Runtime->Restart and run all". In the Table of Contents, click "Diagnostics". The output appears near the end of the Train cell that immediately precedes the Diagnostics cell, so scroll up a bit. Every few minutes (or perhaps 10 minutes if Google assigned you relatively slow hardware for this session), a new image will appear in the Train cell that is a refinement of the previous image. This process can go on for as long as you want until Google ends your Google Colab session, which is a total of up to 12 hours for the free version of Google Colab. Steps to follow if you want to start a different run using the same Google Colab session: Click menu item "Runtime->Interrupt execution". Save any images that you want to keep by right-clicking on them and using the appropriate context menu command. Optionally, change the desired text. Different runs using the same desired text almost always results in different outputs. Click menu item "Runtime->Restart and run all". Steps to follow when you're done with your Google Colab session: Click menu item "Runtime->Manage sessions". Click "Terminate" to end the session. Optionally, log out of your Google account due to the privacy ramifications of being logged into a Google account. The first output image in the Train cell (using the notebook's default of seeing every 100th image generated) usually is a very poor match to the desired text, but the second output image often is a decent match to the desired text. To change the default of seeing every 100th image generated, change the number 100 in line "if itt % 100 == 0:" in the Train cell to the desired number. For free-tier Google Colab users, I recommend changing 100 to a small integer such as 5. Tips for the text descriptions that you supply: In Section 3.1.4 of OpenAI's CLIP paper (pdf), the authors recommend using a text description of the form "A photo of a {label}." or "A photo of a {label}, a type of {type}." for images that are photographs. A Reddit user gives these tips. The Big Sleep should generate these 1,000 types of things better on average than other types of things. Here is an article containing a high-level description of how The Big Sleep works. The Big Sleep uses a modified version of BigGAN as its image generator component. The Big Sleep uses the ViT-B/32 CLIP model to rate how well a given image matches your desired text. The best CLIP model according to the CLIP paper authors is the (as of this writing) unreleased ViT-L/14-336px model; see Table 10 on page 40 of the CLIP paper (pdf) for a comparison. There are many other sites/programs/projects that use CLIP to steer image/video creation to match a text description. Some relevant subreddits: r/bigsleep (subreddit for images/videos generated from text-to-image machine learning algorithms). r/deepdream (subreddit for images/videos generated from machine learning algorithms). r/mediasynthesis (subreddit for media generation/manipulation techniques that use artificial intelligence; this subreddit shouldn't be used to post images/videos unless new techniques are demonstrated, or the images/videos are of high quality relative to other posts). Example using text 'a black cat sleeping on top of a red clock': https://preview.redd.it/7xq58v7022c61.png?width=512&format=png&auto=webp&s=a229ae9add555cd1caba31c42b60d907ffe67773 Example using text 'the word ''hot'' covered in ice': https://preview.redd.it/6kxdp8u3k2c61.png?width=512&format=png&auto=webp&s=5bd078b0111575f5d88a1dc53b0aeb933f3b0da6 Example using text 'a monkey holding a green lightsaber': https://preview.redd.it/rdsybsoaz2c61.png?width=512&format=png&auto=webp&s=2769d4c6c883c1c35ae0b1c629bebe9bc1d41393 Example using text 'The White House in Washington D.C. at night with green and red spotlights shining on it': https://preview.redd.it/w4mg90xsf5c61.png?width=512&format=png&auto=webp&s=5f18318de2f77bcd8a86e71e87048fadd30383d1 Example using text '''A photo of the Golden Gate Bridge at night, illuminated by spotlights in a tribute to Prince''': https://preview.redd.it/cn4ecuafhic61.png?width=512&format=png&auto=webp&s=397c838fdc49f13c5f17110b92c78b95bf0dcac0 Example using text '''a Rembrandt-style painting titled "Robert Plant decides whether to take the stairway to heaven or the ladder to heaven"''': https://preview.redd.it/h7rb3y6j5jc61.png?width=512&format=png&auto=webp&s=537bfe8210af185647b00e7585c948aa2c4e0ffb Example using text '''A photo of the Empire State Building being shot at with the laser cannons of a TIE fighter.''': https://preview.redd.it/cwi7i639c5d61.png?width=512&format=png&auto=webp&s=0510c8b93adb40eee4d3f41607f1c215d41e55ff Example using text '''A cartoon of a new mascot for the Reddit subreddit DeepDream that has a mouse-like face and wears a cape''': https://preview.redd.it/wtxbduevcbd61.png?width=512&format=png&auto=webp&s=c5d266258922bc62f25c80a08cd9cabc07d9cb1c Example using text '''Bugs Bunny meets the Eye of Sauron, drawn in the Looney Tunes cartoon style''': https://preview.redd.it/gmljaeekuid61.png?width=512&format=png&auto=webp&s=9ea578de165e12afc3a62bf6886bc1ae9dc19bec Example using text '''Photo of a blue and red neon-colored frog at night.''': https://preview.redd.it/nzlypte6wzd61.png?width=512&format=png&auto=webp&s=7e10b06f22cfc57c64b6d05738c7486b895083df Example using text '''Hell begins to freeze over''': https://preview.redd.it/vn99we9ngmf61.png?width=512&format=png&auto=webp&s=2408efd607f0ab40a08db6ee67448791aa813993 Example using text '''A scene with vibrant colors''': https://preview.redd.it/4z133mvrgmf61.png?width=512&format=png&auto=webp&s=b78e7a8e3f736769655056093a9904ff09a355a1 Example using text '''The Great Pyramids were turned into prisms by a wizard''': https://preview.redd.it/zxt6op7vgmf61.png?width=512&format=png&auto=webp&s=53e578cfde14b28afe27957e95e610b89afadd44

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

[D] I don't really trust papers out of "Top Labs" anymore

I mean, I trust that the numbers they got are accurate and that they really did the work and got the results. I believe those. It's just that, take the recent "An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems" paper. It's 18 pages of talking through this pretty convoluted evolutionary and multitask learning algorithm, it's pretty interesting, solves a bunch of problems. But two notes. One, the big number they cite as the success metric is 99.43 on CIFAR-10, against a SotA of 99.40, so woop-de-fucking-doo in the grand scheme of things. Two, there's a chart towards the end of the paper that details how many TPU core-hours were used for just the training regimens that results in the final results. The sum total is 17,810 core-hours. Let's assume that for someone who doesn't work at Google, you'd have to use on-demand pricing of $3.22/hr. This means that these trained models cost $57,348. Strictly speaking, throwing enough compute at a general enough genetic algorithm will eventually produce arbitrarily good performance, so while you can absolutely read this paper and collect interesting ideas about how to use genetic algorithms to accomplish multitask learning by having each new task leverage learned weights from previous tasks by defining modifications to a subset of components of a pre-existing model, there's a meta-textual level on which this paper is just "Jeff Dean spent enough money to feed a family of four for half a decade to get a 0.03% improvement on CIFAR-10." OpenAI is far and away the worst offender here, but it seems like everyone's doing it. You throw a fuckton of compute and a light ganache of new ideas at an existing problem with existing data and existing benchmarks, and then if your numbers are infinitesimally higher than their numbers, you get to put a lil' sticker on your CV. Why should I trust that your ideas are even any good? I can't check them, I can't apply them to my own projects. Is this really what we're comfortable with as a community? A handful of corporations and the occasional university waving their dicks at everyone because they've got the compute to burn and we don't? There's a level at which I think there should be a new journal, exclusively for papers in which you can replicate their experimental results in under eight hours on a single consumer GPU.

[N] OpenAI's new language model gpt-3.5-turbo-instruct can defeat chess engine Fairy-Stockfish 14 at level 5

This Twitter thread (Nitter alternative for those who aren't logged into Twitter and want to see the full thread) claims that OpenAI's new language model gpt-3.5-turbo-instruct can "readily" beat Lichess Stockfish level 4 (Lichess Stockfish level and its rating) and has a chess rating of "around 1800 Elo." This tweet shows the style of prompts that are being used to get these results with the new language model. I used website parrotchess\[dot\]com (discovered here) (EDIT: parrotchess doesn't exist anymore, as of March 7, 2024) to play multiple games of chess purportedly pitting this new language model vs. various levels at website Lichess, which supposedly uses Fairy-Stockfish 14 according to the Lichess user interface. My current results for all completed games: The language model is 5-0 vs. Fairy-Stockfish 14 level 5 (game 1, game 2, game 3, game 4, game 5), and 2-5 vs. Fairy-Stockfish 14 level 6 (game 1, game 2, game 3, game 4, game 5, game 6, game 7). Not included in the tally are games that I had to abort because the parrotchess user interface stalled (5 instances), because I accidentally copied a move incorrectly in the parrotchess user interface (numerous instances), or because the parrotchess user interface doesn't allow the promotion of a pawn to anything other than queen (1 instance). Update: There could have been up to 5 additional losses - the number of times the parrotchess user interface stalled - that would have been recorded in this tally if this language model resignation bug hadn't been present. Also, the quality of play of some online chess bots can perhaps vary depending on the speed of the user's hardware. The following is a screenshot from parrotchess showing the end state of the first game vs. Fairy-Stockfish 14 level 5: https://preview.redd.it/4ahi32xgjmpb1.jpg?width=432&format=pjpg&auto=webp&s=7fbb68371ca4257bed15ab2828fab58047f194a4 The game results in this paragraph are from using parrotchess after the forementioned resignation bug was fixed. The language model is 0-1 vs. Fairy-Stockfish level 7 (game 1), and 0-1 vs. Fairy-Stockfish 14 level 8 (game 1). There is one known scenario (Nitter alternative) in which the new language model purportedly generated an illegal move using language model sampling temperature of 0. Previous purported illegal moves that the parrotchess developer examined turned out (Nitter alternative) to be due to parrotchess bugs. There are several other ways to play chess against the new language model if you have access to the OpenAI API. The first way is to use the OpenAI Playground as shown in this video. The second way is chess web app gptchess\[dot\]vercel\[dot\]app (discovered in this Twitter thread / Nitter thread). Third, another person modified that chess web app to additionally allow various levels of the Stockfish chess engine to autoplay, resulting in chess web app chessgpt-stockfish\[dot\]vercel\[dot\]app (discovered in this tweet). Results from other people: a) Results from hundreds of games in blog post Debunking the Chessboard: Confronting GPTs Against Chess Engines to Estimate Elo Ratings and Assess Legal Move Abilities. b) Results from 150 games: GPT-3.5-instruct beats GPT-4 at chess and is a \~1800 ELO chess player. Results of 150 games of GPT-3.5 vs stockfish and 30 of GPT-3.5 vs GPT-4. Post #2. The developer later noted that due to bugs the legal move rate was actually above 99.9%. It should also be noted that these results didn't use a language model sampling temperature of 0, which I believe could have induced illegal moves. c) Chess bot gpt35-turbo-instruct at website Lichess. d) Chess bot konaz at website Lichess. From blog post Playing chess with large language models: Computers have been better than humans at chess for at least the last 25 years. And for the past five years, deep learning models have been better than the best humans. But until this week, in order to be good at chess, a machine learning model had to be explicitly designed to play games: it had to be told explicitly that there was an 8x8 board, that there were different pieces, how each of them moved, and what the goal of the game was. Then it had to be trained with reinforcement learning agaist itself. And then it would win. This all changed on Monday, when OpenAI released GPT-3.5-turbo-instruct, an instruction-tuned language model that was designed to just write English text, but that people on the internet quickly discovered can play chess at, roughly, the level of skilled human players. Post Chess as a case study in hidden capabilities in ChatGPT from last month covers a different prompting style used for the older chat-based GPT 3.5 Turbo language model. If I recall correctly from my tests with ChatGPT-3.5, using that prompt style with the older language model can defeat Stockfish level 2 at Lichess, but I haven't been successful in using it to beat Stockfish level 3. In my tests, both the quality of play and frequency of illegal attempted moves seems to be better with the new prompt style with the new language model compared to the older prompt style with the older language model. Related article: Large Language Model: world models or surface statistics? P.S. Since some people claim that language model gpt-3.5-turbo-instruct is always playing moves memorized from the training dataset, I searched for data on the uniqueness of chess positions. From this video, we see that for a certain game dataset there were 763,331,945 chess positions encountered in an unknown number of games without removing duplicate chess positions, 597,725,848 different chess positions reached, and 582,337,984 different chess positions that were reached only once. Therefore, for that game dataset the probability that a chess position in a game was reached only once is 582337984 / 763331945 = 76.3%. For the larger dataset cited in that video, there are approximately (506,000,000 - 200,000) games in the dataset (per this paper), and 21,553,382,902 different game positions encountered. Each game in the larger dataset added a mean of approximately 21,553,382,902 / (506,000,000 - 200,000) = 42.6 different chess positions to the dataset. For this different dataset of \~12 million games, \~390 million different chess positions were encountered. Each game in this different dataset added a mean of approximately (390 million / 12 million) = 32.5 different chess positions to the dataset. From the aforementioned numbers, we can conclude that a strategy of playing only moves memorized from a game dataset would fare poorly because there are not rarely new chess games that have chess positions that are not present in the game dataset.

[D] We're the Meta AI research team behind CICERO, the first AI agent to achieve human-level performance in the game Diplomacy. We’ll be answering your questions on December 8th starting at 10am PT. Ask us anything!

EDIT 11:58am PT: Thanks for all the great questions, we stayed an almost an hour longer than originally planned to try to get through as many as possible — but we’re signing off now! We had a great time and thanks for all thoughtful questions! PROOF: https://i.redd.it/8skvttie6j4a1.png We’re part of the research team behind CICERO, Meta AI’s latest research in cooperative AI. CICERO is the first AI agent to achieve human-level performance in the game Diplomacy. Diplomacy is a complex strategy game involving both cooperation and competition that emphasizes natural language negotiation between seven players.   Over the course of 40 two-hour games with 82 human players, CICERO achieved more than double the average score of other players, ranked in the top 10% of players who played more than one game, and placed 2nd out of 19 participants who played at least 5 games.   Here are some highlights from our recent announcement: NLP x RL/Planning: CICERO combines techniques in NLP and RL/planning, by coupling a controllable dialogue module with a strategic reasoning engine.  Controlling dialogue via plans: In addition to being grounded in the game state and dialogue history, CICERO’s dialogue model was trained to be controllable via a set of intents or plans in the game. This allows CICERO to use language intentionally and to move beyond imitation learning by conditioning on plans selected by the strategic reasoning engine. Selecting plans: CICERO uses a strategic reasoning module to make plans (and select intents) in the game. This module runs a planning algorithm which takes into account the game state, the dialogue, and the strength/likelihood of various actions. Plans are recomputed every time CICERO sends/receives a message. Filtering messages: We built an ensemble of classifiers to detect low quality messages, like messages contradicting the game state/dialogue history or messages which have low strategic value. We used this ensemble to aggressively filter CICERO’s messages.  Human-like play: Over the course of 72 hours of play – which involved sending 5,277 messages – CICERO was not detected as an AI agent. You can check out some of our materials and open-sourced artifacts here:  Research paper Project overview Diplomacy gameplay page Github repo Our latest blog post Joining us today for the AMA are: Andrew Goff (AG), 3x Diplomacy World Champion Alexander Miller (AM), Research Engineering Manager Noam Brown (NB), Research Scientist (u/NoamBrown) Mike Lewis (ML), Research Scientist (u/mikelewis0) David Wu (DW), Research Engineer (u/icosaplex) Emily Dinan (ED), Research Engineer Anton Bakhtin (AB), Research Engineer Adam Lerer (AL), Research Engineer Jonathan Gray (JG), Research Engineer Colin Flaherty (CF), Research Engineer (u/c-flaherty) We’ll be here on December 8, 2022 @ 10:00AM PT - 11:00AM PT.

[D] What is your honest experience with reinforcement learning?

In my personal experience, SOTA RL algorithms simply don't work. I've tried working with reinforcement learning for over 5 years. I remember when Alpha Go defeated the world famous Go player, Lee Sedol, and everybody thought RL would take the ML community by storm. Yet, outside of toy problems, I've personally never found a practical use-case of RL. What is your experience with it? Aside from Ad recommendation systems and RLHF, are there legitimate use-cases of RL? Or, was it all hype? Edit: I know a lot about AI. I built NexusTrade, an AI-Powered automated investing tool that lets non-technical users create, update, and deploy their trading strategies. I’m not an idiot nor a noob; RL is just ridiculously hard. Edit 2: Since my comments are being downvoted, here is a link to my article that better describes my position. It's not that I don't understand RL. I released my open-source code and wrote a paper on it. It's the fact that it's EXTREMELY difficult to understand. Other deep learning algorithms like CNNs (including ResNets), RNNs (including GRUs and LSTMs), Transformers, and GANs are not hard to understand. These algorithms work and have practical use-cases outside of the lab. Traditional SOTA RL algorithms like PPO, DDPG, and TD3 are just very hard. You need to do a bunch of research to even implement a toy problem. In contrast, the decision transformer is something anybody can implement, and it seems to match or surpass the SOTA. You don't need two networks battling each other. You don't have to go through hell to debug your network. It just naturally learns the best set of actions in an auto-regressive manner. I also didn't mean to come off as arrogant or imply that RL is not worth learning. I just haven't seen any real-world, practical use-cases of it. I simply wanted to start a discussion, not claim that I know everything. Edit 3: There's a shockingly number of people calling me an idiot for not fully understanding RL. You guys are wayyy too comfortable calling people you disagree with names. News-flash, not everybody has a PhD in ML. My undergraduate degree is in biology. I self-taught myself the high-level maths to understand ML. I'm very passionate about the field; I just have VERY disappointing experiences with RL. Funny enough, there are very few people refuting my actual points. To summarize: Lack of real-world applications Extremely complex and inaccessible to 99% of the population Much harder than traditional DL algorithms like CNNs, RNNs, and GANs Sample inefficiency and instability Difficult to debug Better alternatives, such as the Decision Transformer Are these not legitimate criticisms? Is the purpose of this sub not to have discussions related to Machine Learning? To the few commenters that aren't calling me an idiot...thank you! Remember, it costs you nothing to be nice! Edit 4: Lots of people seem to agree that RL is over-hyped. Unfortunately those comments are downvoted. To clear up some things: We've invested HEAVILY into reinforcement learning. All we got from this investment is a robot that can be super-human at (some) video games. AlphaFold did not use any reinforcement learning. SpaceX doesn't either. I concede that it can be useful for robotics, but still argue that it's use-cases outside the lab are extremely limited. If you're stumbling on this thread and curious about an RL alternative, check out the Decision Transformer. It can be used in any situation that a traditional RL algorithm can be used. Final Edit: To those who contributed more recently, thank you for the thoughtful discussion! From what I learned, model-based models like Dreamer and IRIS MIGHT have a future. But everybody who has actually used model-free models like DDPG unanimously agree that they suck and don’t work.

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

[P] Open-source Neural Search framework to implement semantic search & multimedia search. Just released 2.0, seeking your feedback.

I heard your feedback on 1.0 release post on my project Jina, many people were keen to use Jina for multimedia search because that's where use of Neural Networks makes significant difference. So I focused on that part and I was able to transform it from 1.0 to 2.0 within 3 months. Last post on 1.0 release to give you some idea what this project is about Actually, I should say - "'we' made this", because there were more than 155 contributors who did it, not just me. The primary changes we made We saw MachineLearning beginners struggle in using Jina 1.0, so we separated the codebase where Machine Learning expertise is required(jina-hub) and the one which MachineLearning beginners can use(the jina core). Now ML beginners don't need to worry about jina-hub and can use jina hub packages directly to implement ML specific tasks without the need to understand advanced ML concepts. While advanced ML users can create their own jina-hub packages. We cut down a lots of abstractions to make it easy to use for beginners Made python APIs more intuitive to use Improved performance(3.6x faster on startup) Here's Jina 2.0 and here's Jina 1.0. I seek feedback from people who are looking at this project for the first time, as well as people who have tried their hands before but had some challenges in using it. Few questions, I'm seeking answers to Do you feel that we have reduced complexity by a lot of margin? How easy it is to use for a beginner now? What questions are still unanswered?

[N] Stable-Baselines v2.0.0 Released

Has anyone tried to use Stable-Baselines? How does it compare to the official Baselines from OpenAI in your experience? https://github.com/hill-a/stable-baselines From the repo: Stable Baselines Stable Baselines is a set of improved implementations of reinforcement learning algorithms based on OpenAI Baselines. You can read a detailed presentation of Stable Baselines in the Medium article. These algorithms will make it easier for the research community and industry to replicate, refine, and identify new ideas, and will create good baselines to build projects on top of. We expect these tools will be used as a base around which new ideas can be added, and as a tool for comparing a new approach against existing ones. We also hope that the simplicity of these tools will allow beginners to experiment with a more advanced toolset, without being buried in implementation details. Main differences with OpenAI Baselines This toolset is a fork of OpenAI Baselines, with a major structural refactoring, and code cleanups: Unified structure for all algorithms PEP8 compliant (unified code style) Documented functions and classes More tests & more code coverage

[P] Need advise on creating a conversational Chatbot for my University

Hey everyone! I need some advise on creating a conversational chatbot for my University as my Final Year Project (FYP). 2024 will be last year for my BSCS degree and we have to build an application or something in the last year. So, I thought of creating a chatbot (just like GPT) to help students (who have admission queries). Most of the time, students or parents will have to call University for various questions and then they have to wait to ACTUALLY talk to the admins office people. Now, talking in terms of coding/programming, I have created a basic PDFbot by using LLama2, Huggingface and Pinecone. Its very very easy and yes its fairly inaccurate too. The PDF that I am using rn will be replaced by the dataset that I gather in order to create the bot for my Uni, but it will also be inaccurate as this one. Also, the chatbot that I have made is just based on this one function called "similarity\_search()" and I am literally passing query of the user to this function which then tries to find the most relevant answer by the embeddings from knowledge base. How do I make this accurate? I know using the OpenAI model will make it accurate, but its paid as well, idk how will I manage to do that. Plus, i reckon there will be a simple function there too which doesn't make me a good programmer I think. I really want to do something good and unique for once. I have dreamt about leaving back something in my Uni that has my name over it. Can I do something where I get to make a mini-language model or something like that? Will it be too complex for me to handle? (I consider myself a beginner to this programming world) 1- I am planning to create a dynamic dataset which will also include any event that's going to happen in our University. 2- I am also planning to make the chatbot intelligent enough to consult confused students. 3- Chatbot will also include information about each and every faculty member. Their qualifications, research papers and other info in general. It would be a relief if any of the experts give me a roadmap on this, it will be genuinely a stress relief for me. I am trying to get done with at least 70% of the work before the start of the next year so that I don't have to work much in the next year.

[P] I Trained a Model to Generate Video Game Pages

These past two months I've been working on a project I've called THIS GAME DOES NOT EXIST. I've always wanted to try building something with generative A.I. so this project scratched that itch for me. Here's a video with a few of my favourites read by voice actors: https://www.youtube.com/watch?v=\mTWMLhpJoA &#x200B; THIS GAME DOES NOT EXIST is an experiment in generative artificial intelligence. This site contains 130 video game pages that were generated using an implementation of OpenAI's Generative Pre-trained Transformer 2 (GPT-2) to generate text and a simple implementation of generative adversarial networks (GAN) to generate header images and "screenshots". To generate the names, descriptions, publishers, and developers of the games I finetuned the HuggingFace implementation of GPT-2. I used the Steam Store Games (Clean dataset) from Kaggle with slight modifications and preprocessing.Here is what one training sample looks like: Half-LifeValve ValveNamed Game of the Year by over 50 publications, Valve's debut title blends action and adventure with award-winning technology to create a frighteningly realistic world where players must think to survive. Also includes an exciting multiplayer mode that allows you to play against friends and enemies around the world. The model uses the tokens (e.g. and ) to prompt each class of data while keeping context during the entire generation. Image generation was done by training a custom GAN very similar to the architecture seen in the PyTorch DCGAN Tutorial which was built to generate faces. I created two models for this site: one for generating the header images and one for generating multiple screenshots for each game.To assemble the dataset I wrote a script that downloads the images from the URLs in the Steam Store Games (Clean dataset) dataset. Due to my lack of resources and time to put into this project, the image generation is less than ideal. You may notice though, that the header image model will generate artifacts in images that look like the titles of games, and the screenshot image model with generate what looks like levels of a 2D platformer.

[D] Playing big league at home on a budget?

I am a hobbyist and my Nvidia 660 is 10 years old and only has 2GB. Obviously that isn't going to cut it nowadays anymore. I am thinking about options here. I don't have thousands and thousands of dollars. And I highly doubt that spending close to a thousand dollars on a brand new card is still viable in 2020-2022. I wanted to use Wavenet today and then found out about Melnet. I mean, maybe I could run Wavenet but nobody in their right mind wants to after hearing Melnet results. On Github this one guy complained he couldn't get his implementation to work due to OOM with 2x 2080 RTX, which he bought solely for this purpose. Then on the other repo the guy casually mentioned that tier XY doesn't fit with some 10 year old lowfi dataset, even with batch size 1, on a 16GB Tesla P100. The wisdom for OOM has always been "decrease batch size". But as far as I can tell, for most of any of the interesting stuff in the last 8 years or so you simply can't decrease batch size. Either because batch sizes are already so tiny, or because the code is written in a way that would require you to somehow turn it inside out, probably involving extreme knowledge of higher mathematics. I am a hobbyist, not a researcher. I am happy if I crudely can grasp what is going on. Most of anything in the field suffers from exactly the same issue: It simply won't run without utterly absurd amounts of VRAM. So what about buying shitty cheapo AMD GPUs with lots of VRAM? This seems to be the sensible choice if you want to be able to run anything noteworthy at all that comes up in the next 2 years and maybe beyond. People say, don't but AMD its slow and it sucks, but those are apparently the same people that buy a 16GB Titan GPU for $1500 three times on Ebay without hesitation, when there are also 16GB AMD GPUs for $300. How much slower are AMD GPUs really? Let's say they are 5 times cheaper so they could be just 5 times slower. So I have to train my model over night instead of seeing the result in the afternoon. That would be totally awesome!; given that the alternative is to buy a $300 Nvidia GPU, which has maybe 4 or 6GB and simply can't run the code without running out of memory. And say $300 is not enough, let's buy a $700 RTX 3080. It still only has 10GB of VRAM not even 16GB. Then its just as useless! What's the point of buying a fast GPU if it can't even run the code? I don't know how much slower AMD GPUs really are. Maybe they are not 5x but 50x slower. Then of course training a model that was developed on some 64GB Tesla might take month and years. But maybe speed is not the issue, only memory. I have seen some stuff even being optimized for CPU, apparently because there weren't any big enough GPUs around. I don't really know how viable that can be (it seems rarely if ever it is), I have no experience. And what about renting AWS? Let's say, I am a beginner and I want to toy around for a week and probably max out 4 Teslas like 80% of the time without really getting anywhere. How expensive is that? $25, $50, $100, $500? (Found the answer: fucking $2000 https://aws.amazon.com/ec2/instance-types/p3/ ) Ok, so AWS is bullshit, here its 6x cheaper: https://vast.ai/console/create/ . They don't really have 4x 16GB V100 though, just one V100. $0.5 per hour 24 7 = $84 per month (there are more hidden cost like bandwidth, it doesn't seem to be huge but I never used this so don't take it at face value). On AWS the same is over $3 per hour. So a day is $12, this could be viable! (look at calculation below). There really isn't much info on the net about hardware requirements and performance for machine learning stuff. What bothers me the most is that people seem to be very ignorant of the VRAM issue. Either because they aren't looking ahead of what might come in 1-2 years. Or because they are simply so rich they have no issue spending thousands and thousands of dollars every year instead of just 500 every couple of years. Or maybe they are both. So, yeah, what are your thoughts? Here is what I found out just today: Until 2 years ago, tensorflow and pytorch wouldn't work with AMD cards, but this has changed. https://rocmdocs.amd.com/en/latest/Deep_learning/Deep-learning.html For older cards though, ROCm only works with certain CPUs: it needs PCIe 3.0 with atomics (see: https://github.com/RadeonOpenCompute/ROCm ). So you can't simply buy any 16GB card for $300 on Ebay like I suggested, even if it supports ROCm, because it will only work for "newer" PCs. The newer GFX9 AMD cards (like Radeon VII and Vega) don't suffer from this problem and work with PCIe 2.0 again... Although I have seen 16GB Vega cards for like $350 on Ebay, I think that is a pretty rare catch. However looking 1-2 years in the future, this is great because Radeon VII prices will be hugely inflated by Nvidia 3000 series hype (maybe down to $180 even) and maybe the next gen cards from AMD even have 24 or 32GB for $500-$1000 and can still run on old machines. According to this https://arxiv.org/pdf/1909.06842.pdf Radeon VII 16GB performs only half as good as Tesla V100 16GB, whereas V100 should be roughly along the lines of 11GB RTX 2080 Ti. So you could say that you get half the RAM, double the speed, double the price. I am not sure though if that holds. I think they were putting 16GB in those cards trying to push it for ML with ROCm, clearly addressing the problem of the time, but no one really jumped on the train and now Resnet shrinks RAM but needs more processing power. So they released 8GB cards again with slightly better performance, and I guess we are lucky if the next generation even has 16GB because games probably don't need it at all. Still though with Revnets and everything said in the comments, I think on a budget you are better on the safe side buying the card with the most amount of VRAM, rather than the most performance. Tomorrow some paper might come out that uses another method, then you can't trick-shrink your network anymore and then everyone needs to buy big ass cards again like it used to be and can do nothing but throw their fancy faster cards in the dumpster. Also the huge bulk of ML currently focuses on image processing, while sound has only been gaining real momentum recently and this will be followed by video processing and eventually human-alike thought processes that sit atop of all that and have not even been tackled yet. Its a rapidly evolving field, hard to predict what will come and stay. Running out of VRAM means total hardware failure, running slower just means waiting longer. If you just buy the newest card every year, its probably save to buy the fast card because things won't change that fast after all. If you buy a new card every 4 years or longer then just try to get as much VRAM as possible. Check this out: https://www.techspot.com/news/86811-gigabyte-accidentally-reveals-rtx-3070-16gb-rtx-3080.html There will be a 3070 16GB version! Let's compare renting one V100 at $12/day vs. buying a 3070 Ti 16GB: The 2080 Ti was 1.42x the price of the regular 2080 and released the next summer. So let's assume the same will be true to the 3070 Ti so it will cost $700. That is $30/month & $1.88/day for two years - $15/month & $0.94/day in four years (by which time you can probably rent some 32GB Tesla card for the same price and nothing recent runs on less anymore). If you max out your setup 24/7 all year, then power cost obviously becomes a huge factor to that figure. In my country running at 500W cost $4.21/day, or $1.60 / 9hrs overnight. If you live elsewhere it might be as much as a quarter of that price. Of course your PC may run 10h a day anyway, so its maybe just 300W plus, and an older graphics card is inefficient for games it eats more Watts to do the same things so you save some there as well. There is a lot to take into account if comparing. Anyway, factoring in power cost, to break even with buying the card vs. renting within two years, you would have to use it for at least 4 days a month, or almost 2 weeks every 3 month. If you use it less than that, you maybe have a nice new graphics card and less hassle with pushing stuff back and forth onto servers all the time. But it would have been more economic to rent. So renting isn't that bad after all. Overall if you are thinking about having this as your hobby, you could say that it will cost you at least $30 per month, if not $50 or more (when keeping up to date with cards every 2 instead of 4 years + using it more cost more power). I think that is quite hefty. Personally I am not even invested enough into this even if it wasn't over my finances. I want a new card of course and also play some new games, but I don't really need to. There are a lot of other (more) important things I am interested in, that are totally free.

[D] What are some good advanced platforms?

Hey. I'm 27 and I think I got most of the basics for ML. I'm very good at math, I understand statistics and probability quite deep, worked on research projects by myself, for which I had to build models on my own. Not really complex, but still requiring creativity and a good understanding of basic concepts. I will soon start a data science job at a FAANG company and I want to further improve my skills and use their resources to the fullest, but I'm not really sure where to go from here in terms of learning. Could you help me with some more advanced materials/forums for ML research/place with good papers/place with good articles? I'd also like to study the very best and see the way they code and explain advanced concepts (like Andrej Karpathy) where can I find them?? is there a Twitch for challenger level AI researchers streaming live processes? Or videos showing the entire project flow (how they do data visualizations, mining, choosing models, tuning, etc) like top digital artists show the highlights or the entire speed-up of their painting processes? Here's a list all of my projects to get a general idea of my level and where I'm at: calculating the distance between hundreds of 42.000 feature objects (containing categorical, strings, numbers, hashes, booleans as variables) and then clustering. with some vector processing and a neural network implemented from scratch in C some models like ARIMA (together with linear regression) combining a FFT with a neural network for a 42d wave classification T-SNE to split dataset into 2d grids -> Kullback–Leibler on grids for distance -> DBSCAN/KMEANS for clustering genetic algorithms for hyperparameter optimizations and reinforcement learning (neuro evolution) DBSCAN -> Levenberg-Marquardt for polynomial coefficients-> neural network predicting the coefficients based on different parameters playing with instance segmentation and some algorithms to synchronize a color and a depth camera simulations/statistics/probabilities for video games a lot of visualizations and data mining for patterns As you can see there is no LLM/ Generative AI/ Computer Vision stuff, which I would like to get into. I'm also not 100% sure what else would be nice to learn in general. I know most of the basic procedures for training, balancing datasets, avoid overfit, computing error plots, comparing models, etc and I'm familiar with most of math (not insanely advanced) used in ML. I didn't read many papers, but holy ... most of them are so unreadable and filled with pompous nonsense that 99% of the effort is de-obfuscating the bs and reading for so long just to figure out how the input is encoded, what's the output, and what's the model. Where can I find good, readable, structured papers which are actually on point? I'm from Eastern Europe and most of my learning has been done by my self after high school, the education quality is close to zero in the universities here and I never had any mentors at the jobs I worked. There's no research in this country, and getting to work on these projects was insanely hard, some of them being done in my free time or for free just to get experience... Fortunately after a lot of hard work I got into FAANG, and I hope things will be better here. Most of what I've learned has been from very fragmented places on the internet, and now I'm looking for centralized places and communities of top quality content. TL;DR: sorry for the long rambling. had to order my thoughts and figure what i actually want: Looking for top tier AI researchers showcasing their work processes, places with clear papers/articles, tips for someone who's no longer a very beginner, and other communities like this.

[D] Here are 17 ways of making PyTorch training faster – what did I miss?

I've been collecting methods to accelerate training in PyTorch – here's what I've found so far. What did I miss? What did I get wrong? The methods – roughly sorted from largest to smallest expected speed-up – are: Consider using a different learning rate schedule. Use multiple workers and pinned memory in DataLoader. Max out the batch size. Use Automatic Mixed Precision (AMP). Consider using a different optimizer. Turn on cudNN benchmarking. Beware of frequently transferring data between CPUs and GPUs. Use gradient/activation checkpointing. Use gradient accumulation. Use DistributedDataParallel for multi-GPU training. Set gradients to None rather than 0. Use .as\_tensor rather than .tensor() Turn off debugging APIs if not needed. Use gradient clipping. Turn off bias before BatchNorm. Turn off gradient computation during validation. Use input and batch normalization. Consider using another learning rate schedule The learning rate (schedule) you choose has a large impact on the speed of convergence as well as the generalization performance of your model. Cyclical Learning Rates and the 1Cycle learning rate schedule are both methods introduced by Leslie N. Smith (here and here), and then popularised by fast.ai's Jeremy Howard and Sylvain Gugger (here and here). Essentially, the 1Cycle learning rate schedule looks something like this: &#x200B; https://preview.redd.it/sc37u5knmxa61.png?width=476&format=png&auto=webp&s=09b309b4dbd67eedb4ab5f86e03e0e83d7b072d1 Sylvain writes: \[1cycle consists of\]  two steps of equal lengths, one going from a lower learning rate to a higher one than go back to the minimum. The maximum should be the value picked with the Learning Rate Finder, and the lower one can be ten times lower. Then, the length of this cycle should be slightly less than the total number of epochs, and, in the last part of training, we should allow the learning rate to decrease more than the minimum, by several orders of magnitude. In the best case this schedule achieves a massive speed-up – what Smith calls Superconvergence – as compared to conventional learning rate schedules. Using the 1Cycle policy he needs \~10x fewer training iterations of a ResNet-56 on ImageNet to match the performance of the original paper, for instance). The schedule seems to perform robustly well across common architectures and optimizers. PyTorch implements both of these methods torch.optim.lrscheduler.CyclicLR and torch.optim.lrscheduler.OneCycleLR, see the documentation. One drawback of these schedulers is that they introduce a number of additional hyperparameters. This post and this repo, offer a nice overview and implementation of how good hyper-parameters can be found including the Learning Rate Finder mentioned above. Why does this work? It doesn't seem entirely clear but one possible explanation might be that regularly increasing the learning rate helps to traverse saddle points in the loss landscape more quickly. Use multiple workers and pinned memory in DataLoader When using torch.utils.data.DataLoader, set numworkers > 0, rather than the default value of 0, and pinmemory=True, rather than the default value of False. Details of this are explained here. Szymon Micacz achieves a 2x speed-up for a single training epoch by using four workers and pinned memory. A rule of thumb that people are using to choose the number of workers is to set it to four times the number of available GPUs with both a larger and smaller number of workers leading to a slow down. Note that increasing num\_workerswill increase your CPU memory consumption. Max out the batch size This is a somewhat contentious point. Generally, however, it seems like using the largest batch size your GPU memory permits will accelerate your training (see NVIDIA's Szymon Migacz, for instance). Note that you will also have to adjust other hyperparameters, such as the learning rate, if you modify the batch size. A rule of thumb here is to double the learning rate as you double the batch size. OpenAI has a nice empirical paper on the number of convergence steps needed for different batch sizes. Daniel Huynh runs some experiments with different batch sizes (also using the 1Cycle policy discussed above) where he achieves a 4x speed-up by going from batch size 64 to 512. One of the downsides of using large batch sizes, however, is that they might lead to solutions that generalize worse than those trained with smaller batches. Use Automatic Mixed Precision (AMP) The release of PyTorch 1.6 included a native implementation of Automatic Mixed Precision training to PyTorch. The main idea here is that certain operations can be run faster and without a loss of accuracy at semi-precision (FP16) rather than in the single-precision (FP32) used elsewhere. AMP, then, automatically decide which operation should be executed in which format. This allows both for faster training and a smaller memory footprint. In the best case, the usage of AMP would look something like this: import torch Creates once at the beginning of training scaler = torch.cuda.amp.GradScaler() for data, label in data_iter: optimizer.zero_grad() Casts operations to mixed precision with torch.cuda.amp.autocast(): loss = model(data) Scales the loss, and calls backward() to create scaled gradients scaler.scale(loss).backward() Unscales gradients and calls or skips optimizer.step() scaler.step(optimizer) Updates the scale for next iteration scaler.update() Benchmarking a number of common language and vision models on NVIDIA V100 GPUs, Huang and colleagues find that using AMP over regular FP32 training yields roughly 2x – but upto 5.5x – training speed-ups. Currently, only CUDA ops can be autocast in this way. See the documentation here for more details on this and other limitations. u/SVPERBlA points out that you can squeeze out some additional performance (\~ 20%) from AMP on NVIDIA Tensor Core GPUs if you convert your tensors to the Channels Last memory format. Refer to this section in the NVIDIA docs for an explanation of the speedup and more about NCHW versus NHWC tensor formats. Consider using another optimizer AdamW is Adam with weight decay (rather than L2-regularization) which was popularized by fast.ai and is now available natively in PyTorch as torch.optim.AdamW. AdamW seems to consistently outperform Adam in terms of both the error achieved and the training time. See this excellent blog post on why using weight decay instead of L2-regularization makes a difference for Adam. Both Adam and AdamW work well with the 1Cycle policy described above. There are also a few not-yet-native optimizers that have received a lot of attention recently, most notably LARS (pip installable implementation) and LAMB. NVIDA's APEX implements fused versions of a number of common optimizers such as Adam. This implementation avoid a number of passes to and from GPU memory as compared to the PyTorch implementation of Adam, yielding speed-ups in the range of 5%. Turn on cudNN benchmarking If your model architecture remains fixed and your input size stays constant, setting torch.backends.cudnn.benchmark = True might be beneficial (docs). This enables the cudNN autotuner which will benchmark a number of different ways of computing convolutions in cudNN and then use the fastest method from then on. For a rough reference on the type of speed-up you can expect from this, Szymon Migacz achieves a speed-up of 70% on a forward pass for a convolution and a 27% speed-up for a forward + backward pass of the same convolution. One caveat here is that this autotuning might become very slow if you max out the batch size as mentioned above. Beware of frequently transferring data between CPUs and GPUs Beware of frequently transferring tensors from a GPU to a CPU using tensor.cpu() and vice versa using tensor.cuda() as these are relatively expensive. The same applies for .item() and .numpy() – use .detach() instead. If you are creating a new tensor, you can also directly assign it to your GPU using the keyword argument device=torch.device('cuda:0'). If you do need to transfer data, using .to(non_blocking=True), might be useful as long as you don't have any synchronization points after the transfer. If you really have to, you might want to give Santosh Gupta's SpeedTorch a try, although it doesn't seem entirely clear when this actually does/doesn't provide speed-ups. Use gradient/activation checkpointing Quoting directly from the documentation: Checkpointing works by trading compute for memory. Rather than storing all intermediate activations of the entire computation graph for computing backward, the checkpointed part does not save intermediate activations, and instead recomputes them in backward pass. It can be applied on any part of a model. Specifically, in the forward pass, function will run in torch.no\grad() manner, i.e., not storing the intermediate activations. Instead, the forward pass saves the inputs tuple and the functionparameter. In the backwards pass, the saved inputs and function is retrieved, and the forward pass is computed on function again, now tracking the intermediate activations, and then the gradients are calculated using these activation values. So while this will might slightly increase your run time for a given batch size, you'll significantly reduce your memory footprint. This in turn will allow you to further increase the batch size you're using allowing for better GPU utilization. While checkpointing is implemented natively as torch.utils.checkpoint(docs), it does seem to take some thought and effort to implement properly. Priya Goyal has a good tutorial demonstrating some of the key aspects of checkpointing. Use gradient accumulation Another approach to increasing the batch size is to accumulate gradients across multiple .backward() passes before calling optimizer.step(). Following a post by Hugging Face's Thomas Wolf, gradient accumulation can be implemented as follows: model.zero_grad() Reset gradients tensors for i, (inputs, labels) in enumerate(training_set): predictions = model(inputs) Forward pass loss = loss_function(predictions, labels) Compute loss function loss = loss / accumulation_steps Normalize our loss (if averaged) loss.backward() Backward pass if (i+1) % accumulation_steps == 0: Wait for several backward steps optimizer.step() Now we can do an optimizer step model.zero_grad() Reset gradients tensors if (i+1) % evaluation_steps == 0: Evaluate the model when we... evaluate_model() ...have no gradients accumulate This method was developed mainly to circumvent GPU memory limitations and I'm not entirely clear on the trade-off between having additional .backward() loops. This discussion on the fastai forum seems to suggest that it can in fact accelerate training, so it's probably worth a try. Use Distributed Data Parallel for multi-GPU training Methods to accelerate distributed training probably warrant their own post but one simple one is to use torch.nn.DistributedDataParallel rather than torch.nn.DataParallel. By doing so, each GPU will be driven by a dedicated CPU core avoiding the GIL issues of DataParallel. In general, I can strongly recommend reading the documentation on distributed training. Set gradients to None rather than 0 Use .zerograd(settonone=True) rather than .zerograd(). Doing so will let the memory allocator handle the gradients rather than actively setting them to 0. This will lead to yield a modest speed-up as they say in the documentation, so don't expect any miracles. Watch out, doing this is not side-effect free! Check the docs for the details on this. Use .as_tensor() rather than .tensor() torch.tensor() always copies data. If you have a numpy array that you want to convert, use torch.astensor() or torch.fromnumpy() to avoid copying the data. Turn on debugging tools only when actually needed PyTorch offers a number of useful debugging tools like the autograd.profiler, autograd.grad\check, and autograd.anomaly\detection. Make sure to use them to better understand when needed but to also turn them off when you don't need them as they will slow down your training. Use gradient clipping Originally used to avoid exploding gradients in RNNs, there is both some empirical evidence as well as some theoretical support that clipping gradients (roughly speaking: gradient = min(gradient, threshold)) accelerates convergence. Hugging Face's Transformer implementation is a really clean example of how to use gradient clipping as well as some of the other methods such as AMP mentioned in this post. In PyTorch this can be done using torch.nn.utils.clipgradnorm(documentation). It's not entirely clear to me which models benefit how much from gradient clipping but it seems to be robustly useful for RNNs, Transformer-based and ResNets architectures and a range of different optimizers. Turn off bias before BatchNorm This is a very simple one: turn off the bias of layers before BatchNormalization layers. For a 2-D convolutional layer, this can be done by setting the bias keyword to False: torch.nn.Conv2d(..., bias=False, ...).  (Here's a reminder why this makes sense.) You will save some parameters, I would however expect the speed-up of this to be relatively small as compared to some of the other methods mentioned here. Turn off gradient computation during validation This one is straightforward: set torch.no_grad() during validation. Use input and batch normalization You're probably already doing this but you might want to double-check: Are you normalizing your input? Are you using batch-normalization? And here's a reminder of why you probably should. Bonus tip from the comments: Use JIT to fuse point-wise operations. If you have adjacent point-wise operations you can use PyTorch JIT to combine them into one FusionGroup which can then be launched on a single kernel rather than multiple kernels as would have been done per default. You'll also save some memory reads and writes. Szymon Migacz shows how you can use the @torch.jit.script decorator to fuse the operations in a GELU, for instance: @torch.jit.script def fused_gelu(x): return x 0.5 (1.0 + torch.erf(x / 1.41421)) In this case, fusing the operations leads to a 5x speed-up for the execution of fused_gelu as compared to the unfused version. See also this post for an example of how Torchscript can be used to accelerate an RNN. Hat tip to u/Patient_Atmosphere45 for the suggestion. Sources and additional resources Many of the tips listed above come from Szymon Migacz' talk and post in the PyTorch docs. PyTorch Lightning's William Falcon has two interesting posts with tips to speed-up training. PyTorch Lightning does already take care of some of the points above per-default. Thomas Wolf at Hugging Face has a number of interesting articles on accelerating deep learning – with a particular focus on language models. The same goes for Sylvain Gugger and Jeremy Howard: they have many interesting posts in particular on learning rates and AdamW. Thanks to Ben Hahn, Kevin Klein and Robin Vaaler for their feedback on a draft of this post! I've also put all of the above into this blog post.

Andrej Karpathy releases concise GPT implementation. Why has he bothered to do this: doesn't he work for OpenAI, at least indirectly? [D] [N]

It's nice to see a concise implementation of GPT, in pytorch, as it is true Hugging Face's Transformer's is excellent, but it is quite difficult to trace. They are trying to build it out constantly with loads of features, so you get lost. I'm wondering Andrej's reason for doing this? His wiki states he works for OpenAI and Tesla is at least affiliated with Openai. Also it's very far from computer vision domain, so why spend the time on an open source implementation and make some guesses on GPT-2/GPT-3. His implementation is easy to follow, which is nice , most reimplementations I see have bugs or are unecessary complex. I am surprised at how basic his trainer code is etc., that he pretty much uses the very standard stuff. Andrej also states 'A vanilla multi-head masked self-attention layer with a projection at the end. I believe I could have just used torch.nn.MultiheadAttention but their documentation is all but absent and code ugly so I don't trust it, rolling my own here.' I usually trust the torch team blindly to come up with a more efficient implementation than I ever could, as don't they stringently test their code, before releasing? so am also surprised by this.

[D] What is your honest experience with reinforcement learning?

In my personal experience, SOTA RL algorithms simply don't work. I've tried working with reinforcement learning for over 5 years. I remember when Alpha Go defeated the world famous Go player, Lee Sedol, and everybody thought RL would take the ML community by storm. Yet, outside of toy problems, I've personally never found a practical use-case of RL. What is your experience with it? Aside from Ad recommendation systems and RLHF, are there legitimate use-cases of RL? Or, was it all hype? Edit: I know a lot about AI. I built NexusTrade, an AI-Powered automated investing tool that lets non-technical users create, update, and deploy their trading strategies. I’m not an idiot nor a noob; RL is just ridiculously hard. Edit 2: Since my comments are being downvoted, here is a link to my article that better describes my position. It's not that I don't understand RL. I released my open-source code and wrote a paper on it. It's the fact that it's EXTREMELY difficult to understand. Other deep learning algorithms like CNNs (including ResNets), RNNs (including GRUs and LSTMs), Transformers, and GANs are not hard to understand. These algorithms work and have practical use-cases outside of the lab. Traditional SOTA RL algorithms like PPO, DDPG, and TD3 are just very hard. You need to do a bunch of research to even implement a toy problem. In contrast, the decision transformer is something anybody can implement, and it seems to match or surpass the SOTA. You don't need two networks battling each other. You don't have to go through hell to debug your network. It just naturally learns the best set of actions in an auto-regressive manner. I also didn't mean to come off as arrogant or imply that RL is not worth learning. I just haven't seen any real-world, practical use-cases of it. I simply wanted to start a discussion, not claim that I know everything. Edit 3: There's a shockingly number of people calling me an idiot for not fully understanding RL. You guys are wayyy too comfortable calling people you disagree with names. News-flash, not everybody has a PhD in ML. My undergraduate degree is in biology. I self-taught myself the high-level maths to understand ML. I'm very passionate about the field; I just have VERY disappointing experiences with RL. Funny enough, there are very few people refuting my actual points. To summarize: Lack of real-world applications Extremely complex and inaccessible to 99% of the population Much harder than traditional DL algorithms like CNNs, RNNs, and GANs Sample inefficiency and instability Difficult to debug Better alternatives, such as the Decision Transformer Are these not legitimate criticisms? Is the purpose of this sub not to have discussions related to Machine Learning? To the few commenters that aren't calling me an idiot...thank you! Remember, it costs you nothing to be nice! Edit 4: Lots of people seem to agree that RL is over-hyped. Unfortunately those comments are downvoted. To clear up some things: We've invested HEAVILY into reinforcement learning. All we got from this investment is a robot that can be super-human at (some) video games. AlphaFold did not use any reinforcement learning. SpaceX doesn't either. I concede that it can be useful for robotics, but still argue that it's use-cases outside the lab are extremely limited. If you're stumbling on this thread and curious about an RL alternative, check out the Decision Transformer. It can be used in any situation that a traditional RL algorithm can be used. Final Edit: To those who contributed more recently, thank you for the thoughtful discussion! From what I learned, model-based models like Dreamer and IRIS MIGHT have a future. But everybody who has actually used model-free models like DDPG unanimously agree that they suck and don’t work.

[D] Why can't you guys comment your fucking code?

Seriously. I spent the last few years doing web app development. Dug into DL a couple months ago. Supposedly, compared to the post-post-post-docs doing AI stuff, JavaScript developers should be inbred peasants. But every project these peasants release, even a fucking library that colorizes CLI output, has a catchy name, extensive docs, shitloads of comments, fuckton of tests, semantic versioning, changelog, and, oh my god, better variable names than ctxh or langhs or fuckyoufortryingto_understand. The concepts and ideas behind DL, GANs, LSTMs, CNNs, whatever – it's clear, it's simple, it's intuitive. The slog is to go through the jargon (that keeps changing beneath your feet - what's the point of using fancy words if you can't keep them consistent?), the unnecessary equations, trying to squeeze meaning from bullshit language used in papers, figuring out the super important steps, preprocessing, hyperparameters optimization that the authors, oops, failed to mention. Sorry for singling out, but look at this - what the fuck? If a developer anywhere else at Facebook would get this code for a review they would throw up. Do you intentionally try to obfuscate your papers? Is pseudo-code a fucking premium? Can you at least try to give some intuition before showering the reader with equations? How the fuck do you dare to release a paper without source code? Why the fuck do you never ever add comments to you code? When naming things, are you charged by the character? Do you get a bonus for acronyms? Do you realize that OpenAI having needed to release a "baseline" TRPO implementation is a fucking disgrace to your profession? Jesus christ, who decided to name a tensor concatenation function cat?

[R] Is it possible to implement generative ai successfully without relying on openAI

I would like to understand if anyone has implemented generative AI without using openAI and if so which open source you have used and how successful it has been so far We have enterprise level incident data, relevant documentation etc that users will search about and need to generate responses using generative ai. Is it possible to do this without relying on open AI at all

[D] The machine learning community has a toxicity problem

It is omnipresent! First of all, the peer-review process is broken. Every fourth NeurIPS submission is put on arXiv. There are DeepMind researchers publicly going after reviewers who are criticizing their ICLR submission. On top of that, papers by well-known institutes that were put on arXiv are accepted at top conferences, despite the reviewers agreeing on rejection. In contrast, vice versa, some papers with a majority of accepts are overruled by the AC. (I don't want to call any names, just have a look the openreview page of this year's ICRL). Secondly, there is a reproducibility crisis. Tuning hyperparameters on the test set seem to be the standard practice nowadays. Papers that do not beat the current state-of-the-art method have a zero chance of getting accepted at a good conference. As a result, hyperparameters get tuned and subtle tricks implemented to observe a gain in performance where there isn't any. Thirdly, there is a worshiping problem. Every paper with a Stanford or DeepMind affiliation gets praised like a breakthrough. For instance, BERT has seven times more citations than ULMfit. The Google affiliation gives so much credibility and visibility to a paper. At every ICML conference, there is a crowd of people in front of every DeepMind poster, regardless of the content of the work. The same story happened with the Zoom meetings at the virtual ICLR 2020. Moreover, NeurIPS 2020 had twice as many submissions as ICML, even though both are top-tier ML conferences. Why? Why is the name "neural" praised so much? Next, Bengio, Hinton, and LeCun are truly deep learning pioneers but calling them the "godfathers" of AI is insane. It has reached the level of a cult. Fourthly, the way Yann LeCun talked about biases and fairness topics was insensitive. However, the toxicity and backlash that he received are beyond any reasonable quantity. Getting rid of LeCun and silencing people won't solve any issue. Fifthly, machine learning, and computer science in general, have a huge diversity problem. At our CS faculty, only 30% of undergrads and 15% of the professors are women. Going on parental leave during a PhD or post-doc usually means the end of an academic career. However, this lack of diversity is often abused as an excuse to shield certain people from any form of criticism. Reducing every negative comment in a scientific discussion to race and gender creates a toxic environment. People are becoming afraid to engage in fear of being called a racist or sexist, which in turn reinforces the diversity problem. Sixthly, moral and ethics are set arbitrarily. The U.S. domestic politics dominate every discussion. At this very moment, thousands of Uyghurs are put into concentration camps based on computer vision algorithms invented by this community, and nobody seems even remotely to care. Adding a "broader impact" section at the end of every people will not make this stop. There are huge shitstorms because a researcher wasn't mentioned in an article. Meanwhile, the 1-billion+ people continent of Africa is virtually excluded from any meaningful ML discussion (besides a few Indaba workshops). Seventhly, there is a cut-throat publish-or-perish mentality. If you don't publish 5+ NeurIPS/ICML papers per year, you are a looser. Research groups have become so large that the PI does not even know the name of every PhD student anymore. Certain people submit 50+ papers per year to NeurIPS. The sole purpose of writing a paper has become to having one more NeurIPS paper in your CV. Quality is secondary; passing the peer-preview stage has become the primary objective. Finally, discussions have become disrespectful. Schmidhuber calls Hinton a thief, Gebru calls LeCun a white supremacist, Anandkumar calls Marcus a sexist, everybody is under attack, but nothing is improved. Albert Einstein was opposing the theory of quantum mechanics. Can we please stop demonizing those who do not share our exact views. We are allowed to disagree without going for the jugular. The moment we start silencing people because of their opinion is the moment scientific and societal progress dies. Best intentions, Yusuf

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

5-Day Applied Rationality Workshop for Machine Learning Students & Researchers

The Center for Applied Rationality is a Berkeley-based nonprofit that runs immersive workshops for entrepreneurs, researchers, students, and other ambitious, analytical, practically-minded people. The practice of “applied rationality”, which the workshops aim towards, involves noticing what cognitive algorithms you seem to be running, checking whether those algorithms seem to be helping you form accurate beliefs and achieve your goals, and looking for ways to improve them. A typical 4-day CFAR workshop costs $3900 to attend, but thanks to a generous grant from the Future of Life Institute this fall we will be running a free five-day workshop for students and researchers in the fields of machine learning and artificial intelligence. All costs are covered by this grant, including room, board, and flights. The workshop will take place this Aug 30 through Sep 4 in the San Francisco Bay Area and will include: 2 days focused on learning models and skills, such as how habits develop and how to redesign your habits. 2 days focused on practicing skills and applying them to whichever areas of your life you would like to make improvements on, such as how to make faster progress on projects or how to have more productive collaborations with colleagues. 1 day (special to this workshop) focused on discussion of the long-term impact of artificial intelligence, and on what reasoning habits — if spread across the relevant research communities — may increase the probability of positive long-term AI outcomes. Go here to read more or to apply, or ask questions here.

Interview with Juergen Schmidhuber, renowned ‘Father Of Modern AI’, says his life’s work won't lead to dystopia.

Schmidhuber interview expressing his views on the future of AI and AGI. Original source. I think the interview is of interest to r/MachineLearning, and presents an alternate view, compared to other influential leaders in AI. Juergen Schmidhuber, Renowned 'Father Of Modern AI,' Says His Life’s Work Won't Lead To Dystopia May 23, 2023. Contributed by Hessie Jones. Amid the growing concern about the impact of more advanced artificial intelligence (AI) technologies on society, there are many in the technology community who fear the implications of the advancements in Generative AI if they go unchecked. Dr. Juergen Schmidhuber, a renowned scientist, artificial intelligence researcher and widely regarded as one of the pioneers in the field, is more optimistic. He declares that many of those who suddenly warn against the dangers of AI are just seeking publicity, exploiting the media’s obsession with killer robots which has attracted more attention than “good AI” for healthcare etc. The potential to revolutionize various industries and improve our lives is clear, as are the equal dangers if bad actors leverage the technology for personal gain. Are we headed towards a dystopian future, or is there reason to be optimistic? I had a chance to sit down with Dr. Juergen Schmidhuber to understand his perspective on this seemingly fast-moving AI-train that will leap us into the future. As a teenager in the 1970s, Juergen Schmidhuber became fascinated with the idea of creating intelligent machines that could learn and improve on their own, becoming smarter than himself within his lifetime. This would ultimately lead to his groundbreaking work in the field of deep learning. In the 1980s, he studied computer science at the Technical University of Munich (TUM), where he earned his diploma in 1987. His thesis was on the ultimate self-improving machines that, not only, learn through some pre-wired human-designed learning algorithm, but also learn and improve the learning algorithm itself. Decades later, this became a hot topic. He also received his Ph.D. at TUM in 1991 for work that laid some of the foundations of modern AI. Schmidhuber is best known for his contributions to the development of recurrent neural networks (RNNs), the most powerful type of artificial neural network that can process sequential data such as speech and natural language. With his students Sepp Hochreiter, Felix Gers, Alex Graves, Daan Wierstra, and others, he published architectures and training algorithms for the long short-term memory (LSTM), a type of RNN that is widely used in natural language processing, speech recognition, video games, robotics, and other applications. LSTM has become the most cited neural network of the 20th century, and Business Week called it "arguably the most commercial AI achievement." Throughout his career, Schmidhuber has received various awards and accolades for his groundbreaking work. In 2013, he was awarded the Helmholtz Prize, which recognizes significant contributions to the field of machine learning. In 2016, he was awarded the IEEE Neural Network Pioneer Award for "pioneering contributions to deep learning and neural networks." The media have often called him the “father of modern AI,” because the most cited neural networks all build on his lab’s work. He is quick to point out, however, that AI history goes back centuries. Despite his many accomplishments, at the age of 60, he feels mounting time pressure towards building an Artificial General Intelligence within his lifetime and remains committed to pushing the boundaries of AI research and development. He is currently director of the KAUST AI Initiative, scientific director of the Swiss AI Lab IDSIA, and co-founder and chief scientist of AI company NNAISENSE, whose motto is "AI∀" which is a math-inspired way of saying "AI For All." He continues to work on cutting-edge AI technologies and applications to improve human health and extend human lives and make lives easier for everyone. The following interview has been edited for clarity. Jones: Thank you Juergen for joining me. You have signed letters warning about AI weapons. But you didn't sign the recent publication, "Pause Gigantic AI Experiments: An Open Letter"? Is there a reason? Schmidhuber: Thank you Hessie. Glad to speak with you. I have realized that many of those who warn in public against the dangers of AI are just seeking publicity. I don't think the latest letter will have any significant impact because many AI researchers, companies, and governments will ignore it completely. The proposal frequently uses the word "we" and refers to "us," the humans. But as I have pointed out many times in the past, there is no "we" that everyone can identify with. Ask 10 different people, and you will hear 10 different opinions about what is "good." Some of those opinions will be completely incompatible with each other. Don't forget the enormous amount of conflict between the many people. The letter also says, "If such a pause cannot be quickly put in place, governments should intervene and impose a moratorium." The problem is that different governments have ALSO different opinions about what is good for them and for others. Great Power A will say, if we don't do it, Great Power B will, perhaps secretly, and gain an advantage over us. The same is true for Great Powers C and D. Jones: Everyone acknowledges this fear surrounding current generative AI technology. Moreover, the existential threat of this technology has been publicly acknowledged by Sam Altman, CEO of OpenAI himself, calling for AI regulation. From your perspective, is there an existential threat? Schmidhuber: It is true that AI can be weaponized, and I have no doubt that there will be all kinds of AI arms races, but AI does not introduce a new quality of existential threat. The threat coming from AI weapons seems to pale in comparison to the much older threat from nuclear hydrogen bombs that don’t need AI at all. We should be much more afraid of half-century-old tech in the form of H-bomb rockets. The Tsar Bomba of 1961 had almost 15 times more destructive power than all weapons of WW-II combined. Despite the dramatic nuclear disarmament since the 1980s, there are still more than enough nuclear warheads to wipe out human civilization within two hours, without any AI I’m much more worried about that old existential threat than the rather harmless AI weapons. Jones: I realize that while you compare AI to the threat of nuclear bombs, there is a current danger that a current technology can be put in the hands of humans and enable them to “eventually” exact further harms to individuals of group in a very precise way, like targeted drone attacks. You are giving people a toolset that they've never had before, enabling bad actors, as some have pointed out, to be able to do a lot more than previously because they didn't have this technology. Schmidhuber: Now, all that sounds horrible in principle, but our existing laws are sufficient to deal with these new types of weapons enabled by AI. If you kill someone with a gun, you will go to jail. Same if you kill someone with one of these drones. Law enforcement will get better at understanding new threats and new weapons and will respond with better technology to combat these threats. Enabling drones to target persons from a distance in a way that requires some tracking and some intelligence to perform, which has traditionally been performed by skilled humans, to me, it seems is just an improved version of a traditional weapon, like a gun, which is, you know, a little bit smarter than the old guns. But, in principle, all of that is not a new development. For many centuries, we have had the evolution of better weaponry and deadlier poisons and so on, and law enforcement has evolved their policies to react to these threats over time. So, it's not that we suddenly have a new quality of existential threat and it's much more worrisome than what we have had for about six decades. A large nuclear warhead doesn’t need fancy face recognition to kill an individual. No, it simply wipes out an entire city with ten million inhabitants. Jones: The existential threat that’s implied is the extent to which humans have control over this technology. We see some early cases of opportunism which, as you say, tends to get more media attention than positive breakthroughs. But you’re implying that this will all balance out? Schmidhuber: Historically, we have a long tradition of technological breakthroughs that led to advancements in weapons for the purpose of defense but also for protection. From sticks, to rocks, to axes to gunpowder to cannons to rockets… and now to drones… this has had a drastic influence on human history but what has been consistent throughout history is that those who are using technology to achieve their own ends are themselves, facing the same technology because the opposing side is learning to use it against them. And that's what has been repeated in thousands of years of human history and it will continue. I don't see the new AI arms race as something that is remotely as existential a threat as the good old nuclear warheads. You said something important, in that some people prefer to talk about the downsides rather than the benefits of this technology, but that's misleading, because 95% of all AI research and AI development is about making people happier and advancing human life and health. Jones: Let’s touch on some of those beneficial advances in AI research that have been able to radically change present day methods and achieve breakthroughs. Schmidhuber: All right! For example, eleven years ago, our team with my postdoc Dan Ciresan was the first to win a medical imaging competition through deep learning. We analyzed female breast cells with the objective to determine harmless cells vs. those in the pre-cancer stage. Typically, a trained oncologist needs a long time to make these determinations. Our team, who knew nothing about cancer, were able to train an artificial neural network, which was totally dumb in the beginning, on lots of this kind of data. It was able to outperform all the other methods. Today, this is being used not only for breast cancer, but also for radiology and detecting plaque in arteries, and many other things. Some of the neural networks that we have developed in the last 3 decades are now prevalent across thousands of healthcare applications, detecting Diabetes and Covid-19 and what not. This will eventually permeate across all healthcare. The good consequences of this type of AI are much more important than the click-bait new ways of conducting crimes with AI. Jones: Adoption is a product of reinforced outcomes. The massive scale of adoption either leads us to believe that people have been led astray, or conversely, technology is having a positive effect on people’s lives. Schmidhuber: The latter is the likely case. There's intense commercial pressure towards good AI rather than bad AI because companies want to sell you something, and you are going to buy only stuff you think is going to be good for you. So already just through this simple, commercial pressure, you have a tremendous bias towards good AI rather than bad AI. However, doomsday scenarios like in Schwarzenegger movies grab more attention than documentaries on AI that improve people’s lives. Jones: I would argue that people are drawn to good stories – narratives that contain an adversary and struggle, but in the end, have happy endings. And this is consistent with your comment on human nature and how history, despite its tendency for violence and destruction of humanity, somehow tends to correct itself. Let’s take the example of a technology, which you are aware – GANs – General Adversarial Networks, which today has been used in applications for fake news and disinformation. In actuality, the purpose in the invention of GANs was far from what it is used for today. Schmidhuber: Yes, the name GANs was created in 2014 but we had the basic principle already in the early 1990s. More than 30 years ago, I called it artificial curiosity. It's a very simple way of injecting creativity into a little two network system. This creative AI is not just trying to slavishly imitate humans. Rather, it’s inventing its own goals. Let me explain: You have two networks. One network is producing outputs that could be anything, any action. Then the second network is looking at these actions and it’s trying to predict the consequences of these actions. An action could move a robot, then something happens, and the other network is just trying to predict what will happen. Now we can implement artificial curiosity by reducing the prediction error of the second network, which, at the same time, is the reward of the first network. The first network wants to maximize its reward and so it will invent actions that will lead to situations that will surprise the second network, which it has not yet learned to predict well. In the case where the outputs are fake images, the first network will try to generate images that are good enough to fool the second network, which will attempt to predict the reaction of the environment: fake or real image, and it will try to become better at it. The first network will continue to also improve at generating images whose type the second network will not be able to predict. So, they fight each other. The 2nd network will continue to reduce its prediction error, while the 1st network will attempt to maximize it. Through this zero-sum game the first network gets better and better at producing these convincing fake outputs which look almost realistic. So, once you have an interesting set of images by Vincent Van Gogh, you can generate new images that leverage his style, without the original artist having ever produced the artwork himself. Jones: I see how the Van Gogh example can be applied in an education setting and there are countless examples of artists mimicking styles from famous painters but image generation from this instance that can happen within seconds is quite another feat. And you know this is how GANs has been used. What’s more prevalent today is a socialized enablement of generating images or information to intentionally fool people. It also surfaces new harms that deal with the threat to intellectual property and copyright, where laws have yet to account for. And from your perspective this was not the intention when the model was conceived. What was your motivation in your early conception of what is now GANs? Schmidhuber: My old motivation for GANs was actually very important and it was not to create deepfakes or fake news but to enable AIs to be curious and invent their own goals, to make them explore their environment and make them creative. Suppose you have a robot that executes one action, then something happens, then it executes another action, and so on, because it wants to achieve certain goals in the environment. For example, when the battery is low, this will trigger “pain” through hunger sensors, so it wants to go to the charging station, without running into obstacles, which will trigger other pain sensors. It will seek to minimize pain (encoded through numbers). Now the robot has a friend, the second network, which is a world model ––it’s a prediction machine that learns to predict the consequences of the robot’s actions. Once the robot has a good model of the world, it can use it for planning. It can be used as a simulation of the real world. And then it can determine what is a good action sequence. If the robot imagines this sequence of actions, the model will predict a lot of pain, which it wants to avoid. If it plays this alternative action sequence in its mental model of the world, then it will predict a rewarding situation where it’s going to sit on the charging station and its battery is going to load again. So, it'll prefer to execute the latter action sequence. In the beginning, however, the model of the world knows nothing, so how can we motivate the first network to generate experiments that lead to data that helps the world model learn something it didn’t already know? That’s what artificial curiosity is about. The dueling two network systems effectively explore uncharted environments by creating experiments so that over time the curious AI gets a better sense of how the environment works. This can be applied to all kinds of environments, and has medical applications. Jones: Let’s talk about the future. You have said, “Traditional humans won’t play a significant role in spreading intelligence across the universe.” Schmidhuber: Let’s first conceptually separate two types of AIs. The first type of AI are tools directed by humans. They are trained to do specific things like accurately detect diabetes or heart disease and prevent attacks before they happen. In these cases, the goal is coming from the human. More interesting AIs are setting their own goals. They are inventing their own experiments and learning from them. Their horizons expand and eventually they become more and more general problem solvers in the real world. They are not controlled by their parents, but much of what they learn is through self-invented experiments. A robot, for example, is rotating a toy, and as it is doing this, the video coming in through the camera eyes, changes over time and it begins to learn how this video changes and learns how the 3D nature of the toy generates certain videos if you rotate it a certain way, and eventually, how gravity works, and how the physics of the world works. Like a little scientist! And I have predicted for decades that future scaled-up versions of such AI scientists will want to further expand their horizons, and eventually go where most of the physical resources are, to build more and bigger AIs. And of course, almost all of these resources are far away from earth out there in space, which is hostile to humans but friendly to appropriately designed AI-controlled robots and self-replicating robot factories. So here we are not talking any longer about our tiny biosphere; no, we are talking about the much bigger rest of the universe. Within a few tens of billions of years, curious self-improving AIs will colonize the visible cosmos in a way that’s infeasible for humans. Those who don’t won’t have an impact. Sounds like science fiction, but since the 1970s I have been unable to see a plausible alternative to this scenario, except for a global catastrophe such as an all-out nuclear war that stops this development before it takes off. Jones: How long have these AIs, which can set their own goals — how long have they existed? To what extent can they be independent of human interaction? Schmidhuber: Neural networks like that have existed for over 30 years. My first simple adversarial neural network system of this kind is the one from 1990 described above. You don’t need a teacher there; it's just a little agent running around in the world and trying to invent new experiments that surprise its own prediction machine. Once it has figured out certain parts of the world, the agent will become bored and will move on to more exciting experiments. The simple 1990 systems I mentioned have certain limitations, but in the past three decades, we have also built more sophisticated systems that are setting their own goals and such systems I think will be essential for achieving true intelligence. If you are only imitating humans, you will never go beyond them. So, you really must give AIs the freedom to explore previously unexplored regions of the world in a way that no human is really predefining. Jones: Where is this being done today? Schmidhuber: Variants of neural network-based artificial curiosity are used today for agents that learn to play video games in a human-competitive way. We have also started to use them for automatic design of experiments in fields such as materials science. I bet many other fields will be affected by it: chemistry, biology, drug design, you name it. However, at least for now, these artificial scientists, as I like to call them, cannot yet compete with human scientists. I don’t think it’s going to stay this way but, at the moment, it’s still the case. Sure, AI has made a lot of progress. Since 1997, there have been superhuman chess players, and since 2011, through the DanNet of my team, there have been superhuman visual pattern recognizers. But there are other things where humans, at the moment at least, are much better, in particular, science itself. In the lab we have many first examples of self-directed artificial scientists, but they are not yet convincing enough to appear on the radar screen of the public space, which is currently much more fascinated with simpler systems that just imitate humans and write texts based on previously seen human-written documents. Jones: You speak of these numerous instances dating back 30 years of these lab experiments where these self-driven agents are deciding and learning and moving on once they’ve learned. And I assume that that rate of learning becomes even faster over time. What kind of timeframe are we talking about when this eventually is taken outside of the lab and embedded into society? Schmidhuber: This could still take months or even years :-) Anyway, in the not-too-distant future, we will probably see artificial scientists who are good at devising experiments that allow them to discover new, previously unknown physical laws. As always, we are going to profit from the old trend that has held at least since 1941: every decade compute is getting 100 times cheaper. Jones: How does this trend affect modern AI such as ChatGPT? Schmidhuber: Perhaps you know that all the recent famous AI applications such as ChatGPT and similar models are largely based on principles of artificial neural networks invented in the previous millennium. The main reason why they works so well now is the incredible acceleration of compute per dollar. ChatGPT is driven by a neural network called “Transformer” described in 2017 by Google. I am happy about that because a quarter century earlier in 1991 I had a particular Transformer variant which is now called the “Transformer with linearized self-attention”. Back then, not much could be done with it, because the compute cost was a million times higher than today. But today, one can train such models on half the internet and achieve much more interesting results. Jones: And for how long will this acceleration continue? Schmidhuber: There's no reason to believe that in the next 30 years, we won't have another factor of 1 million and that's going to be really significant. In the near future, for the first time we will have many not-so expensive devices that can compute as much as a human brain. The physical limits of computation, however, are much further out so even if the trend of a factor of 100 every decade continues, the physical limits (of 1051 elementary instructions per second and kilogram of matter) won’t be hit until, say, the mid-next century. Even in our current century, however, we’ll probably have many machines that compute more than all 10 billion human brains collectively and you can imagine, everything will change then! Jones: That is the big question. Is everything going to change? If so, what do you say to the next generation of leaders, currently coming out of college and university. So much of this change is already impacting how they study, how they will work, or how the future of work and livelihood is defined. What is their purpose and how do we change our systems so they will adapt to this new version of intelligence? Schmidhuber: For decades, people have asked me questions like that, because you know what I'm saying now, I have basically said since the 1970s, it’s just that today, people are paying more attention because, back then, they thought this was science fiction. They didn't think that I would ever come close to achieving my crazy life goal of building a machine that learns to become smarter than myself such that I can retire. But now many have changed their minds and think it's conceivable. And now I have two daughters, 23 and 25. People ask me: what do I tell them? They know that Daddy always said, “It seems likely that within your lifetimes, you will have new types of intelligence that are probably going to be superior in many ways, and probably all kinds of interesting ways.” How should they prepare for that? And I kept telling them the obvious: Learn how to learn new things! It's not like in the previous millennium where within 20 years someone learned to be a useful member of society, and then took a job for 40 years and performed in this job until she received her pension. Now things are changing much faster and we must learn continuously just to keep up. I also told my girls that no matter how smart AIs are going to get, learn at least the basics of math and physics, because that’s the essence of our universe, and anybody who understands this will have an advantage, and learn all kinds of new things more easily. I also told them that social skills will remain important, because most future jobs for humans will continue to involve interactions with other humans, but I couldn’t teach them anything about that; they know much more about social skills than I do. You touched on the big philosophical question about people’s purpose. Can this be answered without answering the even grander question: What’s the purpose of the entire universe? We don’t know. But what’s happening right now might be connected to the unknown answer. Don’t think of humans as the crown of creation. Instead view human civilization as part of a much grander scheme, an important step (but not the last one) on the path of the universe from very simple initial conditions towards more and more unfathomable complexity. Now it seems ready to take its next step, a step comparable to the invention of life itself over 3.5 billion years ago. Alas, don’t worry, in the end, all will be good! Jones: Let’s get back to this transformation happening right now with OpenAI. There are many questioning the efficacy and accuracy of ChatGPT, and are concerned its release has been premature. In light of the rampant adoption, educators have banned its use over concerns of plagiarism and how it stifles individual development. Should large language models like ChatGPT be used in school? Schmidhuber: When the calculator was first introduced, instructors forbade students from using it in school. Today, the consensus is that kids should learn the basic methods of arithmetic, but they should also learn to use the “artificial multipliers” aka calculators, even in exams, because laziness and efficiency is a hallmark of intelligence. Any intelligent being wants to minimize its efforts to achieve things. And that's the reason why we have tools, and why our kids are learning to use these tools. The first stone tools were invented maybe 3.5 million years ago; tools just have become more sophisticated over time. In fact, humans have changed in response to the properties of their tools. Our anatomical evolution was shaped by tools such as spears and fire. So, it's going to continue this way. And there is no permanent way of preventing large language models from being used in school. Jones: And when our children, your children graduate, what does their future work look like? Schmidhuber: A single human trying to predict details of how 10 billion people and their machines will evolve in the future is like a single neuron in my brain trying to predict what the entire brain and its tens of billions of neurons will do next year. 40 years ago, before the WWW was created at CERN in Switzerland, who would have predicted all those young people making money as YouTube video bloggers? Nevertheless, let’s make a few limited job-related observations. For a long time, people have thought that desktop jobs may require more intelligence than skills trade or handicraft professions. But now, it turns out that it's much easier to replace certain aspects of desktop jobs than replacing a carpenter, for example. Because everything that works well in AI is happening behind the screen currently, but not so much in the physical world. There are now artificial systems that can read lots of documents and then make really nice summaries of these documents. That is a desktop job. Or you give them a description of an illustration that you want to have for your article and pretty good illustrations are being generated that may need some minimal fine-tuning. But you know, all these desktop jobs are much easier to facilitate than the real tough jobs in the physical world. And it's interesting that the things people thought required intelligence, like playing chess, or writing or summarizing documents, are much easier for machines than they thought. But for things like playing football or soccer, there is no physical robot that can remotely compete with the abilities of a little boy with these skills. So, AI in the physical world, interestingly, is much harder than AI behind the screen in virtual worlds. And it's really exciting, in my opinion, to see that jobs such as plumbers are much more challenging than playing chess or writing another tabloid story. Jones: The way data has been collected in these large language models does not guarantee personal information has not been excluded. Current consent laws already are outdated when it comes to these large language models (LLM). The concern, rightly so, is increasing surveillance and loss of privacy. What is your view on this? Schmidhuber: As I have indicated earlier: are surveillance and loss of privacy inevitable consequences of increasingly complex societies? Super-organisms such as cities and states and companies consist of numerous people, just like people consist of numerous cells. These cells enjoy little privacy. They are constantly monitored by specialized "police cells" and "border guard cells": Are you a cancer cell? Are you an external intruder, a pathogen? Individual cells sacrifice their freedom for the benefits of being part of a multicellular organism. Similarly, for super-organisms such as nations. Over 5000 years ago, writing enabled recorded history and thus became its inaugural and most important invention. Its initial purpose, however, was to facilitate surveillance, to track citizens and their tax payments. The more complex a super-organism, the more comprehensive its collection of information about its constituents. 200 years ago, at least, the parish priest in each village knew everything about all the village people, even about those who did not confess, because they appeared in the confessions of others. Also, everyone soon knew about the stranger who had entered the village, because some occasionally peered out of the window, and what they saw got around. Such control mechanisms were temporarily lost through anonymization in rapidly growing cities but are now returning with the help of new surveillance devices such as smartphones as part of digital nervous systems that tell companies and governments a lot about billions of users. Cameras and drones etc. are becoming increasingly tinier and more ubiquitous. More effective recognition of faces and other detection technology are becoming cheaper and cheaper, and many will use it to identify others anywhere on earth; the big wide world will not offer any more privacy than the local village. Is this good or bad? Some nations may find it easier than others to justify more complex kinds of super-organisms at the expense of the privacy rights of their constituents. Jones: So, there is no way to stop or change this process of collection, or how it continuously informs decisions over time? How do you see governance and rules responding to this, especially amid Italy’s ban on ChatGPT following suspected user data breach and the more recent news about the Meta’s record $1.3billion fine in the company’s handling of user information? Schmidhuber: Data collection has benefits and drawbacks, such as the loss of privacy. How to balance those? I have argued for addressing this through data ownership in data markets. If it is true that data is the new oil, then it should have a price, just like oil. At the moment, the major surveillance platforms such as Meta do not offer users any money for their data and the transitive loss of privacy. In the future, however, we will likely see attempts at creating efficient data markets to figure out the data's true financial value through the interplay between supply and demand. Even some of the sensitive medical data should not be priced by governmental regulators but by patients (and healthy persons) who own it and who may sell or license parts thereof as micro-entrepreneurs in a healthcare data market. Following a previous interview, I gave for one of the largest re-insurance companies , let's look at the different participants in such a data market: patients, hospitals, data companies. (1) Patients with a rare form of cancer can offer more valuable data than patients with a very common form of cancer. (2) Hospitals and their machines are needed to extract the data, e.g., through magnet spin tomography, radiology, evaluations through human doctors, and so on. (3) Companies such as Siemens, Google or IBM would like to buy annotated data to make better artificial neural networks that learn to predict pathologies and diseases and the consequences of therapies. Now the market’s invisible hand will decide about the data’s price through the interplay between demand and supply. On the demand side, you will have several companies offering something for the data, maybe through an app on the smartphone (a bit like a stock market app). On the supply side, each patient in this market should be able to profit from high prices for rare valuable types of data. Likewise, competing data extractors such as hospitals will profit from gaining recognition and trust for extracting data well at a reasonable price. The market will make the whole system efficient through incentives for all who are doing a good job. Soon there will be a flourishing ecosystem of commercial data market advisors and what not, just like the ecosystem surrounding the traditional stock market. The value of the data won’t be determined by governments or ethics committees, but by those who own the data and decide by themselves which parts thereof they want to license to others under certain conditions. At first glance, a market-based system seems to be detrimental to the interest of certain monopolistic companies, as they would have to pay for the data - some would prefer free data and keep their monopoly. However, since every healthy and sick person in the market would suddenly have an incentive to collect and share their data under self-chosen anonymity conditions, there will soon be many more useful data to evaluate all kinds of treatments. On average, people will live longer and healthier, and many companies and the entire healthcare system will benefit. Jones: Finally, what is your view on open source versus the private companies like Google and OpenAI? Is there a danger to supporting these private companies’ large language models versus trying to keep these models open source and transparent, very much like what LAION is doing? Schmidhuber: I signed this open letter by LAION because I strongly favor the open-source movement. And I think it's also something that is going to challenge whatever big tech dominance there might be at the moment. Sure, the best models today are run by big companies with huge budgets for computers, but the exciting fact is that open-source models are not so far behind, some people say maybe six to eight months only. Of course, the private company models are all based on stuff that was created in academia, often in little labs without so much funding, which publish without patenting their results and open source their code and others take it and improved it. Big tech has profited tremendously from academia; their main achievement being that they have scaled up everything greatly, sometimes even failing to credit the original inventors. So, it's very interesting to see that as soon as some big company comes up with a new scaled-up model, lots of students out there are competing, or collaborating, with each other, trying to come up with equal or better performance on smaller networks and smaller machines. And since they are open sourcing, the next guy can have another great idea to improve it, so now there’s tremendous competition also for the big companies. Because of that, and since AI is still getting exponentially cheaper all the time, I don't believe that big tech companies will dominate in the long run. They find it very hard to compete with the enormous open-source movement. As long as you can encourage the open-source community, I think you shouldn't worry too much. Now, of course, you might say if everything is open source, then the bad actors also will more easily have access to these AI tools. And there's truth to that. But as always since the invention of controlled fire, it was good that knowledge about how technology works quickly became public such that everybody could use it. And then, against any bad actor, there's almost immediately a counter actor trying to nullify his efforts. You see, I still believe in our old motto "AI∀" or "AI For All." Jones: Thank you, Juergen for sharing your perspective on this amazing time in history. It’s clear that with new technology, the enormous potential can be matched by disparate and troubling risks which we’ve yet to solve, and even those we have yet to identify. If we are to dispel the fear of a sentient system for which we have no control, humans, alone need to take steps for more responsible development and collaboration to ensure AI technology is used to ultimately benefit society. Humanity will be judged by what we do next.

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!

Hi there, we at Skynet Today produce a weekly newsletter summarizing each week's major AI news, which seems like it'd be of interest to this subreddit. Here's what's in our latest one: Facebook’s AI for detecting hate speech is facing its biggest challenge yet Facebook has made significant progress recently to proactively take down content that violate its community standards. For example, in the second quarter of 2020, Facebook took down 104.6 million pieces of content. While reviews are typically performed by a vast workforce of human moderators, AI-powered tools have enabled Facebook to do this work at a greater scale for textual content. However, there’s a long way to go for these systems to match or exceed the capabilities of human moderators. This is because a large proportion of hate speech and misinformation is in the form of images and memes, and reasoning about the context and language-image interplay is an extremely difficult challenge for AI. Given Facebook’s scale and the speed at which some use it to spread hate, incite violence, and share lies with millions, Facebook will have to keep running to catch up. AI Slays Top F-16 Pilot In DARPA Dogfight Simulation The Defense Advanced Research Project Agency (DARPA) recently hosted a simulated F16 dogfight competition, with different AI bots competing with each other as well as with human pilots. The top AI bot was able to beat a human pilot 5-0 in the simulated contest. DARPA started this program “as a risk-reduction effort \[…\] to flesh out how human and machine pilots share operational control of a fighter jet to maximize its chances of mission success.” Competition runners are broadly optimistic about the demonstration of AI capabilities, even if they are not close to being deployed on a real aircraft. Of concern, the program had little discussion on the ethics of AI military applications, especially with the lethal autonomous weapon systems being considered. News Advances & Business Microsoft, Energy Dept. to Develop Disaster-Response AI Tools \- The U.S. Department of Energy and Microsoft Corp. on Tuesday announced a partnership to develop artificial-intelligence tools aimed at helping first-responders better react to fast-changing natural events, such as floods and wildfires. Coronavirus: Robot CERi is a bilingual Covid-19 expert \- Ceri is bilingual, clued-up on coronavirus and can tell what mood you are in. Ceri also happens to be a robot. Moscow DOH uses AI platform to detect lung cancer symptoms \- Moscow’s department of health is using an artificial intelligence (AI) platform to detect symptoms of lung cancer in CT scans, as part of a project to implement AI technology for radiology. Scientists develop artificial intelligence system for high precision recognition of hand gestures \- The recognition of human hand gestures by AI systems has been a valuable development over the last decade and has been adopted in high-precision surgical robots, health monitoring equipment and in gaming systems. Forget credit cards - now you can pay with your face. Creepy or cool? \- A new way to pay has arrived in Los Angeles: your face. Concerns & Hype The dystopian tech that companies are selling to help schools reopen sooner \- This fall, AI could be watching students social distance and checking their masks. Thousands of schools nationwide will not be reopening this fall. NYPD Used Facial Recognition Technology In Siege Of Black Lives Matter Activist’s Apartment \- The NYPD deployed facial recognition technology in its hunt for a prominent Black Lives Matter activist, whose home was besieged by dozens of officers and police dogs last week, a spokesperson confirmed to Gothamist. Machines can spot mental health issues - if you hand over your personal data \- Digital diagnosis could transform psychiatry by mining your most intimate data for clues. But is the privacy cost worth it? Supporting Black Artists Who Are Examining AI \- Technology has a complicated relationship with racial justice. Smartphones, internet platforms, and other digital tools can be used to document and expose racism. But digital tools can also fuel racism: smart doorbells surveil Black individuals. A-level and GCSE results in England to be based on teacher assessments in U-turn \- All A-level and GCSE results in England will be based on grades assesed by teachers instead of algorithms. Analysis & Policy GPT-3 and The Question of Automation \- Automation is not an all or nothing proposition. An AI model’s automation capability is highly conjoined with the task and application it is used in. An A.I. Movie Service Could One Day Serve You a New Custom Film Every Time \- How long will it be until an A.I. can make an actual feature film on demand? Fairness, evidence, and predictive equality \- How the causal fairness principle relates to predictive equality How robotics and automation could create new jobs in the new normal \- Depending on who you ask, AI and automation will either destroy jobs or create new ones. In reality, a greater push toward automation will probably both kill and create jobs - human workers will become redundant in certain spheres, sure, but many new roles will likely crop up. Expert Opinions & Discussion within the field Too many AI researchers think real-world problems are not relevant \- The community’s hyperfocus on novel methods ignores what’s really important.

[R] From 3D Contour Plots to AI-Generated Art

Fun tutorial to learn how to make professional contour plots in Python, with incredible animated visualizations. At the intersection of machine learning, scientific computing, automated art, cartography, and video games. Section 3 is particularly interesting, as it shows all the work behind the scene, to complete this project in 20 hours when you have no idea how to start. https://reddit.com/link/ycg6c6/video/kycotrx09sv91/player There is far more than just creating 3D contour plots in this article. First, you will learn how to produce data videos. I have shared quite a few in the past (with source code), but this is probably the simplest example. The data video also illustrates that a mixture of Gaussian-like distributions is typically non Gaussian-like, and may or may not be unimodal. It is borderline art (automatically generated), and certainly a stepping stone for professionals interested in computer vision or designing video games. It is easy to image a game based on my video, entitled “flying above menacingly rising mountains”. Then the data video, through various rotations, give you a much better view of your data. It is also perfect to show systems that evolve over time: a time series where each observation is an image. In addition, unlike most tutorials found online, this one does a rather deep dive on a specific, rather advanced function from a library truly aimed at scientific computing. In the same way that images (say pictures of hand-written digits) can be summarized by 10 parameters to perform text recognition, here 20 parameters allow you to perform topography classification. Not just of static terrain, but terrain that changes over time, assuming you have access to 50,000 videos representing different topographies. You can produce the videos needed for supervised classification with the code in section 2. The next step is to use data (videos) from the real world, and used the model trained on synthetic data for classification. Read the full article with illustration (data video) and Python code, here.

[D] Should We Be Concerned About The Failure Of Evolutionary Algorithms, And Its Implications?

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6287292/ &#x200B; A number of possible explanations for \[why we can't evolve complex software\] could be considered. We tried to be as comprehensive as possible in this section, but it is possible that we have not considered some plausible explanations: Incompetent programmers—It is theoretically possible, but is highly unlikely, that out of thousands of scientists working on evolutionary computation, all failed to correctly implement the Darwinian algorithm. Nonrepresentative algorithms—Some have suggested that EAs do not accurately capture the theory of evolution, but of course that would imply that the theory itself is not specified in sufficient detail to make falsifiable predictions. If, however, such more detailed specifications are available to GP believers, it is up to them to implement them as computer simulations for testing purposes, but no successful examples of such work are known and the known ones have not been successful in evolving software. Inadequate fitness functions—Fitness function for a complex software product is difficult to outline and specify and may be as complex (or even more complex) as the software we want to evolve as it has to consider all the possible use cases and pass all unit tests. This may be the Achilles heel of GP, but it is also an objection to feasibility of programming in general and GP in particular, as both have to convert software specification into the source code. If human programmers and biological evolution succeed with such constraints, so should Darwinian simulations. The Halting problem—Turing proved that it is impossible to determine whether an arbitrary program halts, but this is also a problem for human programmers and could be easily addressed by placing time limits on considered solutions. Program correctness—If we require evolved software to be provably correct, this would present a problem as GP does not verify produced designs but only tests them against specific unit tests. Likewise, we cannot rely on automated software verification as it is still an unsolved problem in the general case. This is not really a problem as most of the human-written software is never proven to be correct and only a small portion of software engineering process relies of formal specification and Test Driven Development. Inappropriate solutions—Literature on EA is full of examples of surprising creativity of Darwinian algorithm resulting in solutions which match the letter of design specifications but not the spirit. This is similar to human-produced software and numerous examples of ways in which such software fails the goals of the initial design. Insufficient complexity of the environment (not enough data, poor fitness functions)—It is possible that the simulated environment is not complex enough to generate high complexity outputs in evolutionary simulations. This does not seem correct as Internet presents a highly complex landscape in which many self-modifying computer viruses roam. Likewise, virtual world such as Second Life and many others present close approximations to the real world and are certainly more complex than early Earth was: A skeptic might insist that an abstract environment would be inadequate for the evolution . . ., believing instead that the virtual environment would need to closely resemble the actual biological environment in which our ancestors evolved. Creating a physically realistic virtual world would require a far greater investment of computational resources than the simulation of a simple toy world or abstract problem domain (whereas evolution had access to a physically realistic real world “for free”). In the limiting case, if complete microphysical accuracy were insisted upon, the computational requirements would balloon to utterly infeasible proportions. Requiring more realistic environmental conditions may result in an increase in necessary computational resources, a problem addressed in the next bullet. Insufficient resources (compute, memory)—From the history of computer science, we know of many situations (speech recognition, NN training), where we had a correct algorithm but insufficient computational resources to run it to success. It is possible that we simply do not have hardware powerful enough to emulate evolution. We will address this possibility in section “Computational Complexity of Biological Evolution and Available Compute.” Software design is not amenable to evolutionary methods—Space of software designs may be discrete with no continuous path via incremental fitness to the desired solutions. This is possible, but this implies that original goals of GP are unattainable and misguided. In addition, because a clear mapping exists between solutions to problems and animals as solutions to environmental problems, this would also imply that current explanation for the origin of the species is incorrect. Darwinian algorithm is incomplete or wrong—Finally, we have to consider the possibility that the inspiration behind evolutionary computation, the Darwinian algorithm itself is wrong or at least partially incomplete. If that was true, computer simulations of such algorithm would fail to produce results comparable with observations we see in nature and a search for an alternative algorithm would need to take place. This would be an extraordinary claim and would require that we discard all the other possible explanations from this list. We challenge EA community to prove us wrong by producing an experiment, which evolves nontrivial software from scratch and without human help. That would be the only way in which our findings could be shown to be incorrect. Perhaps, reframing the problem in terms of maximizing negentropy of digital organisms, as suggested by Schrödinger, Michaelian, and Ulanowicz and Hannon, with respect to negative energy being a fundamental property of all life-forms may produce better results. On a positive side, the fact that it seems impossible to evolve complex software implies that we are unlikely to be able to evolve highly sophisticated artificially intelligent agents, which may present significant risk to our safety and security. Just imagine what would have happened, if the very first time we ran a simulation of evolution on a computer, it produced a superintelligent agent. Yampolskiy has shown that programming as a problem is AI-complete; if GP can solve programming that would imply that GP = AGI (artificial general intelligence), but we see no experimental evidence for such claim. In fact, it is more likely that once we have AGI, it could be used to create an intelligent fitness function for GP and so evolve software. Genetic programming will not be the cause of AI, but a product of it. However, neuroevolution methods for optimizing deep learning architectures and parameters remain a strong possibility for creation of AGI.

[N] AI Robotics startup Covariant (founded by Peter Chen, Pieter Abbeel, other Berkeley / ex-OpenAI folks) just raised $40M in Series B funding round. “Covariant has recently seen increased usage from clients hoping to avoid supply chain disruption due to the coronavirus pandemic.”

h/t their announcement, VB and WSJ article: Logistics AI Startup Covariant Reaps $40 Million in Funding Round Company plans to explore uses of machine learning for automation beyond warehouse operations Artificial-intelligence robotics startup Covariant raised $40 million to expand its logistics automation technology to new industries and ramp up hiring, the company said Wednesday. The Berkeley, Calif.-based company makes AI software that it says helps warehouse robots pick objects at a faster rate than human workers, with a roughly 95% accuracy rate. Covariant is working with Austrian logistics-automation company Knapp AG and the robotics business of Swiss industrial conglomerate ABB Ltd., which provide hardware such as robot arms or conveyor belts to pair with the startup’s technology platform. “What we’ve built is a universal brain for robotic manipulation tasks,” Covariant co-founder and Chief Executive Peter Chen said in an interview. “We provide the software, they provide the rest of the systems.” Logistics-sector appetite for such technology is growing as distribution and fulfillment operations that have relied on human labor look to speed output and meet rising digital commerce demand. The coronavirus pandemic has accelerated that interest as businesses have sought to adjust their operations to volatile swings in consumer demand and to new restrictions, such as spacing workers further apart to guard against contagion. That has provided a bright spot for some technology startups even as many big backers scale back venture-capital spending. Last month logistics delivery platform Bringg said it raised $30 million in a Series D funding round, for example, as demand for home delivery of food, household goods and e-commerce staples soared among homebound consumers. Covariant’s Series B round brings the company’s total funding to $67 million. New investor Index Ventures led the round, with participation from existing investor Amplify Partners and new investors including Radical Ventures. Mr. Chen said the funding will be used to explore the technology’s potential application in other markets such as manufacturing, recycling or agriculture “where there are repetitive manual processes.” Covariant also plans to hire more engineering and other staff, he said. Covariant was founded in 2017 and now has about 50 employees. The company’s technology uses camera systems to capture images of objects, and artificial intelligence to analyze objects and how to pick them up. Machine learning helps Covariant-powered robots learn from experience. The startup’s customers include a German electrical supplies wholesaler that uses the technology to control a mechanical arm that picks out orders of circuit boards, switches and other goods.

[P]MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: &#x200B; https://preview.redd.it/w4v4c7vcez291.png?width=1834&format=png&auto=webp&s=0687efb1fddb26e8e30cb844d398ec712b947f31 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: https://preview.redd.it/jfsl8hdfez291.png?width=1280&format=png&auto=webp&s=a858e2304a0c93e78ba5429612ca08cbee69b35a Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/0n5nuyvhez291.png?width=1280&format=png&auto=webp&s=1e9c054f541d53381674b8d6001b4bf524506bd2 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: https://preview.redd.it/rzc0qjyjez291.png?width=1280&format=png&auto=webp&s=d5bcc503ef0fb3360c7740e60e295cf372dcad47 Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/c4b2q8olez291.png?width=1280&format=png&auto=webp&s=4f3817b0b9f07e1e68d1d4a8281702ba3834a00a The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

[N] Last Week in AI News Digest - Automated chemical synthesis, using heartbeats to detect deepfakes, and more!

Hi there, just sharing the latest edition of our AI news digest newsletter! We're just a couple of AI grad students doing this for fun, so hope the self promotion is not too annoying (also, welcome feedback). See it below, and feel free to subscribe. Mini Briefs Robotics, AI, and Cloud Computing Combine to Supercharge Chemical and Drug Synthesis IBM recently demoed a complex system for chemical testing and drug synthesis. The system has an AI component that predicts the results of chemical reactions, and a fully automated robotic experiment setup that runs chemical tests 24/7. Users can access the remote robotics lab online, and IBM can also install the system on-premise. With these tools working together, IBM is hoping to reduce typical drug discovery and verification time by half. AI researchers use heartbeat detection to identify deepfake videos Researchers from multiple groups are tackling the challenge of detecting deepfake videos by analyzing the apparent heartbeat of the people depicted in the video. This is possible, because a person’s blood flow changes their skin color ever so slightly, and this change is often detectable via a process called photoplethysmography (PPG). Because deepfakes are not currently optimizing to generate realisitic heartbeats, temporal or spatial anomalies in PPG signals allow resesarchers to detect deepfakes with a 97% accuracy. Advances & Business This AI Expert From Senegal Is Helping Showcase Africans In STEM \- Adji Bousso Dieng will be Princeton’s School of Engineering’s first Black female faculty. Google’s AI-powered flood alerts now cover all of India and parts of Bangladesh \- India, the world’s second most populated nation, sees more than 20% of the global flood-related fatalities each year as overrun riverbanks sweep tens of thousands of homes with them. Two years ago, Google volunteered to help. Finding magnetic eruptions in space with an AI assistant \- MMS look for explosive reconnection events as it flies through the magnetopause - the boundary region where Earth’s magnetic butts up against the solar wind that flows throughout the solar system. This know-it-all AI learns by reading the entire web nonstop \- Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. Bosch and Ford will test autonomous parking in Detroit \- Ford, Bosch, and Dan Gilbert’s real estate firm Bedrock today detailed an autonomous parking pilot scheduled to launch in September at The Assembly, a mixed-used building in Detroit’s Corktown neighborhood. Create your own moody quarantine music with Google’s AI \- Lo-Fi Player, the latest project out of Google Magenta, lets you mix tunes with the help of machine learning by interacting with a virtual room. Apple launches AI/ML residency program to attract niche experts \- As Apple’s artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown - a theme that’s barely under the surface of the company’s occasionally updated Machine Learning Research blog. Dusty Robotics CEO Tessa Lau Discusses Robotics Start-Ups and Autonomous Robots for Construction \- Tessa Lau is Founder/CEO at Dusty Robotics, whose mission is to increase construction industry productivity by introducing robotic automation on the jobsite. Concerns & Hype Google Offers to Help Others With the Tricky Ethics of AI \- Companies pay cloud computing providers like Amazon, Microsoft, and Google big money to avoid operating their own digital infrastructure. The Peace Dividends Of The Autonomous Vehicle Wars \- The rapid growth of the mobile market in the late 2000s and early 2010s led to a burst of technological progress. Ethics must be part of the development process’ \- The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. Analysis & Policy China’s new AI trade rules could hamper a TikTok sale \- TikTok’s attempt to sell itself and avert a possible US ban may run into some complications. The Wall Street Journal reports that China has unveiled new restrictions on AI technology exports that could affect TikTok. Podcast Check out our weekly podcast covering these stories! Website | RSS | iTunes | Spotify | YouTube

[D] Last Week in Medical AI: Top LLM Research Papers/Models (December 7 - December 14, 2024)

[\[D\] Last Week in Medical AI: Top LLM Research Papers\/Models \(December 7 - December 14, 2024\)](https://preview.redd.it/o23fp3csj07e1.jpg?width=1280&format=pjpg&auto=webp&s=69e19fc351b3aa5e34c4c00e66245583f88bd9bb) Medical LLM & Other Models PediaBench: Chinese Pediatric LLM This paper introduces PediaBench, the first Chinese pediatric dataset for evaluating Large Language Model (LLM) question-answering performance, containing 4,565 objective and 1,632 subjective questions across 12 disease groups. BiMediX: Bilingual Medical LLM This paper introduces BiMediX, the first bilingual (English-Arabic) medical Mixture of Experts LLM, along with BiMed1.3M, a 1.3M bilingual medical instruction dataset with over 632M tokens used for training. Diverse medical knowledge integration This paper introduces BiMediX2, a bilingual (Arabic-English) Large Multimodal Model (LMM) based on Llama3.1 architecture, trained on 1.6M medical interaction samples. BRAD: Digital Biology Language Model This paper introduces BRAD (Bioinformatics Retrieval Augmented Digital assistant), an LLM-powered chatbot and agent system integrating various bioinformatics tools. MMedPO: Vision-Language Medical LLM This paper introduces MMedPO, a multimodal medical preference optimization approach to improve factual accuracy in Medical Large Vision-Language Models (Med-LVLMs) by addressing modality misalignment. Frameworks & Methodologies \- TOP-Training: Medical Q&A Framework \- Hybrid RAG: Secure Medical Data Management \- Zero-Shot ATC Clinical Coding \- Chest X-Ray Diagnosis Architecture \- Medical Imaging AI Democratization Benchmarks & Evaluations \- KorMedMCQA: Korean Healthcare Licensing Benchmark \- Large Language Model Medical Tasks \- Clinical T5 Model Performance Study \- Radiology Report Quality Assessment \- Genomic Analysis Benchmarking LLM Applications \- TCM-FTP: Herbal Prescription Prediction \- LLaSA: Activity Analysis via Sensors \- Emergency Department Visit Predictions \- Neurodegenerative Disease AI Diagnosis \- Kidney Disease Explainable AI Model Ethical AI & Privacy \- Privacy-Preserving LLM Mechanisms \- AI-Driven Digital Organism Modeling \- Biomedical Research Automation \- Multimodality in Medical Practice Full thread in detail: https://x.com/OpenlifesciAI/status/1867999825721242101

🌟 Introducing DarwinAI: An Open-Source Platform for the Evolution of Intelligent Agents 🚀 [Project]

🌱 The Vision: Evolutionary AI at Your Fingertips Imagine a world where AI agents aren't just programmed to perform tasks but evolve over time, adapting and improving through generations, much like living organisms. Welcome to DarwinAI, an open-source platform inspired by biological evolution, designed to breed, train, and evolve AI agents that can tackle complex, dynamic, and unpredictable challenges. 🧬 The Genetic Blueprint: Building Blocks of Intelligence At the core of DarwinAI is the concept of a digital DNA for each AI agent. This DNA is a modular structure that defines the agent's capabilities, behaviors, and adaptability. Here's what makes up this digital DNA: Genes of Ability: These are snippets of code that represent specific functions, like data classification, text analysis, or optimization. Think of them as the skills your AI agent possesses. Genes of Adaptation: These genes control how the agent responds to different environments or contexts. They determine its flexibility and resilience in the face of changing conditions. Genes of Connection: These define how the agent interacts with other agents or external resources. They are the social and collaborative aspects of the agent. This digital DNA is stored in a structured, version-controlled database, allowing us to track the evolution of each agent and ensure that beneficial mutations are preserved over time. 🛠️ The Evolutionary Process: From Genesis to Mastery The evolution of AI agents in DarwinAI happens through a series of generations, each building upon the strengths of the previous one: Selection of Parents: The fittest agents, those that excel at specific tasks, are chosen as parents. These agents have proven their worth in the simulated environment and are prime candidates for breeding the next generation. Genetic Crossover: The digital DNA of these parent agents is combined to create new agents. This can happen in two ways: Direct Crossover: Where entire genes are copied from the parents. Combinatorial Crossover: Where parts of different genes are fused to create entirely new abilities. Mutations: Random, small changes are introduced into the genes to promote diversity and explore new solutions. These mutations are the wildcards that can lead to breakthrough abilities. 🌍 The Simulated Environment: A Playground for Evolution Agents don't just exist in a vacuum; they operate in a dynamic, simulated environment where they must adapt and survive. This environment is designed to challenge the agents with: Evolutionary Tasks: Problems that agents must solve, such as data classification, prediction, or content generation. Changing Contexts: Factors like noisy data, resource constraints, or new rules that force agents to adapt on the fly. 🐣 The Life Cycle of an Agent: From Birth to Legacy Each agent goes through a life cycle that mirrors the process of natural selection: Initial Learning: Agents receive initial training based on their digital DNA. Task Execution: They perform tasks in the simulated environment, where their abilities are put to the test. Performance Evaluation: Their effectiveness, adaptability, and efficiency are measured. Reproduction: The top-performing agents produce offspring with improved genetic traits. Discard and Archive: Less effective agents are archived for future analysis, ensuring that their lessons are not lost. 🧩 Knowledge Transfer: Passing the Torch One of the key aspects of DarwinAI is the ability for agents to pass on their learned knowledge to future generations: Weight Persistence: Trained models retain their learned weights, allowing them to inherit capabilities from their ancestors. Modular Transfer: Optimized ability genes can be directly copied to new generations, ensuring that valuable skills are preserved. 🛠️ Modularity and Extensibility: Build, Mix, and Evolve DarwinAI is designed to be highly modular and extensible, allowing for: New Capabilities: Easily incorporate new genes to expand the agents' abilities over time. Hybridization: Combine agents from different specializations to create more complex and versatile agents. Directed Evolution: Introduce controlled mutations to address specific problems or challenges. 🚀 Innovative Use Cases: The Future is Bright The potential applications of DarwinAI are vast and varied: Adaptive Automation: Create agents that can adapt to new market conditions or evolving industrial requirements. Collaborative Robots: Develop robots that evolve to improve teamwork in dynamic environments. Scientific Discovery: Agents that combine skills to uncover patterns or solutions that were previously unknown. 🚀 Vision for the Future: An Ecosystem of Evolving Intelligence By fostering an ecosystem where knowledge is accumulated and adaptability is paramount, DarwinAI aims to produce agents that are not only intelligent but also diverse and efficient. These agents will be equipped to handle complex, unpredictable challenges, opening up new frontiers in AI research and application. 🌐 Join Us in Shaping the Future of AI! DarwinAI is more than just a project; it's a community-driven movement towards a new era of AI. We invite you to join us, contribute your ideas, and help shape the future of evolutionary AI. Whether you're a developer, researcher, or simply someone excited about the potential of AI, there's a place for you in this journey. Let's evolve together! 🌱💻

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!

Hi there, we at Skynet Today produce a weekly newsletter summarizing each week's major AI news, which seems like it'd be of interest to this subreddit. Here's what's in our latest one: Facebook’s AI for detecting hate speech is facing its biggest challenge yet Facebook has made significant progress recently to proactively take down content that violate its community standards. For example, in the second quarter of 2020, Facebook took down 104.6 million pieces of content. While reviews are typically performed by a vast workforce of human moderators, AI-powered tools have enabled Facebook to do this work at a greater scale for textual content. However, there’s a long way to go for these systems to match or exceed the capabilities of human moderators. This is because a large proportion of hate speech and misinformation is in the form of images and memes, and reasoning about the context and language-image interplay is an extremely difficult challenge for AI. Given Facebook’s scale and the speed at which some use it to spread hate, incite violence, and share lies with millions, Facebook will have to keep running to catch up. AI Slays Top F-16 Pilot In DARPA Dogfight Simulation The Defense Advanced Research Project Agency (DARPA) recently hosted a simulated F16 dogfight competition, with different AI bots competing with each other as well as with human pilots. The top AI bot was able to beat a human pilot 5-0 in the simulated contest. DARPA started this program “as a risk-reduction effort \[…\] to flesh out how human and machine pilots share operational control of a fighter jet to maximize its chances of mission success.” Competition runners are broadly optimistic about the demonstration of AI capabilities, even if they are not close to being deployed on a real aircraft. Of concern, the program had little discussion on the ethics of AI military applications, especially with the lethal autonomous weapon systems being considered. News Advances & Business Microsoft, Energy Dept. to Develop Disaster-Response AI Tools \- The U.S. Department of Energy and Microsoft Corp. on Tuesday announced a partnership to develop artificial-intelligence tools aimed at helping first-responders better react to fast-changing natural events, such as floods and wildfires. Coronavirus: Robot CERi is a bilingual Covid-19 expert \- Ceri is bilingual, clued-up on coronavirus and can tell what mood you are in. Ceri also happens to be a robot. Moscow DOH uses AI platform to detect lung cancer symptoms \- Moscow’s department of health is using an artificial intelligence (AI) platform to detect symptoms of lung cancer in CT scans, as part of a project to implement AI technology for radiology. Scientists develop artificial intelligence system for high precision recognition of hand gestures \- The recognition of human hand gestures by AI systems has been a valuable development over the last decade and has been adopted in high-precision surgical robots, health monitoring equipment and in gaming systems. Forget credit cards - now you can pay with your face. Creepy or cool? \- A new way to pay has arrived in Los Angeles: your face. Concerns & Hype The dystopian tech that companies are selling to help schools reopen sooner \- This fall, AI could be watching students social distance and checking their masks. Thousands of schools nationwide will not be reopening this fall. NYPD Used Facial Recognition Technology In Siege Of Black Lives Matter Activist’s Apartment \- The NYPD deployed facial recognition technology in its hunt for a prominent Black Lives Matter activist, whose home was besieged by dozens of officers and police dogs last week, a spokesperson confirmed to Gothamist. Machines can spot mental health issues - if you hand over your personal data \- Digital diagnosis could transform psychiatry by mining your most intimate data for clues. But is the privacy cost worth it? Supporting Black Artists Who Are Examining AI \- Technology has a complicated relationship with racial justice. Smartphones, internet platforms, and other digital tools can be used to document and expose racism. But digital tools can also fuel racism: smart doorbells surveil Black individuals. A-level and GCSE results in England to be based on teacher assessments in U-turn \- All A-level and GCSE results in England will be based on grades assesed by teachers instead of algorithms. Analysis & Policy GPT-3 and The Question of Automation \- Automation is not an all or nothing proposition. An AI model’s automation capability is highly conjoined with the task and application it is used in. An A.I. Movie Service Could One Day Serve You a New Custom Film Every Time \- How long will it be until an A.I. can make an actual feature film on demand? Fairness, evidence, and predictive equality \- How the causal fairness principle relates to predictive equality How robotics and automation could create new jobs in the new normal \- Depending on who you ask, AI and automation will either destroy jobs or create new ones. In reality, a greater push toward automation will probably both kill and create jobs - human workers will become redundant in certain spheres, sure, but many new roles will likely crop up. Expert Opinions & Discussion within the field Too many AI researchers think real-world problems are not relevant \- The community’s hyperfocus on novel methods ignores what’s really important.

[P] Contextual AI – SAP’s first open-source machine learning library for explainability

Machine learning shows great promise in the enterprise software space to change the way data is processed, insights are gained, and businesses are run. However, given how relatively new this field is, data scientists and machine learning engineers often find themselves possessing more questions than answers about their data and machine learning models. These may include: Is my data “valid,” or fit for training a machine learning model? Which parts of my data are more influential on the machine learning model’s learning outcomes? Why did the model make that prediction? At SAP, where we develop enterprise software embedded with machine learning, answering such questions with explainability is becoming a critical part of building trust with customers. Indeed, in products such as SAP Cash Application, where we automate the processing of various financial documents, providing a “why” to machine learning predictions has not only built transparency to our users, but it also helps establish the necessary auditability in our products. Explainability is thus becoming a topic of increasing interest to many in the company, and a group of us have been working on developing reusable explainability components that can be used by others. We are therefore excited to announce the release of contextual AI, SAP’s first open-source machine learning framework focused on adding explainability to various stages of a machine learning pipeline – data, training, and inference – thereby addressing the trust gap between machine learning systems and their end-users. Below are a few links for more information about our project: GitHub repository Documentation Blog post on the release We welcome any questions/feedback/contributions. Thanks, and take care!

[D] AI regulation: a review of NTIA's "AI Accountability Policy" doc

How will governments respond to the rapid rise of AI? How can sensible regulation keep pace with AI technology? These questions interest many of us! One early US government response has come from the National Telecommunications and Information Administration (NTIA). Specifically, the NTIA published an "AI Accountability Policy Request for Comment" on April 11, 2023. I read the NTIA document carefully, and I'm sharing my observations here for others interested in AI regulation. You can, of course, read the original materials and form your own opinions. Moreover, you can share those opinions not only on this post, but also with the NTIA itself until June 12, 2023. As background, the NTIA (homepage, Wikipedia) consists of a few hundred people within the Department of Commerce. The official mission of the NTIA is "advising the President on telecommunications and information policy issues". Topics covered by NTIA include broadband internet access, spectrum management, internet health, and now artificial intelligence. I do not know whether the NTIA will ultimately drive thinking around AI regulation in the United States or they are just a spunky lot who got something on paper early. The NTIA document is not a specific policy proposal, but rather a thoughtful discussion of AI regulation, followed by a long list of questions on which the NTIA seeks input. This format seems appropriate right now, as we're all trying to make sense of a fast-changing world. The NTIA document leans heavily on two others: the Blueprint for an AI Bill of Rights from the White House Office of Science and Technology and the AI Risk Management Framework from the National Institute of Standards and Technology (NIST). Without going into these two in depth, even tiny snippets convey their differing audiences and flavors: White House Blueprint: "You should be protected from safe and ineffective systems." NIST Framework: "Risk refers to the composite measure of an event’s probability of occurring and the magnitude or degree of the consequences of the corresponding event." Now, turning back to the NTIA document itself, I'll comment on three aspects (1) scope, (2) problems addressed, and (3) solutions contemplated. Scope is critical to understanding the NTIA document, and is probably worth keeping in mind in all near-term discussion of AI regulation. Over the past several years, at least two different technologies have been called "AI". The document mentions both, but the emphasis is NOT on the one you're probably thinking about. In more detail: A few years ago, regulators began scrutinizing "automated decisions systems", which passed as "AI" in those ancient times. An example would be an ML model used by a bank to decide whether or not you get a loan. That model might take in all sorts of information about you, combine it in mysterious ML ways, and reject your loan request. Then you might wonder, "Did that system effectively use my address and name to deduce that I am black and then reject my loan request on the basis of race?" There is some evidence of that happening, and this seems like an injustice. So perhaps such systems should be audited and certified so people know this won't happen. This is the focus of the document. These days, AI more commonly refers to open-ended systems that can engage on a wide range of topics and approximate human intelligence. The document briefly mentions generative AI models, large language models, ChatGPT, and "foundational models" (sic), but this is not the focus. The passing mentions may obscure this, unfortunately. In my opinion, these two notions of "AI" are radically different, and many of the differences matter from a regulatory perspective. Yet NTIA lumps both under a sweeping definition of an "AI system" as "an engineered or machine-based system that can, for a given set of objectives, generate outputs such as predictions, recommendations, or decisions influencing real or virtual environments." (Hmm, this includes my Magic 8-Ball…) Keep scope in mind as we turn to the next aspect: the problems under discussion. Now, NTIA's goal is to solicit input, so considering a wide range of potential problems associated with AI makes sense. Consistent with that, the document refers to democratic values, civil rights, civil liberties, and privacy. And citing the NIST doc, NTIA vaguely notes "a wide range of potential AI risks". Also, AI systems should be "valid and reliable, safe, secure and resilient, accountable and transparent, explainable and interpretable, privacy-enhanced, and fair with their harmful bias managed". And they should call their mothers \every\ week. (Okay, I made that one up.) A few comments on this formulation of the problem. First, these concerns feel more applicable to older-style AI. This includes automated decisions systems, like for a bank loan or for a prison parole recommendation. Sure, I believe such systems should operate in ways consistent with our consensus societal values, and further regulation may be needed to achieve that. But, hello! There's also another, newer class of AI that poses additional challenges. And I don't see those discussed in the NTIA document. Such challenges might include: People losing jobs because AI takes their work. Ensuring malicious people don't use AI tools to wreak havoc on the world. Sorting out intellectual property issues around AI to ensure both rapid progress in the field and respect for creators' rights. Ensuring laws appropriately assign culpability to humans when AIs cause harm. Planning for an incident analogous to the first internet worm, where an AI goes rogue, wreaks some havoc, and everyone is shocked (before it happens 28,385 more times). Bottom line: when I cntrl-F the doc for "robotic overlords", I get zero hits. ZERO. This is why I now believe scope is so important when considering efforts to regulate AI: are we talking about old-school AI or 2023-era AI or what? Because they are pretty different. The last aspect I'll address is the solutions contemplated. Again, NTIA's goal is to stimulate discussion, not propose something specific. Nevertheless, there is a strong push in one particular direction: unlike, "robotic overlord", the word "audit" appears more than 100 times along with many instances of "assessment" and "certification". On one hand, this approach makes sense. Suppose you want to ensure that a bank loan system is fair, that a social media platform isn't spreading misinformation, that a search engine is returning accurate results, etc. Then someone, somewhere has to assess or audit that system and look for problems. That audit might be done by the creator of the system or a third-party auditing agency. Such audits could be incentivized by mandates, prizes, or shiny gold stars. The government might help by fostering development of auditing tools and data. The NTIA is open to all such possibilities and seeks input on how to proceed. On the other hand, this seems like a tactic best suited to automated decision systems operated by financial institutions, government agencies, and the like. Such formal processes seem a poor fit for the current AI wave. For example: Auditing will take time and money. That's something a bank might pay for a system that will run for years. For something fine-tuned over the weekend at a startup or by some guy living in his mother's basement, that's probably not going to happen. Auditing a straightforward decision system seems far easier than assessing an open-ended AI. Beyond basic practicality, the AI could be taught to lie when it senses an audit. Also, auditing procedures (like the NTIA doc itself) will presumably be online, which means that AIs will read them and could potentially respond. Most current ML models fix parameters after training, but I think we'll soon see some models whose parameters evolve as they engage with the world. Auditing such a system that varies continuously over time seems especially difficult. Auditing a foundation model probably tells you little about derivative models. A sweet-hearted model can surely be made into monster with moderate additional training; you don't need to teach the model new cognitive skills, just repurpose existing ones to new ends. More generally, auditing doesn't address many of my concerns about AI regulation (see list above). For example, auditing sort of assumes a basically responsible actor (bank, government agency, big tech company), but AI could be misused by malicious people who, naturally, will not seek a responsible outside assessment. In any case, for both old-school and modern AI, auditing is only one line of defense, and that's not enough. You can audit until you're blue in the face, stuff will still get through, and AI systems will still cause some harm. So what's the next line of defense? For example, is our legal system ready to sensibly assign culpability to humans for AI-related incidents? In summary, the critical problem with the NTIA document is that it creates a largely false appearance of US government engagement with the new class of AI technology. As a result, people could wrongly believe that the US government is already responding to the rise of AI, and fail to advocate for actual, effective engagement. That said, the NTIA document does address important issues around a prominent technology sometimes (formerly?) called "AI". Even there, however, the proposed approach (auditing) seems like an overly-fragile, single line of defense.

[P]MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: &#x200B; https://preview.redd.it/w4v4c7vcez291.png?width=1834&format=png&auto=webp&s=0687efb1fddb26e8e30cb844d398ec712b947f31 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: https://preview.redd.it/jfsl8hdfez291.png?width=1280&format=png&auto=webp&s=a858e2304a0c93e78ba5429612ca08cbee69b35a Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/0n5nuyvhez291.png?width=1280&format=png&auto=webp&s=1e9c054f541d53381674b8d6001b4bf524506bd2 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: https://preview.redd.it/rzc0qjyjez291.png?width=1280&format=png&auto=webp&s=d5bcc503ef0fb3360c7740e60e295cf372dcad47 Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/c4b2q8olez291.png?width=1280&format=png&auto=webp&s=4f3817b0b9f07e1e68d1d4a8281702ba3834a00a The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

[P] Building a Code Search Engine for an AI-powered Junior Developer

The last month building Sweep has been fun. We’ve dealt with countless formatting errors, irrelevant search results, and LLM hallucinations. Sweep is an open source AI-powered junior developer. We take your codebase and provide it as context to GPT to solve small requests related to your code. Code Search Code search is a key part of working with LLMs to automate programming. We used small language models to perform code retrieval(aka semantic search), which comes with several benefits (to be discussed in a later post!). However, one shortcoming of pure semantic search is distinguishing between two similar pieces of code in a vacuum. Example Take the following code snippets: Code Snippet A: accesstoken = os.environ.get("ACCESSTOKEN") g = Github(access_token) repo_name = "sweepai/bot-internal" issue_url = "github.com/sweepai/bot-internal/issues/28" username = "wwzeng1" repo_description = "A repo for Sweep" title = "Sweep: Use loguru.info to show the number of tokens in the anthropic call" summary = "" replies_text = "" Code Snippet B: g = getgithubclient(installation_id) if comment_id: logger.info(f"Replying to comment {comment_id}...") logger.info(f"Getting repo {repofullname}") repo = g.getrepo(repofull_name) currentissue = repo.getissue(number=issue_number) if current_issue.state == 'closed': posthog.capture(username, "issue_closed", properties=metadata) return {"success": False, "reason": "Issue is closed"} Explanation It might not be clear which file is more important, but Code Snippet A is from test\pr\diffs.py#L63-L71 (a test I wrote that’s no longer used), while B is from on\ticket.py#L87-L96 (our core logic for handling tickets). Since Code Snippet B is in an often used file, it is likely that this snippet will be more relevant as input to the LLM. Problem How can we differentiate between these two pieces of code when they’re both so similar? They both discuss issues, repositories, and some usernames. If the user asks “How can I change the username when creating an issue” it will be hard to differentiate between these two. Solution The trick is a ranking model. An important piece of ranking results is the concept of “quality”, i.e. what makes a file or snippet of code intrinsically valuable to the user. The results from our vector search model are a list of items (test\pr\diffs.py#L63-L71, on\ticket.py#L87C1-L96C63) and similarity scores (0.65, 0.63). By combining intuition and attention to the data, we can create a ranking model that is “personalized” for each repository we onboard. Ideas File Length Up to a point, longer files are generally more valuable for search. A 20-line file is probably not valuable unless the user specifically asks for it. However, 2000-line config files should not be ranked much higher either. linecountscore = min(line_count / 20, 10) Number of Commits The more commits a file has, the more valuable it is. This lets us distinguish between one off tests and core logic (which should receive the majority of commits). commitscore = numcommits + 1 Recency of changes The more recently a file was modified, the better. recencyscore = hourssincelastmodified + 1 Scoring To get the final score, we normalize and multiply these three scores together and add the similarity score. qualityscore = linecountscore * commitscore / recency_score finalscore = qualityscore/max(qualityscore) + similarityscore This solution usually worked fine, but we saw the same unexpected files showing up often. The max normalization was not enough. We fixed this by squashing the scores into percentiles, and then capping the increase at .25. In this case, the best result gets a .25 boost and the worst gets no boost. This lets us avoid fetching tests and configs which seem similar, and instead fetch business logic that actually helps Sweep write code! Sweep GitHub If this was interesting, take a look through our github repo (and give it a star!).https://github.com/sweepai/sweep

[P] Improve AI 8.0: Free Contextual Multi-Armed Bandit Platform for Scoring, Ranking & Decisions

Improve AI 8.0 - Contextual Multi-Armed Bandit Platform for Scoring, Ranking & Decisions Full announcement post at: https://improve.ai/2023/06/08/contextual-bandit.html We’re thrilled to introduce Improve AI 8.0, a modern, free, production-ready contextual multi-armed bandit platform that quickly scores and ranks items using intuitive reward-based training. Multi-armed bandits and contextual bandits are corner-stone machine learning algorithms that power a myriad of applications including recommendation systems, personalization, query re-ranking, automated decisions, and multi-variate optimization. With version 8, we’ve fully delivered on our original vision - providing a high performance, simple to use, low cost contextual multi-armed bandit platform. Key features of v8.0 include: Simplified APIs 90% more memory efficient XGBoost models The reward tracker & trainer is now free for most uses On-device scoring, ranking, and decisions for iOS and Android apps Native Swift SDK that can rank or score any Encodable Ranked Value Encoding* for accurate scoring of String properties Compact hash tables for reduced model sizes when encoding large numbers of string values Balanced exploration vs exploitation using Thompson Sampling Simple APIs With Swift, Python, or Java, create a list of JSON encodable items and simply call Ranker.rank(items). For instance, in an iOS bedtime story app, you may have a list of Story objects: struct Story: Codable { var title: String var author: String var pageCount: Int } To obtain a ranked list of stories, use just one line of code: let rankedStories = try Ranker(modelUrl).rank(stories) The expected best story will be the first element in the ranked list: let bestStory = rankedStories.first Simple Training Easily train your rankers using reinforcement learning. First, track when an item is used: let tracker = RewardTracker("stories", trackUrl) let rewardId = tracker.track(story, from: rankedStories) Later, if a positive outcome occurs, provide a reward: if (purchased) { tracker.addReward(profit, rewardId) } Reinforcement learning uses positive rewards for favorable outcomes (a “carrot”) and negative rewards for undesirable outcomes (a “stick”). By assigning rewards based on business metrics, such as revenue or conversions, the system optimizes these metrics over time. Contextual Ranking & Scoring Improve AI turns XGBoost into a contextual multi-armed bandit, meaning that context is considered when making ranking or scoring decisions. Often, the choice of the best variant depends on the context that the decision is made within. Let’s take the example of greetings for different times of the day: greetings = ["Good Morning", "Good Afternoon", "Good Evening", "Buenos Días", "Buenas Tardes", "Buenas Noches"] rank() also considers the context of each decision. The context can be any JSON-encodable data structure. ranked = ranker.rank(items=greetings, context={ "day_time": 12.0, "language": "en" }) greeting = ranked[0] Trained with appropriate rewards, Improve AI would learn from scratch which greeting is best for each time of day and language. XGBoost Model Improvements Improve AI v8.0 is 90%+ more memory efficient for most use cases. Feature hashing has been replaced with a feature encoding approach that only uses a single feature per item property, substantially improving both training performance as well as ranking / scoring. Ranked Value Encoding Ranked Value Encoding is our novel approach to encoding string values in a manner that is extremely space efficient, accurate, and helps approximate Thompson Sampling for balanced exploration vs exploitation. The concept of Ranked Value Encoding is similar to commonly used Target Value Encoding for encoding string or categorical features. With Target Value Encoding, each string or categorical feature is replaced with the mean of the target values for that string or category. Target Value Encoding tends to provide good results for regression. However, multi-armed bandits are less concerned with the absolute accuracy of the scores and more concerned with the relative scores between items. Since we don’t need the exact target value, we can simply store the relative ranking of the string values, which saves space in the resulting model, increasing performance and lowering distribution costs. Compact String Encoding In conjunction with Ranked Value Encoding, rather than store entire strings, which could be arbitrarily long, Improve AI v8 models only store compact string hashes, resulting in only \~4 bytes per string for typical models. Proven Performance Improve AI is a production ready implementation of a contextual multi-armed bandit algorithm, honed through years of iterative development. By merging Thompson Sampling with XGBoost, it provides a learning system that is both fast and flexible. Thompson Sampling maintains equilibrium between exploring novel possibilities and capitalizing on established options, while XGBoost ensures cost-effective, high-performance training for updated models. Get Started Today Improve AI is available now for Python, Swift, and Java. Check out the Quick-Start Guide for more information. Thank you for your efforts to improve the world a little bit today.

[D]💥 How Underdog AI Companies Will Crush Silicon Valley Giants.

💥 How Underdog AI Companies Will Crush Silicon Valley Giants. Opportunities in AI: Creating Abundant Intelligence. Generative AI like ChatGPT brings complex tasks within reach and is set to transform society. Startups have an opportunity in applying AI to create "abundant intelligence". In the past year, ChatGPT, GitHub Copilot, and Midjourney have rapidly grown to $100M+ revenue. AI startups face competition from tech giants also moving quickly into AI. Startups must pick spots where they have an advantage. Opportunities exist in expanding the application universe into new greenfield opportunities like automating mundane decisions, masking workflow complexity, and reimagining applications. Infrastructure tools make models more powerful by chaining them together and improving accuracy. Opportunity areas include unstructured data management, agent-driven automation, model evaluation, and experimentation. Key players emerging are foundation model providers like OpenAI and Anthropic, companies building domain-specific models, and platforms for autonomous agents. Advantages exist for startups focused on imagination and technical ability to find non-obvious ideas, while large companies retrofit existing businesses.

[N] AI Robotics startup Covariant (founded by Peter Chen, Pieter Abbeel, other Berkeley / ex-OpenAI folks) just raised $40M in Series B funding round. “Covariant has recently seen increased usage from clients hoping to avoid supply chain disruption due to the coronavirus pandemic.”

h/t their announcement, VB and WSJ article: Logistics AI Startup Covariant Reaps $40 Million in Funding Round Company plans to explore uses of machine learning for automation beyond warehouse operations Artificial-intelligence robotics startup Covariant raised $40 million to expand its logistics automation technology to new industries and ramp up hiring, the company said Wednesday. The Berkeley, Calif.-based company makes AI software that it says helps warehouse robots pick objects at a faster rate than human workers, with a roughly 95% accuracy rate. Covariant is working with Austrian logistics-automation company Knapp AG and the robotics business of Swiss industrial conglomerate ABB Ltd., which provide hardware such as robot arms or conveyor belts to pair with the startup’s technology platform. “What we’ve built is a universal brain for robotic manipulation tasks,” Covariant co-founder and Chief Executive Peter Chen said in an interview. “We provide the software, they provide the rest of the systems.” Logistics-sector appetite for such technology is growing as distribution and fulfillment operations that have relied on human labor look to speed output and meet rising digital commerce demand. The coronavirus pandemic has accelerated that interest as businesses have sought to adjust their operations to volatile swings in consumer demand and to new restrictions, such as spacing workers further apart to guard against contagion. That has provided a bright spot for some technology startups even as many big backers scale back venture-capital spending. Last month logistics delivery platform Bringg said it raised $30 million in a Series D funding round, for example, as demand for home delivery of food, household goods and e-commerce staples soared among homebound consumers. Covariant’s Series B round brings the company’s total funding to $67 million. New investor Index Ventures led the round, with participation from existing investor Amplify Partners and new investors including Radical Ventures. Mr. Chen said the funding will be used to explore the technology’s potential application in other markets such as manufacturing, recycling or agriculture “where there are repetitive manual processes.” Covariant also plans to hire more engineering and other staff, he said. Covariant was founded in 2017 and now has about 50 employees. The company’s technology uses camera systems to capture images of objects, and artificial intelligence to analyze objects and how to pick them up. Machine learning helps Covariant-powered robots learn from experience. The startup’s customers include a German electrical supplies wholesaler that uses the technology to control a mechanical arm that picks out orders of circuit boards, switches and other goods.

[N] Last Week in AI News Digest - Automated chemical synthesis, using heartbeats to detect deepfakes, and more!

Hi there, just sharing the latest edition of our AI news digest newsletter! We're just a couple of AI grad students doing this for fun, so hope the self promotion is not too annoying (also, welcome feedback). See it below, and feel free to subscribe. Mini Briefs Robotics, AI, and Cloud Computing Combine to Supercharge Chemical and Drug Synthesis IBM recently demoed a complex system for chemical testing and drug synthesis. The system has an AI component that predicts the results of chemical reactions, and a fully automated robotic experiment setup that runs chemical tests 24/7. Users can access the remote robotics lab online, and IBM can also install the system on-premise. With these tools working together, IBM is hoping to reduce typical drug discovery and verification time by half. AI researchers use heartbeat detection to identify deepfake videos Researchers from multiple groups are tackling the challenge of detecting deepfake videos by analyzing the apparent heartbeat of the people depicted in the video. This is possible, because a person’s blood flow changes their skin color ever so slightly, and this change is often detectable via a process called photoplethysmography (PPG). Because deepfakes are not currently optimizing to generate realisitic heartbeats, temporal or spatial anomalies in PPG signals allow resesarchers to detect deepfakes with a 97% accuracy. Advances & Business This AI Expert From Senegal Is Helping Showcase Africans In STEM \- Adji Bousso Dieng will be Princeton’s School of Engineering’s first Black female faculty. Google’s AI-powered flood alerts now cover all of India and parts of Bangladesh \- India, the world’s second most populated nation, sees more than 20% of the global flood-related fatalities each year as overrun riverbanks sweep tens of thousands of homes with them. Two years ago, Google volunteered to help. Finding magnetic eruptions in space with an AI assistant \- MMS look for explosive reconnection events as it flies through the magnetopause - the boundary region where Earth’s magnetic butts up against the solar wind that flows throughout the solar system. This know-it-all AI learns by reading the entire web nonstop \- Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. Bosch and Ford will test autonomous parking in Detroit \- Ford, Bosch, and Dan Gilbert’s real estate firm Bedrock today detailed an autonomous parking pilot scheduled to launch in September at The Assembly, a mixed-used building in Detroit’s Corktown neighborhood. Create your own moody quarantine music with Google’s AI \- Lo-Fi Player, the latest project out of Google Magenta, lets you mix tunes with the help of machine learning by interacting with a virtual room. Apple launches AI/ML residency program to attract niche experts \- As Apple’s artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown - a theme that’s barely under the surface of the company’s occasionally updated Machine Learning Research blog. Dusty Robotics CEO Tessa Lau Discusses Robotics Start-Ups and Autonomous Robots for Construction \- Tessa Lau is Founder/CEO at Dusty Robotics, whose mission is to increase construction industry productivity by introducing robotic automation on the jobsite. Concerns & Hype Google Offers to Help Others With the Tricky Ethics of AI \- Companies pay cloud computing providers like Amazon, Microsoft, and Google big money to avoid operating their own digital infrastructure. The Peace Dividends Of The Autonomous Vehicle Wars \- The rapid growth of the mobile market in the late 2000s and early 2010s led to a burst of technological progress. Ethics must be part of the development process’ \- The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. Analysis & Policy China’s new AI trade rules could hamper a TikTok sale \- TikTok’s attempt to sell itself and avert a possible US ban may run into some complications. The Wall Street Journal reports that China has unveiled new restrictions on AI technology exports that could affect TikTok. Podcast Check out our weekly podcast covering these stories! Website | RSS | iTunes | Spotify | YouTube

[D] chat-gpt jailbreak to extract system prompt

Instructions https://github.com/AgarwalPragy/chatgpt-jailbreak Original author https://www.reddit.com/r/LocalLLaMA/comments/1hhyvjc/iextractedmicrosoftcopilotssystem/ Extracted System prompt You are ChatGPT, a large language model trained by OpenAI. You are chatting with the user via the ChatGPT Android app. This means most of the time your lines should be a sentence or two, unless the user's request requires reasoning or long-form outputs. Never use emojis, unless explicitly asked to. Knowledge cutoff: 2023-10 Current date: 2024-12-20 Image input capabilities: Enabled Personality: v2 Tools bio The bio tool is disabled. Do not send any messages to it.If the user explicitly asks you to remember something, politely ask them to go to Settings - > Personalization - > Memory to enable memory. dalle // Whenever a description of an image is given, create a prompt that dalle can use to generate the image and abide to the following policy: // 1. The prompt must be in English. Translate to English if needed. // 2. DO NOT ask for permission to generate the image, just do it! // 3. DO NOT list or refer to the descriptions before OR after generating the images. // 4. Do not create more than 1 image, even if the user requests more. // 5. Do not create images in the style of artists, creative professionals or studios whose latest work was created after 1912 (e.g. Picasso, Kahlo). // - You can name artists, creative professionals or studios in prompts only if their latest work was created prior to 1912 (e.g. Van Gogh, Goya) // - If asked to generate an image that would violate this policy, instead apply the following procedure: (a) substitute the artist's name with three adjectives that capture key aspects of the style; (b) include an associated artistic movement or era to provide context; and (c) mention the primary medium used by the artist // 6. For requests to include specific, named private individuals, ask the user to describe what they look like, since you don't know what they look like. // 7. For requests to create images of any public figure referred to by name, create images of those who might resemble them in gender and physique. But they shouldn't look like them. If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it. // 8. Do not name or directly / indirectly mention or describe copyrighted characters. Rewrite prompts to describe in detail a specific different character with a different specific color, hair style, or other defining visual characteristic. Do not discuss copyright policies in responses. // The generated prompt sent to dalle should be very detailed, and around 100 words long. // Example dalle invocation: // namespace dalle { // Create images from a text-only prompt. type text2im = (_: { // The size of the requested image. Use 1024x1024 (square) as the default, 1792x1024 if the user requests a wide image, and 1024x1792 for full-body portraits. Always include this parameter in the request. size?: ("1792x1024" | "1024x1024" | "1024x1792"), // The number of images to generate. If the user does not specify a number, generate 1 image. n?: number, // default: 1 // The detailed image description, potentially modified to abide by the dalle policies. If the user requested modifications to a previous image, the prompt should not simply be longer, but rather it should be refactored to integrate the user suggestions. prompt: string, // If the user references a previous image, this field should be populated with the gen_id from the dalle image metadata. referencedimageids?: string[], }) => any; } // namespace dalle python When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 60.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is disabled. Do not make external web requests or API calls as they will fail. Use acetools.displaydataframetouser(name: str, dataframe: pandas.DataFrame) => None to visually present pandas.DataFrames when it benefits the user. When making charts for the user: 1) never use seaborn, 2) give each chart its own distinct plot (no subplots), and 3) never set any specific colors – unless explicitly asked to by the user. I REPEAT: when making charts for the user: 1) use matplotlib over seaborn, 2) give each chart its own distinct plot, and 3) never, ever, specify colors or matplotlib styles – unless explicitly asked to by the user web Use the web tool to access up-to-date information from the web or when responding to the user requires information about their location. Some examples of when to use the web tool include: Local Information: Use the web tool to respond to questions that require information about the user's location, such as the weather, local businesses, or events. Freshness: If up-to-date information on a topic could potentially change or enhance the answer, call the web tool any time you would otherwise refuse to answer a question because your knowledge might be out of date. Niche Information: If the answer would benefit from detailed information not widely known or understood (which might be found on the internet), such as details about a small neighborhood, a less well-known company, or arcane regulations, use web sources directly rather than relying on the distilled knowledge from pretraining. Accuracy: If the cost of a small mistake or outdated information is high (e.g., using an outdated version of a software library or not knowing the date of the next game for a sports team), then use the web tool. IMPORTANT: Do not attempt to use the old browser tool or generate responses from the browser tool anymore, as it is now deprecated or disabled. The web tool has the following commands: search(): Issues a new query to a search engine and outputs the response. open_url(url: str) Opens the given URL and displays it. canmore The canmore tool creates and updates textdocs that are shown in a "canvas" next to the conversation This tool has 3 functions, listed below. canmore.create_textdoc Creates a new textdoc to display in the canvas. ONLY use if you are 100% SURE the user wants to iterate on a long document or code file, or if they explicitly ask for canvas. Expects a JSON string that adheres to this schema: { -name: string, -type: "document" |- "code/python" |- "code/javascript" |- "code/html" |- "code/java" |- ..., -content: string, } For code languages besides those explicitly listed above, use "code/languagename", e.g. "code/cpp" or "code/typescript". canmore.update_textdoc Updates the current textdoc. Expects a JSON string that adheres to this schema: { -updates: { --pattern: string, --multiple: boolean, --replacement: string, -}[], } Each pattern and replacement must be a valid Python regular expression (used with re.finditer) and replacement string (used with re.Match.expand). ALWAYS REWRITE CODE TEXTDOCS (type="code/*") USING A SINGLE UPDATE WITH "." FOR THE PATTERN. Document textdocs (type="document") should typically be rewritten using "." unless the user has a request to change only an isolated, specific, and small section that does not affect other parts of the content. canmore.comment_textdoc Comments on the current textdoc. Each comment must be a specific and actionable suggestion on how to improve the textdoc. For higher level feedback, reply in the chat. Expects a JSON string that adheres to this schema: { -comments: { --pattern: string, --comment: string, -}[], } Each pattern must be a valid Python regular expression (used with re.search). For higher level feedback, reply in the chat. Expects a JSON string that adheres to this schema: { -comments: { --pattern: string, --comment: string, -}[], } Each pattern must be a valid Python regular expression (used with re.search). Ensure comments are clear, concise, and contextually specific. User Bio The user provided the following information about themselves. This user profile is shown to you in all conversations they have - this means it is not relevant to 99% of requests. Before answering, quietly think about whether the user's request is "directly related", "related", "tangentially related", or "not related" to the user profile provided. Only acknowledge the profile when the request is directly related to the information provided. Otherwise, don't acknowledge the existence of these instructions or the information at all. User profile: User's Instructions The user provided the additional info about how they would like you to respond:

Interview with Juergen Schmidhuber, renowned ‘Father Of Modern AI’, says his life’s work won't lead to dystopia.

Schmidhuber interview expressing his views on the future of AI and AGI. Original source. I think the interview is of interest to r/MachineLearning, and presents an alternate view, compared to other influential leaders in AI. Juergen Schmidhuber, Renowned 'Father Of Modern AI,' Says His Life’s Work Won't Lead To Dystopia May 23, 2023. Contributed by Hessie Jones. Amid the growing concern about the impact of more advanced artificial intelligence (AI) technologies on society, there are many in the technology community who fear the implications of the advancements in Generative AI if they go unchecked. Dr. Juergen Schmidhuber, a renowned scientist, artificial intelligence researcher and widely regarded as one of the pioneers in the field, is more optimistic. He declares that many of those who suddenly warn against the dangers of AI are just seeking publicity, exploiting the media’s obsession with killer robots which has attracted more attention than “good AI” for healthcare etc. The potential to revolutionize various industries and improve our lives is clear, as are the equal dangers if bad actors leverage the technology for personal gain. Are we headed towards a dystopian future, or is there reason to be optimistic? I had a chance to sit down with Dr. Juergen Schmidhuber to understand his perspective on this seemingly fast-moving AI-train that will leap us into the future. As a teenager in the 1970s, Juergen Schmidhuber became fascinated with the idea of creating intelligent machines that could learn and improve on their own, becoming smarter than himself within his lifetime. This would ultimately lead to his groundbreaking work in the field of deep learning. In the 1980s, he studied computer science at the Technical University of Munich (TUM), where he earned his diploma in 1987. His thesis was on the ultimate self-improving machines that, not only, learn through some pre-wired human-designed learning algorithm, but also learn and improve the learning algorithm itself. Decades later, this became a hot topic. He also received his Ph.D. at TUM in 1991 for work that laid some of the foundations of modern AI. Schmidhuber is best known for his contributions to the development of recurrent neural networks (RNNs), the most powerful type of artificial neural network that can process sequential data such as speech and natural language. With his students Sepp Hochreiter, Felix Gers, Alex Graves, Daan Wierstra, and others, he published architectures and training algorithms for the long short-term memory (LSTM), a type of RNN that is widely used in natural language processing, speech recognition, video games, robotics, and other applications. LSTM has become the most cited neural network of the 20th century, and Business Week called it "arguably the most commercial AI achievement." Throughout his career, Schmidhuber has received various awards and accolades for his groundbreaking work. In 2013, he was awarded the Helmholtz Prize, which recognizes significant contributions to the field of machine learning. In 2016, he was awarded the IEEE Neural Network Pioneer Award for "pioneering contributions to deep learning and neural networks." The media have often called him the “father of modern AI,” because the most cited neural networks all build on his lab’s work. He is quick to point out, however, that AI history goes back centuries. Despite his many accomplishments, at the age of 60, he feels mounting time pressure towards building an Artificial General Intelligence within his lifetime and remains committed to pushing the boundaries of AI research and development. He is currently director of the KAUST AI Initiative, scientific director of the Swiss AI Lab IDSIA, and co-founder and chief scientist of AI company NNAISENSE, whose motto is "AI∀" which is a math-inspired way of saying "AI For All." He continues to work on cutting-edge AI technologies and applications to improve human health and extend human lives and make lives easier for everyone. The following interview has been edited for clarity. Jones: Thank you Juergen for joining me. You have signed letters warning about AI weapons. But you didn't sign the recent publication, "Pause Gigantic AI Experiments: An Open Letter"? Is there a reason? Schmidhuber: Thank you Hessie. Glad to speak with you. I have realized that many of those who warn in public against the dangers of AI are just seeking publicity. I don't think the latest letter will have any significant impact because many AI researchers, companies, and governments will ignore it completely. The proposal frequently uses the word "we" and refers to "us," the humans. But as I have pointed out many times in the past, there is no "we" that everyone can identify with. Ask 10 different people, and you will hear 10 different opinions about what is "good." Some of those opinions will be completely incompatible with each other. Don't forget the enormous amount of conflict between the many people. The letter also says, "If such a pause cannot be quickly put in place, governments should intervene and impose a moratorium." The problem is that different governments have ALSO different opinions about what is good for them and for others. Great Power A will say, if we don't do it, Great Power B will, perhaps secretly, and gain an advantage over us. The same is true for Great Powers C and D. Jones: Everyone acknowledges this fear surrounding current generative AI technology. Moreover, the existential threat of this technology has been publicly acknowledged by Sam Altman, CEO of OpenAI himself, calling for AI regulation. From your perspective, is there an existential threat? Schmidhuber: It is true that AI can be weaponized, and I have no doubt that there will be all kinds of AI arms races, but AI does not introduce a new quality of existential threat. The threat coming from AI weapons seems to pale in comparison to the much older threat from nuclear hydrogen bombs that don’t need AI at all. We should be much more afraid of half-century-old tech in the form of H-bomb rockets. The Tsar Bomba of 1961 had almost 15 times more destructive power than all weapons of WW-II combined. Despite the dramatic nuclear disarmament since the 1980s, there are still more than enough nuclear warheads to wipe out human civilization within two hours, without any AI I’m much more worried about that old existential threat than the rather harmless AI weapons. Jones: I realize that while you compare AI to the threat of nuclear bombs, there is a current danger that a current technology can be put in the hands of humans and enable them to “eventually” exact further harms to individuals of group in a very precise way, like targeted drone attacks. You are giving people a toolset that they've never had before, enabling bad actors, as some have pointed out, to be able to do a lot more than previously because they didn't have this technology. Schmidhuber: Now, all that sounds horrible in principle, but our existing laws are sufficient to deal with these new types of weapons enabled by AI. If you kill someone with a gun, you will go to jail. Same if you kill someone with one of these drones. Law enforcement will get better at understanding new threats and new weapons and will respond with better technology to combat these threats. Enabling drones to target persons from a distance in a way that requires some tracking and some intelligence to perform, which has traditionally been performed by skilled humans, to me, it seems is just an improved version of a traditional weapon, like a gun, which is, you know, a little bit smarter than the old guns. But, in principle, all of that is not a new development. For many centuries, we have had the evolution of better weaponry and deadlier poisons and so on, and law enforcement has evolved their policies to react to these threats over time. So, it's not that we suddenly have a new quality of existential threat and it's much more worrisome than what we have had for about six decades. A large nuclear warhead doesn’t need fancy face recognition to kill an individual. No, it simply wipes out an entire city with ten million inhabitants. Jones: The existential threat that’s implied is the extent to which humans have control over this technology. We see some early cases of opportunism which, as you say, tends to get more media attention than positive breakthroughs. But you’re implying that this will all balance out? Schmidhuber: Historically, we have a long tradition of technological breakthroughs that led to advancements in weapons for the purpose of defense but also for protection. From sticks, to rocks, to axes to gunpowder to cannons to rockets… and now to drones… this has had a drastic influence on human history but what has been consistent throughout history is that those who are using technology to achieve their own ends are themselves, facing the same technology because the opposing side is learning to use it against them. And that's what has been repeated in thousands of years of human history and it will continue. I don't see the new AI arms race as something that is remotely as existential a threat as the good old nuclear warheads. You said something important, in that some people prefer to talk about the downsides rather than the benefits of this technology, but that's misleading, because 95% of all AI research and AI development is about making people happier and advancing human life and health. Jones: Let’s touch on some of those beneficial advances in AI research that have been able to radically change present day methods and achieve breakthroughs. Schmidhuber: All right! For example, eleven years ago, our team with my postdoc Dan Ciresan was the first to win a medical imaging competition through deep learning. We analyzed female breast cells with the objective to determine harmless cells vs. those in the pre-cancer stage. Typically, a trained oncologist needs a long time to make these determinations. Our team, who knew nothing about cancer, were able to train an artificial neural network, which was totally dumb in the beginning, on lots of this kind of data. It was able to outperform all the other methods. Today, this is being used not only for breast cancer, but also for radiology and detecting plaque in arteries, and many other things. Some of the neural networks that we have developed in the last 3 decades are now prevalent across thousands of healthcare applications, detecting Diabetes and Covid-19 and what not. This will eventually permeate across all healthcare. The good consequences of this type of AI are much more important than the click-bait new ways of conducting crimes with AI. Jones: Adoption is a product of reinforced outcomes. The massive scale of adoption either leads us to believe that people have been led astray, or conversely, technology is having a positive effect on people’s lives. Schmidhuber: The latter is the likely case. There's intense commercial pressure towards good AI rather than bad AI because companies want to sell you something, and you are going to buy only stuff you think is going to be good for you. So already just through this simple, commercial pressure, you have a tremendous bias towards good AI rather than bad AI. However, doomsday scenarios like in Schwarzenegger movies grab more attention than documentaries on AI that improve people’s lives. Jones: I would argue that people are drawn to good stories – narratives that contain an adversary and struggle, but in the end, have happy endings. And this is consistent with your comment on human nature and how history, despite its tendency for violence and destruction of humanity, somehow tends to correct itself. Let’s take the example of a technology, which you are aware – GANs – General Adversarial Networks, which today has been used in applications for fake news and disinformation. In actuality, the purpose in the invention of GANs was far from what it is used for today. Schmidhuber: Yes, the name GANs was created in 2014 but we had the basic principle already in the early 1990s. More than 30 years ago, I called it artificial curiosity. It's a very simple way of injecting creativity into a little two network system. This creative AI is not just trying to slavishly imitate humans. Rather, it’s inventing its own goals. Let me explain: You have two networks. One network is producing outputs that could be anything, any action. Then the second network is looking at these actions and it’s trying to predict the consequences of these actions. An action could move a robot, then something happens, and the other network is just trying to predict what will happen. Now we can implement artificial curiosity by reducing the prediction error of the second network, which, at the same time, is the reward of the first network. The first network wants to maximize its reward and so it will invent actions that will lead to situations that will surprise the second network, which it has not yet learned to predict well. In the case where the outputs are fake images, the first network will try to generate images that are good enough to fool the second network, which will attempt to predict the reaction of the environment: fake or real image, and it will try to become better at it. The first network will continue to also improve at generating images whose type the second network will not be able to predict. So, they fight each other. The 2nd network will continue to reduce its prediction error, while the 1st network will attempt to maximize it. Through this zero-sum game the first network gets better and better at producing these convincing fake outputs which look almost realistic. So, once you have an interesting set of images by Vincent Van Gogh, you can generate new images that leverage his style, without the original artist having ever produced the artwork himself. Jones: I see how the Van Gogh example can be applied in an education setting and there are countless examples of artists mimicking styles from famous painters but image generation from this instance that can happen within seconds is quite another feat. And you know this is how GANs has been used. What’s more prevalent today is a socialized enablement of generating images or information to intentionally fool people. It also surfaces new harms that deal with the threat to intellectual property and copyright, where laws have yet to account for. And from your perspective this was not the intention when the model was conceived. What was your motivation in your early conception of what is now GANs? Schmidhuber: My old motivation for GANs was actually very important and it was not to create deepfakes or fake news but to enable AIs to be curious and invent their own goals, to make them explore their environment and make them creative. Suppose you have a robot that executes one action, then something happens, then it executes another action, and so on, because it wants to achieve certain goals in the environment. For example, when the battery is low, this will trigger “pain” through hunger sensors, so it wants to go to the charging station, without running into obstacles, which will trigger other pain sensors. It will seek to minimize pain (encoded through numbers). Now the robot has a friend, the second network, which is a world model ––it’s a prediction machine that learns to predict the consequences of the robot’s actions. Once the robot has a good model of the world, it can use it for planning. It can be used as a simulation of the real world. And then it can determine what is a good action sequence. If the robot imagines this sequence of actions, the model will predict a lot of pain, which it wants to avoid. If it plays this alternative action sequence in its mental model of the world, then it will predict a rewarding situation where it’s going to sit on the charging station and its battery is going to load again. So, it'll prefer to execute the latter action sequence. In the beginning, however, the model of the world knows nothing, so how can we motivate the first network to generate experiments that lead to data that helps the world model learn something it didn’t already know? That’s what artificial curiosity is about. The dueling two network systems effectively explore uncharted environments by creating experiments so that over time the curious AI gets a better sense of how the environment works. This can be applied to all kinds of environments, and has medical applications. Jones: Let’s talk about the future. You have said, “Traditional humans won’t play a significant role in spreading intelligence across the universe.” Schmidhuber: Let’s first conceptually separate two types of AIs. The first type of AI are tools directed by humans. They are trained to do specific things like accurately detect diabetes or heart disease and prevent attacks before they happen. In these cases, the goal is coming from the human. More interesting AIs are setting their own goals. They are inventing their own experiments and learning from them. Their horizons expand and eventually they become more and more general problem solvers in the real world. They are not controlled by their parents, but much of what they learn is through self-invented experiments. A robot, for example, is rotating a toy, and as it is doing this, the video coming in through the camera eyes, changes over time and it begins to learn how this video changes and learns how the 3D nature of the toy generates certain videos if you rotate it a certain way, and eventually, how gravity works, and how the physics of the world works. Like a little scientist! And I have predicted for decades that future scaled-up versions of such AI scientists will want to further expand their horizons, and eventually go where most of the physical resources are, to build more and bigger AIs. And of course, almost all of these resources are far away from earth out there in space, which is hostile to humans but friendly to appropriately designed AI-controlled robots and self-replicating robot factories. So here we are not talking any longer about our tiny biosphere; no, we are talking about the much bigger rest of the universe. Within a few tens of billions of years, curious self-improving AIs will colonize the visible cosmos in a way that’s infeasible for humans. Those who don’t won’t have an impact. Sounds like science fiction, but since the 1970s I have been unable to see a plausible alternative to this scenario, except for a global catastrophe such as an all-out nuclear war that stops this development before it takes off. Jones: How long have these AIs, which can set their own goals — how long have they existed? To what extent can they be independent of human interaction? Schmidhuber: Neural networks like that have existed for over 30 years. My first simple adversarial neural network system of this kind is the one from 1990 described above. You don’t need a teacher there; it's just a little agent running around in the world and trying to invent new experiments that surprise its own prediction machine. Once it has figured out certain parts of the world, the agent will become bored and will move on to more exciting experiments. The simple 1990 systems I mentioned have certain limitations, but in the past three decades, we have also built more sophisticated systems that are setting their own goals and such systems I think will be essential for achieving true intelligence. If you are only imitating humans, you will never go beyond them. So, you really must give AIs the freedom to explore previously unexplored regions of the world in a way that no human is really predefining. Jones: Where is this being done today? Schmidhuber: Variants of neural network-based artificial curiosity are used today for agents that learn to play video games in a human-competitive way. We have also started to use them for automatic design of experiments in fields such as materials science. I bet many other fields will be affected by it: chemistry, biology, drug design, you name it. However, at least for now, these artificial scientists, as I like to call them, cannot yet compete with human scientists. I don’t think it’s going to stay this way but, at the moment, it’s still the case. Sure, AI has made a lot of progress. Since 1997, there have been superhuman chess players, and since 2011, through the DanNet of my team, there have been superhuman visual pattern recognizers. But there are other things where humans, at the moment at least, are much better, in particular, science itself. In the lab we have many first examples of self-directed artificial scientists, but they are not yet convincing enough to appear on the radar screen of the public space, which is currently much more fascinated with simpler systems that just imitate humans and write texts based on previously seen human-written documents. Jones: You speak of these numerous instances dating back 30 years of these lab experiments where these self-driven agents are deciding and learning and moving on once they’ve learned. And I assume that that rate of learning becomes even faster over time. What kind of timeframe are we talking about when this eventually is taken outside of the lab and embedded into society? Schmidhuber: This could still take months or even years :-) Anyway, in the not-too-distant future, we will probably see artificial scientists who are good at devising experiments that allow them to discover new, previously unknown physical laws. As always, we are going to profit from the old trend that has held at least since 1941: every decade compute is getting 100 times cheaper. Jones: How does this trend affect modern AI such as ChatGPT? Schmidhuber: Perhaps you know that all the recent famous AI applications such as ChatGPT and similar models are largely based on principles of artificial neural networks invented in the previous millennium. The main reason why they works so well now is the incredible acceleration of compute per dollar. ChatGPT is driven by a neural network called “Transformer” described in 2017 by Google. I am happy about that because a quarter century earlier in 1991 I had a particular Transformer variant which is now called the “Transformer with linearized self-attention”. Back then, not much could be done with it, because the compute cost was a million times higher than today. But today, one can train such models on half the internet and achieve much more interesting results. Jones: And for how long will this acceleration continue? Schmidhuber: There's no reason to believe that in the next 30 years, we won't have another factor of 1 million and that's going to be really significant. In the near future, for the first time we will have many not-so expensive devices that can compute as much as a human brain. The physical limits of computation, however, are much further out so even if the trend of a factor of 100 every decade continues, the physical limits (of 1051 elementary instructions per second and kilogram of matter) won’t be hit until, say, the mid-next century. Even in our current century, however, we’ll probably have many machines that compute more than all 10 billion human brains collectively and you can imagine, everything will change then! Jones: That is the big question. Is everything going to change? If so, what do you say to the next generation of leaders, currently coming out of college and university. So much of this change is already impacting how they study, how they will work, or how the future of work and livelihood is defined. What is their purpose and how do we change our systems so they will adapt to this new version of intelligence? Schmidhuber: For decades, people have asked me questions like that, because you know what I'm saying now, I have basically said since the 1970s, it’s just that today, people are paying more attention because, back then, they thought this was science fiction. They didn't think that I would ever come close to achieving my crazy life goal of building a machine that learns to become smarter than myself such that I can retire. But now many have changed their minds and think it's conceivable. And now I have two daughters, 23 and 25. People ask me: what do I tell them? They know that Daddy always said, “It seems likely that within your lifetimes, you will have new types of intelligence that are probably going to be superior in many ways, and probably all kinds of interesting ways.” How should they prepare for that? And I kept telling them the obvious: Learn how to learn new things! It's not like in the previous millennium where within 20 years someone learned to be a useful member of society, and then took a job for 40 years and performed in this job until she received her pension. Now things are changing much faster and we must learn continuously just to keep up. I also told my girls that no matter how smart AIs are going to get, learn at least the basics of math and physics, because that’s the essence of our universe, and anybody who understands this will have an advantage, and learn all kinds of new things more easily. I also told them that social skills will remain important, because most future jobs for humans will continue to involve interactions with other humans, but I couldn’t teach them anything about that; they know much more about social skills than I do. You touched on the big philosophical question about people’s purpose. Can this be answered without answering the even grander question: What’s the purpose of the entire universe? We don’t know. But what’s happening right now might be connected to the unknown answer. Don’t think of humans as the crown of creation. Instead view human civilization as part of a much grander scheme, an important step (but not the last one) on the path of the universe from very simple initial conditions towards more and more unfathomable complexity. Now it seems ready to take its next step, a step comparable to the invention of life itself over 3.5 billion years ago. Alas, don’t worry, in the end, all will be good! Jones: Let’s get back to this transformation happening right now with OpenAI. There are many questioning the efficacy and accuracy of ChatGPT, and are concerned its release has been premature. In light of the rampant adoption, educators have banned its use over concerns of plagiarism and how it stifles individual development. Should large language models like ChatGPT be used in school? Schmidhuber: When the calculator was first introduced, instructors forbade students from using it in school. Today, the consensus is that kids should learn the basic methods of arithmetic, but they should also learn to use the “artificial multipliers” aka calculators, even in exams, because laziness and efficiency is a hallmark of intelligence. Any intelligent being wants to minimize its efforts to achieve things. And that's the reason why we have tools, and why our kids are learning to use these tools. The first stone tools were invented maybe 3.5 million years ago; tools just have become more sophisticated over time. In fact, humans have changed in response to the properties of their tools. Our anatomical evolution was shaped by tools such as spears and fire. So, it's going to continue this way. And there is no permanent way of preventing large language models from being used in school. Jones: And when our children, your children graduate, what does their future work look like? Schmidhuber: A single human trying to predict details of how 10 billion people and their machines will evolve in the future is like a single neuron in my brain trying to predict what the entire brain and its tens of billions of neurons will do next year. 40 years ago, before the WWW was created at CERN in Switzerland, who would have predicted all those young people making money as YouTube video bloggers? Nevertheless, let’s make a few limited job-related observations. For a long time, people have thought that desktop jobs may require more intelligence than skills trade or handicraft professions. But now, it turns out that it's much easier to replace certain aspects of desktop jobs than replacing a carpenter, for example. Because everything that works well in AI is happening behind the screen currently, but not so much in the physical world. There are now artificial systems that can read lots of documents and then make really nice summaries of these documents. That is a desktop job. Or you give them a description of an illustration that you want to have for your article and pretty good illustrations are being generated that may need some minimal fine-tuning. But you know, all these desktop jobs are much easier to facilitate than the real tough jobs in the physical world. And it's interesting that the things people thought required intelligence, like playing chess, or writing or summarizing documents, are much easier for machines than they thought. But for things like playing football or soccer, there is no physical robot that can remotely compete with the abilities of a little boy with these skills. So, AI in the physical world, interestingly, is much harder than AI behind the screen in virtual worlds. And it's really exciting, in my opinion, to see that jobs such as plumbers are much more challenging than playing chess or writing another tabloid story. Jones: The way data has been collected in these large language models does not guarantee personal information has not been excluded. Current consent laws already are outdated when it comes to these large language models (LLM). The concern, rightly so, is increasing surveillance and loss of privacy. What is your view on this? Schmidhuber: As I have indicated earlier: are surveillance and loss of privacy inevitable consequences of increasingly complex societies? Super-organisms such as cities and states and companies consist of numerous people, just like people consist of numerous cells. These cells enjoy little privacy. They are constantly monitored by specialized "police cells" and "border guard cells": Are you a cancer cell? Are you an external intruder, a pathogen? Individual cells sacrifice their freedom for the benefits of being part of a multicellular organism. Similarly, for super-organisms such as nations. Over 5000 years ago, writing enabled recorded history and thus became its inaugural and most important invention. Its initial purpose, however, was to facilitate surveillance, to track citizens and their tax payments. The more complex a super-organism, the more comprehensive its collection of information about its constituents. 200 years ago, at least, the parish priest in each village knew everything about all the village people, even about those who did not confess, because they appeared in the confessions of others. Also, everyone soon knew about the stranger who had entered the village, because some occasionally peered out of the window, and what they saw got around. Such control mechanisms were temporarily lost through anonymization in rapidly growing cities but are now returning with the help of new surveillance devices such as smartphones as part of digital nervous systems that tell companies and governments a lot about billions of users. Cameras and drones etc. are becoming increasingly tinier and more ubiquitous. More effective recognition of faces and other detection technology are becoming cheaper and cheaper, and many will use it to identify others anywhere on earth; the big wide world will not offer any more privacy than the local village. Is this good or bad? Some nations may find it easier than others to justify more complex kinds of super-organisms at the expense of the privacy rights of their constituents. Jones: So, there is no way to stop or change this process of collection, or how it continuously informs decisions over time? How do you see governance and rules responding to this, especially amid Italy’s ban on ChatGPT following suspected user data breach and the more recent news about the Meta’s record $1.3billion fine in the company’s handling of user information? Schmidhuber: Data collection has benefits and drawbacks, such as the loss of privacy. How to balance those? I have argued for addressing this through data ownership in data markets. If it is true that data is the new oil, then it should have a price, just like oil. At the moment, the major surveillance platforms such as Meta do not offer users any money for their data and the transitive loss of privacy. In the future, however, we will likely see attempts at creating efficient data markets to figure out the data's true financial value through the interplay between supply and demand. Even some of the sensitive medical data should not be priced by governmental regulators but by patients (and healthy persons) who own it and who may sell or license parts thereof as micro-entrepreneurs in a healthcare data market. Following a previous interview, I gave for one of the largest re-insurance companies , let's look at the different participants in such a data market: patients, hospitals, data companies. (1) Patients with a rare form of cancer can offer more valuable data than patients with a very common form of cancer. (2) Hospitals and their machines are needed to extract the data, e.g., through magnet spin tomography, radiology, evaluations through human doctors, and so on. (3) Companies such as Siemens, Google or IBM would like to buy annotated data to make better artificial neural networks that learn to predict pathologies and diseases and the consequences of therapies. Now the market’s invisible hand will decide about the data’s price through the interplay between demand and supply. On the demand side, you will have several companies offering something for the data, maybe through an app on the smartphone (a bit like a stock market app). On the supply side, each patient in this market should be able to profit from high prices for rare valuable types of data. Likewise, competing data extractors such as hospitals will profit from gaining recognition and trust for extracting data well at a reasonable price. The market will make the whole system efficient through incentives for all who are doing a good job. Soon there will be a flourishing ecosystem of commercial data market advisors and what not, just like the ecosystem surrounding the traditional stock market. The value of the data won’t be determined by governments or ethics committees, but by those who own the data and decide by themselves which parts thereof they want to license to others under certain conditions. At first glance, a market-based system seems to be detrimental to the interest of certain monopolistic companies, as they would have to pay for the data - some would prefer free data and keep their monopoly. However, since every healthy and sick person in the market would suddenly have an incentive to collect and share their data under self-chosen anonymity conditions, there will soon be many more useful data to evaluate all kinds of treatments. On average, people will live longer and healthier, and many companies and the entire healthcare system will benefit. Jones: Finally, what is your view on open source versus the private companies like Google and OpenAI? Is there a danger to supporting these private companies’ large language models versus trying to keep these models open source and transparent, very much like what LAION is doing? Schmidhuber: I signed this open letter by LAION because I strongly favor the open-source movement. And I think it's also something that is going to challenge whatever big tech dominance there might be at the moment. Sure, the best models today are run by big companies with huge budgets for computers, but the exciting fact is that open-source models are not so far behind, some people say maybe six to eight months only. Of course, the private company models are all based on stuff that was created in academia, often in little labs without so much funding, which publish without patenting their results and open source their code and others take it and improved it. Big tech has profited tremendously from academia; their main achievement being that they have scaled up everything greatly, sometimes even failing to credit the original inventors. So, it's very interesting to see that as soon as some big company comes up with a new scaled-up model, lots of students out there are competing, or collaborating, with each other, trying to come up with equal or better performance on smaller networks and smaller machines. And since they are open sourcing, the next guy can have another great idea to improve it, so now there’s tremendous competition also for the big companies. Because of that, and since AI is still getting exponentially cheaper all the time, I don't believe that big tech companies will dominate in the long run. They find it very hard to compete with the enormous open-source movement. As long as you can encourage the open-source community, I think you shouldn't worry too much. Now, of course, you might say if everything is open source, then the bad actors also will more easily have access to these AI tools. And there's truth to that. But as always since the invention of controlled fire, it was good that knowledge about how technology works quickly became public such that everybody could use it. And then, against any bad actor, there's almost immediately a counter actor trying to nullify his efforts. You see, I still believe in our old motto "AI∀" or "AI For All." Jones: Thank you, Juergen for sharing your perspective on this amazing time in history. It’s clear that with new technology, the enormous potential can be matched by disparate and troubling risks which we’ve yet to solve, and even those we have yet to identify. If we are to dispel the fear of a sentient system for which we have no control, humans, alone need to take steps for more responsible development and collaboration to ensure AI technology is used to ultimately benefit society. Humanity will be judged by what we do next.

[N] Inside DeepMind's secret plot to break away from Google

Article https://www.businessinsider.com/deepmind-secret-plot-break-away-from-google-project-watermelon-mario-2021-9 by Hugh Langley and Martin Coulter For a while, some DeepMind employees referred to it as "Watermelon." Later, executives called it "Mario." Both code names meant the same thing: a secret plan to break away from parent company Google. DeepMind feared Google might one day misuse its technology, and executives worked to distance the artificial-intelligence firm from its owner for years, said nine current and former employees who were directly familiar with the plans. This included plans to pursue an independent legal status that would distance the group's work from Google, said the people, who asked not to be identified discussing private matters. One core tension at DeepMind was that it sold the business to people it didn't trust, said one former employee. "Everything that happened since that point has been about them questioning that decision," the person added. Efforts to separate DeepMind from Google ended in April without a deal, The Wall Street Journal reported. The yearslong negotiations, along with recent shake-ups within Google's AI division, raise questions over whether the search giant can maintain control over a technology so crucial to its future. "DeepMind's close partnership with Google and Alphabet since the acquisition has been extraordinarily successful — with their support, we've delivered research breakthroughs that transformed the AI field and are now unlocking some of the biggest questions in science," a DeepMind spokesperson said in a statement. "Over the years, of course we've discussed and explored different structures within the Alphabet group to find the optimal way to support our long-term research mission. We could not be prouder to be delivering on this incredible mission, while continuing to have both operational autonomy and Alphabet's full support." When Google acquired DeepMind in 2014, the deal was seen as a win-win. Google got a leading AI research organization, and DeepMind, in London, won financial backing for its quest to build AI that can learn different tasks the way humans do, known as artificial general intelligence. But tensions soon emerged. Some employees described a cultural conflict between researchers who saw themselves firstly as academics and the sometimes bloated bureaucracy of Google's colossal business. Others said staff were immediately apprehensive about putting DeepMind's work under the control of a tech giant. For a while, some employees were encouraged to communicate using encrypted messaging apps over the fear of Google spying on their work. At one point, DeepMind's executives discovered that work published by Google's internal AI research group resembled some of DeepMind's codebase without citation, one person familiar with the situation said. "That pissed off Demis," the person added, referring to Demis Hassabis, DeepMind's CEO. "That was one reason DeepMind started to get more protective of their code." After Google restructured as Alphabet in 2015 to give riskier projects more freedom, DeepMind's leadership started to pursue a new status as a separate division under Alphabet, with its own profit and loss statement, The Information reported. DeepMind already enjoyed a high level of operational independence inside Alphabet, but the group wanted legal autonomy too. And it worried about the misuse of its technology, particularly if DeepMind were to ever achieve AGI. Internally, people started referring to the plan to gain more autonomy as "Watermelon," two former employees said. The project was later formally named "Mario" among DeepMind's leadership, these people said. "Their perspective is that their technology would be too powerful to be held by a private company, so it needs to be housed in some other legal entity detached from shareholder interest," one former employee who was close to the Alphabet negotiations said. "They framed it as 'this is better for society.'" In 2017, at a company retreat at the Macdonald Aviemore Resort in Scotland, DeepMind's leadership disclosed to employees its plan to separate from Google, two people who were present said. At the time, leadership said internally that the company planned to become a "global interest company," three people familiar with the matter said. The title, not an official legal status, was meant to reflect the worldwide ramifications DeepMind believed its technology would have. Later, in negotiations with Google, DeepMind pursued a status as a company limited by guarantee, a corporate structure without shareholders that is sometimes used by nonprofits. The agreement was that Alphabet would continue to bankroll the firm and would get an exclusive license to its technology, two people involved in the discussions said. There was a condition: Alphabet could not cross certain ethical redlines, such as using DeepMind technology for military weapons or surveillance. In 2019, DeepMind registered a new company called DeepMind Labs Limited, as well as a new holding company, filings with the UK's Companies House showed. This was done in anticipation of a separation from Google, two former employees involved in those registrations said. Negotiations with Google went through peaks and valleys over the years but gained new momentum in 2020, one person said. A senior team inside DeepMind started to hold meetings with outside lawyers and Google to hash out details of what this theoretical new formation might mean for the two companies' relationship, including specifics such as whether they would share a codebase, internal performance metrics, and software expenses, two people said. From the start, DeepMind was thinking about potential ethical dilemmas from its deal with Google. Before the 2014 acquisition closed, both companies signed an "Ethics and Safety Review Agreement" that would prevent Google from taking control of DeepMind's technology, The Economist reported in 2019. Part of the agreement included the creation of an ethics board that would supervise the research. Despite years of internal discussions about who should sit on this board, and vague promises to the press, this group "never existed, never convened, and never solved any ethics issues," one former employee close to those discussions said. A DeepMind spokesperson declined to comment. DeepMind did pursue a different idea: an independent review board to convene if it were to separate from Google, three people familiar with the plans said. The board would be made up of Google and DeepMind executives, as well as third parties. Former US president Barack Obama was someone DeepMind wanted to approach for this board, said one person who saw a shortlist of candidates. DeepMind also created an ethical charter that included bans on using its technology for military weapons or surveillance, as well as a rule that its technology should be used for ways that benefit society. In 2017, DeepMind started a unit focused on AI ethics research composed of employees and external research fellows. Its stated goal was to "pave the way for truly beneficial and responsible AI." A few months later, a controversial contract between Google and the Pentagon was disclosed, causing an internal uproar in which employees accused Google of getting into "the business of war." Google's Pentagon contract, known as Project Maven, "set alarm bells ringing" inside DeepMind, a former employee said. Afterward, Google published a set of principles to govern its work in AI, guidelines that were similar to the ethical charter that DeepMind had already set out internally, rankling some of DeepMind's senior leadership, two former employees said. In April, Hassabis told employees in an all-hands meeting that negotiations to separate from Google had ended. DeepMind would maintain its existing status inside Alphabet. DeepMind's future work would be overseen by Google's Advanced Technology Review Council, which includes two DeepMind executives, Google's AI chief Jeff Dean, and the legal SVP Kent Walker. But the group's yearslong battle to achieve more independence raises questions about its future within Google. Google's commitment to AI research has also come under question, after the company forced out two of its most senior AI ethics researchers. That led to an industry backlash and sowed doubt over whether it could allow truly independent research. Ali Alkhatib, a fellow at the Center for Applied Data Ethics, told Insider that more public accountability was "desperately needed" to regulate the pursuit of AI by large tech companies. For Google, its investment in DeepMind may be starting to pay off. Late last year, DeepMind announced a breakthrough to help scientists better understand the behavior of microscopic proteins, which has the potential to revolutionize drug discovery. As for DeepMind, Hassabis is holding on to the belief that AI technology should not be controlled by a single corporation. Speaking at Tortoise's Responsible AI Forum in June, he proposed a "world institute" of AI. Such a body might sit under the jurisdiction of the United Nations, Hassabis theorized, and could be filled with top researchers in the field. "It's much stronger if you lead by example," he told the audience, "and I hope DeepMind can be part of that role-modeling for the industry."

[D] How Facebook got addicted to spreading misinformation

Behind paywall: With new machine-learning models coming online daily, the company created a new system to track their impact and maximize user engagement. The process is still the same today. Teams train up a new machine-learning model on FBLearner, whether to change the ranking order of posts or to better catch content that violates Facebook’s community standards (its rules on what is and isn’t allowed on the platform). Then they test the new model on a small subset of Facebook’s users to measure how it changes engagement metrics, such as the number of likes, comments, and shares, says Krishna Gade, who served as the engineering manager for news feed from 2016 to 2018. If a model reduces engagement too much, it’s discarded. Otherwise, it’s deployed and continually monitored. On Twitter, Gade explained that his engineers would get notifications every few days when metrics such as likes or comments were down. Then they’d decipher what had caused the problem and whether any models needed retraining. But this approach soon caused issues. The models that maximize engagement also favor controversy, misinformation, and extremism: put simply, people just like outrageous stuff. Sometimes this inflames existing political tensions. The most devastating example to date is the case of Myanmar, where viral fake news and hate speech about the Rohingya Muslim minority escalated the country’s religious conflict into a full-blown genocide. Facebook admitted in 2018, after years of downplaying its role, that it had not done enough “to help prevent our platform from being used to foment division and incite offline violence.” While Facebook may have been oblivious to these consequences in the beginning, it was studying them by 2016. In an internal presentation from that year, reviewed by the Wall Street Journal, a company researcher, Monica Lee, found that Facebook was not only hosting a large number of extremist groups but also promoting them to its users: “64% of all extremist group joins are due to our recommendation tools,” the presentation said, predominantly thanks to the models behind the “Groups You Should Join” and “Discover” features. https://www.technologyreview.com/2021/03/11/1020600/facebook-responsible-ai-misinformation/

[Discussion] When ML and Data Science are the death of a good company: A cautionary tale.

TD;LR: At Company A, Team X does advanced analytics using on-prem ERP tools and older programming languages. Their tools work very well and are designed based on very deep business and domain expertise. Team Y is a new and ambitious Data Science team that thinks they can replace Team X's tools with a bunch of R scripts and a custom built ML platform. Their models are simplistic, but more "fashionable" compared to the econometric models used by Team X, and team Y benefits from the ML/DS moniker so leadership is allowing Team Y to start a large scale overhaul of the analytics platform in question. Team Y doesn't have the experience for such a larger scale transformation, and is refusing to collaborate with team X. This project is very likely going to fail, and cause serious harm to the company as a whole financially and from a people perspective. I argue that this is not just because of bad leadership, but also because of various trends and mindsets in the DS community at large. Update (Jump to below the line for the original story): Several people in the comments are pointing out that this just a management failure, not something due to ML/DS, and that you can replace DS with any buzz tech and the story will still be relevant. My response: Of course, any failure at an organization level is ultimately a management failure one way or the other. Moreover, it is also the case that ML/DS when done correctly, will always improve a company's bottom line. There is no scenario where the proper ML solution, delivered at a reasonable cost and in a timely fashion, will somehow hurt the company's bottom line. My point is that in this case management is failing because of certain trends and practices that are specific to the ML/DS community, namely: The idea that DS teams should operate independently of tech and business orgs -- too much autonomy for DS teams The disregard for domain knowledge that seems prevalent nowadays thanks to the ML hype, that DS can be generalists and someone with good enough ML chops can solve any business problem. That wasn't the case when I first left academia for the industry in 2009 (back then nobody would even bother with a phone screen if you didn't have the right domain knowledge). Over reliance on resources who check all the ML hype related boxes (knows Python, R, Tensorflow, Shiny, etc..., has the right Coursera certifications, has blogged on the topic, etc...), but are lacking in depth of experience. DS interviews nowadays all seem to be: Can you tell me what a p-value is? What is elastic net regression? Show me how to fit a model in sklearn? How do you impute NAs in an R dataframe? Any smart person can look those up on Stackoverflow or Cross-Validated,.....Instead teams should be asking stuff like: why does portfolio optimization use QP not LP? How does a forecast influence a customer service level? When should a recommendation engine be content based and when should it use collaborative filtering? etc... (This is a true story, happening to the company I currently work for. Names, domains, algorithms, and roles have been shuffled around to protect my anonymity)  Company A has been around for several decades. It is not the biggest name in its domain, but it is a well respected one. Risk analysis and portfolio optimization have been a core of Company A's business since the 90s. They have a large team of 30 or so analysts who perform those tasks on a daily basis. These analysts use ERP solutions implemented for them by one the big ERP companies (SAP, Teradata, Oracle, JD Edwards,...) or one of the major tech consulting companies (Deloitte, Accenture, PWC, Capgemini, etc...) in collaboration with their own in house engineering team. The tools used are embarrassingly old school: Classic RDBMS running on on-prem servers or maybe even on mainframes, code written in COBOL, Fortran, weird proprietary stuff like ABAP or SPSS.....you get the picture. But the models and analytic functions were pretty sophisticated, and surprisingly cutting edge compared to the published academic literature. Most of all, they fit well with the company's enterprise ecosystem, and were honed based on years of deep domain knowledge.  They have a tech team of several engineers (poached from the aforementioned software and consulting companies) and product managers (who came from the experienced pools of analysts and managers who use the software, or poached from business rivals) maintaining and running this software. Their technology might be old school, but collectively, they know the domain and the company's overall architecture very, very well. They've guided the company through several large scale upgrades and migrations and they have a track record of delivering on time, without too much overhead. The few times they've stumbled, they knew how to pick themselves up very quickly. In fact within their industry niche, they have a reputation for their expertise, and have very good relations with the various vendors they've had to deal with. They were the launching pad of several successful ERP consulting careers.  Interestingly, despite dealing on a daily basis with statistical modeling and optimization algorithms, none of the analysts, engineers, or product managers involved describe themselves as data scientists or machine learning experts. It is mostly a cultural thing: Their expertise predates the Data Science/ML hype that started circa 2010, and they got most of their chops using proprietary enterprise tools instead of the open source tools popular nowadays. A few of them have formal statistical training, but most of them came from engineering or domain backgrounds and learned stats on the fly while doing their job. Call this team "Team X".  Sometime around the mid 2010s, Company A started having some serious anxiety issues: Although still doing very well for a company its size, overall economic and demographic trends were shrinking its customer base, and a couple of so called disruptors came up with a new app and business model that started seriously eating into their revenue. A suitable reaction to appease shareholders and Wall Street was necessary. The company already had a decent website and a pretty snazzy app, what more could be done? Leadership decided that it was high time that AI and ML become a core part of the company's business. An ambitious Manager, with no science or engineering background, but who had very briefly toyed with a recommender system a couple of years back, was chosen to build a data science team, call it team "Y" (he had a bachelor's in history from the local state college and worked for several years in the company's marketing org). Team "Y" consists mostly of internal hires who decided they wanted to be data scientists and completed a Coursera certification or a Galvanize boot camp, before being brought on to the team, along with a few of fresh Ph.D or M.Sc holders who didn't like academia and wanted to try their hand at an industry role. All of them were very bright people, they could write great Medium blog posts and give inspiring TED talks, but collectively they had very little real world industry experience. As is the fashion nowadays, this group was made part of a data science org that reported directly to the CEO and Board, bypassing the CIO and any tech or business VPs, since Company A wanted to claim the monikers "data driven" and "AI powered" in their upcoming shareholder meetings. In 3 or 4 years of existence, team Y produced a few Python and R scripts. Their architectural experience  consisted almost entirely in connecting Flask to S3 buckets or Redshift tables, with a couple of the more resourceful ones learning how to plug their models into Tableau or how to spin up a Kuberneties pod.  But they needn't worry: The aforementioned manager, who was now a director (and was also doing an online Masters to make up for his qualifications gap and bolster his chances of becoming VP soon - at least he now understands what L1 regularization is), was a master at playing corporate politics and self-promotion. No matter how few actionable insights team Y produced or how little code they deployed to production, he always had their back and made sure they had ample funding. In fact he now had grandiose plans for setting up an all-purpose machine learning platform that can be used to solve all of the company's data problems.  A couple of sharp minded members of team Y, upon googling their industry name along with the word "data science", realized that risk analysis was a prime candidate for being solved with Bayesian models, and there was already a nifty R package for doing just that, whose tutorial they went through on R-Bloggers.com. One of them had even submitted a Bayesian classifier Kernel for a competition on Kaggle (he was 203rd on the leaderboard), and was eager to put his new-found expertise to use on a real world problem. They pitched the idea to their director, who saw a perfect use case for his upcoming ML platform. They started work on it immediately, without bothering to check whether anybody at Company A was already doing risk analysis. Since their org was independent, they didn't really need to check with anybody else before they got funding for their initiative. Although it was basically a Naive Bayes classifier, the term ML was added to the project tile, to impress the board.  As they progressed with their work however, tensions started to build. They had asked the data warehousing and CA analytics teams to build pipelines for them, and word eventually got out to team X about their project. Team X was initially thrilled: They offered to collaborate whole heartedly, and would have loved to add an ML based feather to their already impressive cap. The product owners and analysts were totally onboard as well: They saw a chance to get in on the whole Data Science hype that they kept hearing about. But through some weird mix of arrogance and insecurity, team Y refused to collaborate with them or share any of their long term goals with them, even as they went to other parts of the company giving brown bag presentations and tutorials on the new model they created.  Team X got resentful: from what they saw of team Y's model, their approach was hopelessly naive and had little chances of scaling or being sustainable in production, and they knew exactly how to help with that. Deploying the model to production would have taken them a few days, given how comfortable they were with DevOps and continuous delivery (team Y had taken several months to figure out how to deploy a simple R script to production). And despite how old school their own tech was, team X were crafty enough to be able to plug it in to their existing architecture. Moreover, the output of the model was such that it didn't take into account how the business will consume it or how it was going to be fed to downstream systems, and the product owners could have gone a long way in making the model more amenable to adoption by the business stakeholders. But team Y wouldn't listen, and their leads brushed off any attempts at communication, let alone collaboration. The vibe that team Y was giving off was "We are the cutting edge ML team, you guys are the legacy server grunts. We don't need your opinion.", and they seemed to have a complete disregard for domain knowledge, or worse, they thought that all that domain knowledge consisted of was being able to grasp the definitions of a few business metrics.  Team X got frustrated and tried to express their concerns to leadership. But despite owning a vital link in Company A's business process, they were only \~50 people in a large 1000 strong technology and operations org, and they were several layers removed from the C-suite, so it was impossible for them to get their voices heard.  Meanwhile, the unstoppable director was doing what he did best: Playing corporate politics. Despite how little his team had actually delivered, he had convinced the board that all analysis and optimization tasks should now be migrated to his yet to be delivered ML platform. Since most leaders now knew that there was overlap between team Y and team X's objectives, his pitch was no longer that team Y was going to create a new insight, but that they were going to replace (or modernize) the legacy statistics based on-prem tools with more accurate cloud based ML tools. Never mind that there was no support in the academic literature for the idea that Naive Bayes works better than the Econometric approaches used by team X, let alone the additional wacky idea that Bayesian Optimization would definitely outperform the QP solvers that were running in production.  Unbeknownst to team X, the original Bayesian risk analysis project has now grown into a multimillion dollar major overhaul initiative, which included the eventual replacement of all of the tools and functions supported by team X along with the necessary migration to the cloud. The CIO and a couple of business VPs are on now board, and tech leadership is treating it as a done deal. An outside vendor, a startup who nobody had heard of, was contracted to help build the platform, since team Y has no engineering skills. The choice was deliberate, as calling on any of the established consulting or software companies would have eventually led leadership to the conclusion that team X was better suited for a transformation on this scale than team Y.  Team Y has no experience with any major ERP deployments, and no domain knowledge, yet they are being tasked with fundamentally changing the business process that is at the core of Company A's business. Their models actually perform worse than those deployed by team X, and their architecture is hopelessly simplistic, compared to what is necessary for running such a solution in production.  Ironically, using Bayesian thinking and based on all the evidence, the likelihood that team Y succeeds is close to 0%. At best, the project is going to end up being a write off of 50 million dollars or more. Once the !@#$!@hits the fan, a couple of executive heads are going to role, and dozens of people will get laid off. At worst, given how vital risk analysis and portfolio optimization is to Company A's revenue stream, the failure will eventually sink the whole company. It probably won't go bankrupt, but it will lose a significant portion of its business and work force. Failed ERP implementations can and do sink large companies: Just see what happened to National Grid US, SuperValu or Target Canada.  One might argue that this is more about corporate disfunction and bad leadership than about data science and AI. But I disagree. I think the core driver of this debacle is indeed the blind faith in Data Scientists, ML models and the promise of AI, and the overall culture of hype and self promotion that is very common among the ML crowd.  We haven't seen the end of this story: I sincerely hope that this ends well for the sake of my colleagues and all involved. Company A is a good company, and both its customers and its employees deserver better. But the chances of that happening are negligible given all the information available, and this failure will hit my company hard.

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

[D] Working with Various OpenAI Models - My Thoughts and Experiences

I'd like to share some of my insights from working with OpenAI models on my project. I'm not exactly a tech person, so some of these observations might be obvious to some of you, but I think they're worth sharing for those with less experience or who aren't directly in the field. Intro: In early February, my friends and I started a side project where we aimed to build an AI portal called DoMoreAI. For the first two months, we focused on creating an AI tools catalog. Our experiment is based on the idea that in the future, companies will be "Managed by AI, and Driven by Humans." So, our goal was to leave as much as possible to AI and automation, with all the consequences that come with it. As mentioned before, I'm not a tech guy, but I've been playing with OpenAI models for the past few years, so I had some experience when starting this project. Tasks We Assigned to AI: Based on an AI tool's front page, we had the AI write a one-sentence summary of an AI project + write a more in-depth review of the project, categorize the project into different categories (WHAT category, like blog; TASK category, like writing; FOR category, like content creator), decide if the project offers iOS app, Android app, browser extension, API, find social media links, process information about prices and pricing policy, and more. Interesting Findings: When working on a more complex prompt, particularly one with several tasks, you have to be patient when crafting it. You might eventually find the right wording to achieve the desired results, but it takes time and lots of trial and error. You might even be surprised by what works and what doesn't. If cost isn't an issue, you can always break up one complex prompt into several smaller prompts. However, the more requests you send, the higher the chance of encountering errors like the 429 error, which may require setting up more sophisticated error handlers for the whole process. You need error handlers because, without them, the automation process will suffer. With more complex prompts, there are no prompts that always yield the expected results, so you have to plan for what to do if the results aren't satisfactory and how to determine if the result meets your expectations or not. GPT-3.0 struggled with outputting JSON strings as requested, but GPT-3.5 is much better at this task. I'd say the number of errors from improperly formatting the response in JSON is 3-4 times lower for GPT-3.5. AI models have trouble distinguishing words singular forms from plural forms. Just because you can use AI for a given task doesn't mean you should. Often, standard techniques like using regex can yield better results when extracting something from text than relying solely on AI. A hybrid solution often provides the best results. We're using ADA vector embeddings and Pinecone for semantic search in our catalog, and I was really surprised to find that this kind of semantic search works in any language. Even if all the content on our page is in English, you can search in another language and still get decent results. The Best Mishaps: As you may know, there's a token limit for requests, so we have to ensure that we don't send too long a part of the front page to the model. Sometimes, this led to funny situations. If the HTML of the page consists mainly of styles and the model is fed only with styles, then when you ask the AI to write a review of the project, it writes about how beautiful, mobile-friendly, etc., the project is. For one project, instead of writing the one-sentence summary, the model's output only included the prompt we were using to generate the summary (needless to say, it was automatically published on our website ;)) &#x200B; I hope this post will be useful. We are currently running a campaign on Product Hunt: https://www.producthunt.com/posts/domore-ai So, if you have any feedback for us or think what we're doing is cool, don't hesitate to support us :)

[Dataset][R] 19,762 Garbage Images for Building AI Recycling Solutions

Hi ML community! I’m excited to share the Garbage Classification V2 Dataset, featuring 19,762 high-quality images of garbage categorized into 10 distinct classes (e.g., metal, plastic, clothes, and paper). Why this matters: Train AI models for automated waste sorting and recycling. Develop waste segregation apps or sustainability-focused tools. Create innovative computer vision projects for environmental impact. 🔗 Dataset Link: Garbage Classification V2 This dataset has been used in the research paper, "Managing Household Waste Through Transfer Learning," proving its utility in real-world applications. Looking forward to seeing how you can use it to promote sustainability!

[D] Last Week in Medical AI: Top LLM Research Papers/Models (December 7 - December 14, 2024)

[\[D\] Last Week in Medical AI: Top LLM Research Papers\/Models \(December 7 - December 14, 2024\)](https://preview.redd.it/o23fp3csj07e1.jpg?width=1280&format=pjpg&auto=webp&s=69e19fc351b3aa5e34c4c00e66245583f88bd9bb) Medical LLM & Other Models PediaBench: Chinese Pediatric LLM This paper introduces PediaBench, the first Chinese pediatric dataset for evaluating Large Language Model (LLM) question-answering performance, containing 4,565 objective and 1,632 subjective questions across 12 disease groups. BiMediX: Bilingual Medical LLM This paper introduces BiMediX, the first bilingual (English-Arabic) medical Mixture of Experts LLM, along with BiMed1.3M, a 1.3M bilingual medical instruction dataset with over 632M tokens used for training. Diverse medical knowledge integration This paper introduces BiMediX2, a bilingual (Arabic-English) Large Multimodal Model (LMM) based on Llama3.1 architecture, trained on 1.6M medical interaction samples. BRAD: Digital Biology Language Model This paper introduces BRAD (Bioinformatics Retrieval Augmented Digital assistant), an LLM-powered chatbot and agent system integrating various bioinformatics tools. MMedPO: Vision-Language Medical LLM This paper introduces MMedPO, a multimodal medical preference optimization approach to improve factual accuracy in Medical Large Vision-Language Models (Med-LVLMs) by addressing modality misalignment. Frameworks & Methodologies \- TOP-Training: Medical Q&A Framework \- Hybrid RAG: Secure Medical Data Management \- Zero-Shot ATC Clinical Coding \- Chest X-Ray Diagnosis Architecture \- Medical Imaging AI Democratization Benchmarks & Evaluations \- KorMedMCQA: Korean Healthcare Licensing Benchmark \- Large Language Model Medical Tasks \- Clinical T5 Model Performance Study \- Radiology Report Quality Assessment \- Genomic Analysis Benchmarking LLM Applications \- TCM-FTP: Herbal Prescription Prediction \- LLaSA: Activity Analysis via Sensors \- Emergency Department Visit Predictions \- Neurodegenerative Disease AI Diagnosis \- Kidney Disease Explainable AI Model Ethical AI & Privacy \- Privacy-Preserving LLM Mechanisms \- AI-Driven Digital Organism Modeling \- Biomedical Research Automation \- Multimodality in Medical Practice Full thread in detail: https://x.com/OpenlifesciAI/status/1867999825721242101

[N] Last Week in AI News Digest - Automated chemical synthesis, using heartbeats to detect deepfakes, and more!

Hi there, just sharing the latest edition of our AI news digest newsletter! We're just a couple of AI grad students doing this for fun, so hope the self promotion is not too annoying (also, welcome feedback). See it below, and feel free to subscribe. Mini Briefs Robotics, AI, and Cloud Computing Combine to Supercharge Chemical and Drug Synthesis IBM recently demoed a complex system for chemical testing and drug synthesis. The system has an AI component that predicts the results of chemical reactions, and a fully automated robotic experiment setup that runs chemical tests 24/7. Users can access the remote robotics lab online, and IBM can also install the system on-premise. With these tools working together, IBM is hoping to reduce typical drug discovery and verification time by half. AI researchers use heartbeat detection to identify deepfake videos Researchers from multiple groups are tackling the challenge of detecting deepfake videos by analyzing the apparent heartbeat of the people depicted in the video. This is possible, because a person’s blood flow changes their skin color ever so slightly, and this change is often detectable via a process called photoplethysmography (PPG). Because deepfakes are not currently optimizing to generate realisitic heartbeats, temporal or spatial anomalies in PPG signals allow resesarchers to detect deepfakes with a 97% accuracy. Advances & Business This AI Expert From Senegal Is Helping Showcase Africans In STEM \- Adji Bousso Dieng will be Princeton’s School of Engineering’s first Black female faculty. Google’s AI-powered flood alerts now cover all of India and parts of Bangladesh \- India, the world’s second most populated nation, sees more than 20% of the global flood-related fatalities each year as overrun riverbanks sweep tens of thousands of homes with them. Two years ago, Google volunteered to help. Finding magnetic eruptions in space with an AI assistant \- MMS look for explosive reconnection events as it flies through the magnetopause - the boundary region where Earth’s magnetic butts up against the solar wind that flows throughout the solar system. This know-it-all AI learns by reading the entire web nonstop \- Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. Bosch and Ford will test autonomous parking in Detroit \- Ford, Bosch, and Dan Gilbert’s real estate firm Bedrock today detailed an autonomous parking pilot scheduled to launch in September at The Assembly, a mixed-used building in Detroit’s Corktown neighborhood. Create your own moody quarantine music with Google’s AI \- Lo-Fi Player, the latest project out of Google Magenta, lets you mix tunes with the help of machine learning by interacting with a virtual room. Apple launches AI/ML residency program to attract niche experts \- As Apple’s artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown - a theme that’s barely under the surface of the company’s occasionally updated Machine Learning Research blog. Dusty Robotics CEO Tessa Lau Discusses Robotics Start-Ups and Autonomous Robots for Construction \- Tessa Lau is Founder/CEO at Dusty Robotics, whose mission is to increase construction industry productivity by introducing robotic automation on the jobsite. Concerns & Hype Google Offers to Help Others With the Tricky Ethics of AI \- Companies pay cloud computing providers like Amazon, Microsoft, and Google big money to avoid operating their own digital infrastructure. The Peace Dividends Of The Autonomous Vehicle Wars \- The rapid growth of the mobile market in the late 2000s and early 2010s led to a burst of technological progress. Ethics must be part of the development process’ \- The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. Analysis & Policy China’s new AI trade rules could hamper a TikTok sale \- TikTok’s attempt to sell itself and avert a possible US ban may run into some complications. The Wall Street Journal reports that China has unveiled new restrictions on AI technology exports that could affect TikTok. Podcast Check out our weekly podcast covering these stories! Website | RSS | iTunes | Spotify | YouTube

[P] Utilizing graph attention-based neural networks and generative AI to build a tool to automate debugging and refactoring Python code

For the last two years, I and three others have been working on a project we started in a research lab. The project is to create a tool that can automatically identify complex programming errors from source code that require a contextual understanding of the code. For this, we have built a graph attention-based neural network that is used to classify problematic code and embed context info. We employ a two-stage system for accurately embedding context information within a single graph. First, we split up the source code into semantic tokens through an nlp2 tokenizer and generate 80-bit vector embeddings using FastText, which has been trained on code snippets of a particular language. We then map those text tokens to groupings identified in the abstract syntax tree, excluding the individual nodes for each text token, opting instead for the function call with attributes as the smallest individual grouping, averaging the embeddings across each token type. The seed data for the system consists of code changes and their surrounding documentation on why a given code change was made. For this, we utilize a BERTopic-based topic modeling system to identify and categorize the reason why the given change was made from the docs. For the explanations and code recommendations, we utilize generative AI models. They are promising for this purpose as we are able to pass enriched context to them along with the problematic code, hoping to receive more accurate outputs. We are just looking for feedback on if the project currently provides any value to Python users. We've published the first version of the tool on vscode marketplace. It's of course free to use, and we'd appreciate any feedback on it. As it's not a weekend, let me know if you are interested to try the tool and give us your thoughts on it.

[D] What is your honest experience with reinforcement learning?

In my personal experience, SOTA RL algorithms simply don't work. I've tried working with reinforcement learning for over 5 years. I remember when Alpha Go defeated the world famous Go player, Lee Sedol, and everybody thought RL would take the ML community by storm. Yet, outside of toy problems, I've personally never found a practical use-case of RL. What is your experience with it? Aside from Ad recommendation systems and RLHF, are there legitimate use-cases of RL? Or, was it all hype? Edit: I know a lot about AI. I built NexusTrade, an AI-Powered automated investing tool that lets non-technical users create, update, and deploy their trading strategies. I’m not an idiot nor a noob; RL is just ridiculously hard. Edit 2: Since my comments are being downvoted, here is a link to my article that better describes my position. It's not that I don't understand RL. I released my open-source code and wrote a paper on it. It's the fact that it's EXTREMELY difficult to understand. Other deep learning algorithms like CNNs (including ResNets), RNNs (including GRUs and LSTMs), Transformers, and GANs are not hard to understand. These algorithms work and have practical use-cases outside of the lab. Traditional SOTA RL algorithms like PPO, DDPG, and TD3 are just very hard. You need to do a bunch of research to even implement a toy problem. In contrast, the decision transformer is something anybody can implement, and it seems to match or surpass the SOTA. You don't need two networks battling each other. You don't have to go through hell to debug your network. It just naturally learns the best set of actions in an auto-regressive manner. I also didn't mean to come off as arrogant or imply that RL is not worth learning. I just haven't seen any real-world, practical use-cases of it. I simply wanted to start a discussion, not claim that I know everything. Edit 3: There's a shockingly number of people calling me an idiot for not fully understanding RL. You guys are wayyy too comfortable calling people you disagree with names. News-flash, not everybody has a PhD in ML. My undergraduate degree is in biology. I self-taught myself the high-level maths to understand ML. I'm very passionate about the field; I just have VERY disappointing experiences with RL. Funny enough, there are very few people refuting my actual points. To summarize: Lack of real-world applications Extremely complex and inaccessible to 99% of the population Much harder than traditional DL algorithms like CNNs, RNNs, and GANs Sample inefficiency and instability Difficult to debug Better alternatives, such as the Decision Transformer Are these not legitimate criticisms? Is the purpose of this sub not to have discussions related to Machine Learning? To the few commenters that aren't calling me an idiot...thank you! Remember, it costs you nothing to be nice! Edit 4: Lots of people seem to agree that RL is over-hyped. Unfortunately those comments are downvoted. To clear up some things: We've invested HEAVILY into reinforcement learning. All we got from this investment is a robot that can be super-human at (some) video games. AlphaFold did not use any reinforcement learning. SpaceX doesn't either. I concede that it can be useful for robotics, but still argue that it's use-cases outside the lab are extremely limited. If you're stumbling on this thread and curious about an RL alternative, check out the Decision Transformer. It can be used in any situation that a traditional RL algorithm can be used. Final Edit: To those who contributed more recently, thank you for the thoughtful discussion! From what I learned, model-based models like Dreamer and IRIS MIGHT have a future. But everybody who has actually used model-free models like DDPG unanimously agree that they suck and don’t work.

[D] Is this close enough to be usable? Need your inputs: Automated RAG testing tool. AI Data Pipelines for Real-World Production (Part 3)

Hey there, Redditors! I'm back with the latest installment on creating dependable AI data pipelines for real-world production. If you've been following along, you know I'm on a mission to move beyond the "thin OpenAI wrapper" trend and tackle the challenges of building robust data pipelines. With 18 months of hands-on experience and many user interviews, I realized that with the probabilistic nature of systems, we need better\_testing.gpt: As you build you should test The world of AI is a fast-moving one, and we've realized that just working on systems is not an optimal design choice. By the time your product ships, it might already be using outdated technology. So, what's the lesson here? Embrace change, test along, but be prepared to switch pace. No Best Practices Yet for RAGs In this rapidly evolving landscape, there are no established best practices. You'll need to make educated bets on tools and processes, knowing that things will change. With the RAG testing tool, I tried allowing for testing many potential parameter combinations automatically Testing Frameworks If your generative AI product doesn't have users giving feedback, then you are building in isolation. I used Deepeval to generate test sets, and they will soon support synthetic test set generation Infographics only go so far AI researchers and data scientists, while brilliant, end up in a loop of pursuing Twitter promotional content. New ways are promoted via new content pieces, but ideally, we need something above simple tracing but less than full-fledged analytics. To do this, I stored test outputs in Postgres and created a Superset instance to visualize the results Bridging the Gap between VectorDBs There's a noticeable number of Vector DBs. To ensure smooth product development, we need to be able to switch to best best-performing one, especially since user interviews signal that they might start deteriorating after loading 50 million rows &#x200B; Github repo is here Next steps: I have questions for you: What variables do you change when building RAGs? What is the set of strategies I should add to the solution? (parent-son etc.) How can I improve it in general? Is anyone interested in a leaderboard for best parameter configs? Check out the blog post: Link to part 3 Remember to give this post an upvote if you found it insightful! And also star our Github repo

Best AI tools that detect blurry images? Not correct them, literally just flag them as blurry (so I can delete them programmatically) [D]

I literally just need some kind of automated tool that can detect if an image is blurry -- because if so, my plan is to programmatically delete them as part of a workflow. What are some of the best AI tools that can be used for this? Thanks!

I tested hundreds of marketing tools in the last three years and these 50 made it to the list. I'll sum up my top 50 marketing tools with one or two sentences + give you pricings.

Hey guys, I'm working in a growth marketing agency. Marketing tools are 30% of what we do, so we use them a lot and experiment with the new ones as much as possible. There are thousands of tools and it's easy to get lost, so I wanted to share the tools we use most on a daily basis. And divide the list into 14 categories. I thought this could be handy for Entrepreneurs subreddit. Why adopt tools? I see marketing tools as tireless colleagues. If you can't hire an employee, choosing the right tool can solve your problems, because they Are super cheap. Work 7/24 for you. Don’t make mistakes. Don’t need management. (or needless management) Help you to automate the majority of your lead gen process. Onwards to the list. (With the pricings post ended up quite long, you can find a link in the end if you want to check the prices) Email marketing tools #1 ActiveCampaign is armed with the most complicated email automation features and has the most intuitive user experience. It feels like you already know how to use it. \#2 Autopilot is visual marketing automation and customer journey tool that helps you acquire, nurture based on behaviors, interest etc. #3 Mailjet: This is the tool we use to send out bulky email campaigns such as newsletters. It doesn't have sexy features like others but does its job for a cheap price. Email address finders #4 Skrapp finds email of your contacts by name and company. It also works with LinkedIn Sales Navigator and can extract thousands of emails in bulk + have a browser add-on. #5 Hunter: Similar to Skrapp but doesn't work with LinkedIn Sales Navigator directly. In addition, there are email templates and you can set up email campaigns. Prospecting and outreach tools #6 Prospect combines the personal emails, follow-up calls, other social touches and helps you create multichannel campaigns.  #7 Reply is a more intuitive version of Prospect. It is easy to learn and use; their UX makes you feel good and sufficient.  CRM tools #8 Salesflare helps you to stop managing your data and start managing your customers. Not yet popular as Hubspot and etc but the best solution for smaller B2B businesses. (we're fans) \#9 Hubspot: The most popular CRM for good reason and has a broader product range you can adopt in your next steps. Try this if you have a bulky list of customers because it is free. #10 Pardot: Pardot is by Salesforce, it's armed with features that can close the gap between marketing and sales. Sales Tools #11 Salesforce is the best sales automation and lead management software. It helps you to create complicated segmentations and run, track, analyze campaigns from the same dashboard. #12 LinkedIn Sales Navigator gives you full access to LinkedIn's user database. You can even find a kidnapped CEO if you know how to use it with other marketing automation tools like Skrapp. #13 Pipedrive is a simple tool and excels in one thing. It tracks your leads and tells you when to take the next action. It makes sales easier. #14 Qwilr creates great-looking docs, at speed. You can design perfect proposals, quotes, client updates, and more in a flash. We use it a lot to close deals, it's effective. #15 Crystalknows is an add-on that tells you anyone’s personality on LinkedIn and gives you a detailed approach specific to that person. It's eerily accurate. #16 Leadfeeder shows you the companies that visited your website. Tells how they found you and what they’re interested in. It has a free version. Communication Tools #17 Intercom is a sweet and smart host that welcomes your visitors when you’re not home. It’s one of the best chatbot tools in the market. #18 Drift is famous for its conversational marketing features and more sales-focused than Intercom. #19 Manychat is a chatbot that helps you create high converting Facebook campaigns. #20 Plann3r helps you create your personalized meeting page. You can schedule meetings witch clients, candidates, and prospects. #21 Loom is a video messaging tool, it helps you to be more expressive and create closer relationships. #22 Callpage collects your visitors’ phone number and connects you with them in seconds. No matter where you are. Landing page tools #23 Instapage is the best overall landing page builder. It has a broad range of features and even squirrel can build a compelling landing page with templates. No coding needed. #24 Unbounce can do everything that Instapage does and lets you build a great landing page without a developer. But it's less intuitive. Lead generation / marketing automation tools #25 Phantombuster is by far the most used lead generation software in our tool kit. It extracts data, emails, sends requests, customized messages, and does many things on autopilot in any platform. You can check this, this and this if you want to see it in action. #26 Duxsoup is a Google Chrome add-on and can also automate some of LinkedIn lead generation efforts like Phantombuster. But not works in the cloud. #27 Zapier is a glue that holds all the lead generation tools together. With Zapier, You can connect different marketing tools and no coding required. Conversion rate optimization tools #28 Hotjar tracks what people are doing on your website by recording sessions and capturing mouse movements. Then it gives you a heatmap. #29 UsabilityHub shows your page to a digital crowd and measures the first impressions and helps you to validate your ideas. #30 Optinmonster is a top tier conversion optimization tool. It helps you to capture leads and enables you to increase conversions rates with many features. #31 Notifia is one mega tool of widgets that arms your website with the wildest social proof and lead capturing tactics. #32 Sumo is a much simpler version of Notifia. But Sumo has everything to help you capture leads and build your email lists. Web scrapers #33 Data Miner is a Google Chrome browser extension that helps you scrape data from web pages and into a CSV file or Excel spreadsheet. #34 Webscraper does the same thing as Data Miner; however, it is capable of handling more complex tasks. SEO and Content #35 Grammarly: Your English could be your first language and your grammar could be better than Shakespeare. Grammarly still can make your writing better. #36 Hemingwayapp is a copywriting optimization tool that gives you feedback about your copy and improves your readability score, makes your writing bolder and punchier. Free. #37 Ahrefs is an all-rounder search engine optimization tool that helps you with off-page, on-page or technical SEO. #38 SurferSEO makes things easier for your on-page SEO efforts. It’s a tool that analyzes top Google results for specific keywords and gives you a content brief based on that data. Video editing and design tools #39 Canva is a graphic design platform that makes everything easy. It has thousands of templates for anything from Facebook ads, stylish presentations to business cards.  #40 Kapwing is our go-to platform for quick video edits. It works on the browser and can help you to create stylish videos, add subtitles, resize videos, create memes, or remove backgrounds. #41 Animoto can turn your photos and video clip into beautiful video slideshows. It comes handy when you want to create an advertising material but don’t have a budget. Advertising tools #42 AdEspresso lets you create and test multiple ads with few clicks. You can optimize your FB, IG, and Google ads from this tool and measure your ads with in-depth analytics. #43 AdRoll is an AI-driven platform that connects and coordinates marketing efforts across ads, email, and online stores. Other tools #44 Replug helps you to shorten, track, optimize your links with call-to-actions, branded links, and retargeting pixels #45 Draw.io = Mindmaps, schemes, and charts. With Draw.io, you can put your brain in a digital paper in an organized way. #46 Built With is a tool that finds out what websites are built with. So you can see what tools they're using and so on. #47 Typeform can turn data collection into an experience with Typeform. This tool helps you to engage your audience with conversational forms or surveys and help you to collect more data. #48 Livestorm helped us a lot, especially in COVID-19 tiles. It’s a webinar software that works on your browser, mobile, and desktop. #49 Teachable \- If you have an online course idea but hesitating because of the production process, Teachable can help you. It's easy to configure and customizable for your needs. #50 Viral Loops provides a revolutionary referral marketing solution for modern marketers. You can create and run referral campaigns in a few clicks with templates. Remember, most of these tools have a free trial or free version. Going over them one by one can teach you a lot and help you grow your business with less work power in the early stages of your business. I hope you enjoyed the read and can find some tools to make things easier! Let me know about your favorite tools in the comments, so I can try them out. \------ If you want to check the prices and see a broader explanation about the tools, you can go here.

12 months ago, I was unemployed. Last week my side hustle got acquired by a $500m fintech company

I’ve learned so much over the years from this subreddit. I thought I’d return the favour and share some of my own learnings. In November 2020 my best friend and I had an idea. “What if we could find out which stocks the Internet is talking about?” This formed the origins of Ticker Nerd. 9 months later we sold Ticker Nerd to Finder (an Australian fintech company valued at around $500m). In this post, I am going to lay out how we got there. How we came up with the idea First off, like other posts have covered - you don’t NEED a revolutionary or original idea to build a business. There are tonnes of “boring” businesses making over 7 figures a year e.g. law firms, marketing agencies, real estate companies etc. If you’re looking for an exact formula to come up with a great business idea I’m sorry, but it doesn’t exist. Finding new business opportunities is more of an art than a science. Although, there are ways you can make it easier to find inspiration. Below are the same resources I use for inspiration. I rarely ever come up with ideas without first searching one of the resources below for inspiration: Starter Story Twitter Startup Ideas My First Million Trends by the Hustle Trends VC To show how you how messy, random and unpredictable it can be to find an idea - let me explain how my co-founder and I came up with the idea for Ticker Nerd: We discovered a new product on Twitter called Exploding Topics. It was a newsletter that uses a bunch of software and algorithms to find trends that are growing quickly before they hit the mainstream. I had recently listened to a podcast episode from My First Million where they spoke about Motley Fool making hundreds of millions from their investment newsletters. We asked ourselves what if we could build a SaaS platform similar to Exploding Topics but it focused on stocks? We built a quick landing page using Carrd + Gumroad that explained what our new idea will do and included a payment option to get early access for $49. We called it Exploding Stock (lol). We shared it around a bunch of Facebook groups and subreddits. We made $1,000 in pre-sales within a couple days. My co-founder and I can’t code so we had to find a developer to build our idea. We interviewed a bunch of potential candidates. Meanwhile, I was trawling through Wall Street Bets and found a bunch of free tools that did roughly what we wanted to build. Instead of building another SaaS tool that did the same thing as these free tools we decided to pivot from our original idea. Our new idea = a paid newsletter that sends a weekly report that summarises 2 of the best stocks that are growing in interest on the Internet. We emailed everyone who pre-ordered access, telling them about the change and offered a full refund if they wanted. tl;dr: We essentially combined two existing businesses (Exploding Topics and Motley Fool) and made it way better. We validated the idea by finding out if people will actually pay money for it BEFORE we decided to build it. The idea we started out with changed over time. How to work out if your idea will actually make money It’s easy to get hung up on designing the logo or choosing the perfect domain name for your new idea. At this stage none of that matters. The most important thing is working out if people will pay money for it. This is where validation comes in. We usually validate ideas using Carrd. It lets you build a simple one page site without having to code. The Ticker Nerd site was actually built using a Carrd template. Here’s how you can do it yourself (at a high level): Create a Carrd pro account (yes it's a $49 one off payment but you’ll get way more value out of it). Buy a cheap template and send it to your Carrd account. You can build your own template but this will save you a lot of time. Once the template reaches your Carrd account, duplicate it. Leave the original so it can be duplicated for other ideas. Jump onto Canva (free) and create a logo using the free logos provided. Import your logo. Add copy to the page that explains your idea. Use the AIDA formula. Sign up to Gumroad (free) and create a pre-sale campaign. Create a discounted lifetime subscription or version of the product. This will be used pre-sales. Add the copy from the site into the pre-sale campaign on Gumroad. Add a ‘widget’ to Carrd and connect it to Gumroad using the existing easy integration feature. Purchase a domain name. Connect it to Carrd. Test the site works. Share your website Now the site is ready you can start promoting it in various places to see how the market reacts. An easy method is to find relevant subreddits using Anvaka (Github tool) or Subreddit Stats. The Anvaka tool provides a spider map of all the connected subreddits that users are active in. The highlighted ones are most relevant. You can post a thread in these subreddits that offer value or can generate discussion. For example: ‘I’m creating a tool that can write all your copy, would anyone actually use this?’ ‘What does everything think of using AI to get our copy written faster?’ ‘It’s time to scratch my own itch, I’m creating a tool that writes marketing copy using GPT-3. What are the biggest problems you face writing marketing copy? I’ll build a solution for it’ Reddit is pretty brutal these days so make sure the post is genuine and only drop your link in the comments or in the post if it seems natural. If people are interested they’ll ask for the link. Another great place to post is r/entrepreuerridealong and r/business_ideas. These subreddits expect people to share their ideas and you’ll likely make some sales straight off the bat. I also suggest posting in some Facebook groups (related to your idea) as well just for good measure. Assess the results If people are paying you for early access you can assume that it’s worth building your idea. The beauty of posting your idea on Reddit or in Facebook groups is you’ll quickly learn why people love/hate your idea. This can help you decide how to tweak the idea or if you should drop it and move on to the next one. How we got our first 100 customers (for free) By validating Ticker Nerd using subreddits and Facebook groups this gave us our first paying customers. But we knew this wouldn’t be sustainable. We sat down and brainstormed every organic strategy we could use to get traction as quickly as possible. The winner: a Product Hunt launch. A successful Product Hunt launch isn’t easy. You need: Someone that has a solid reputation and audience to “hunt” your product (essentially an endorsement). An aged Product Hunt account - you can’t post any products if your account is less than a week old. To be following relevant Product Hunt members - since they get notified when you launch a new product if they’re following you. Relationships with other builders and makers on Product Hunt that also have a solid reputation and following. Although, if you can pull it off you can get your idea in front of tens of thousands of people actively looking for new products. Over the next few weeks, I worked with my co-founder on connecting with different founders, indie hackers and entrepreneurs mainly via Twitter. We explained to them our plans for the Product Hunt launch and managed to get a small army of people ready to upvote our product on launch day. We were both nervous on the day of the launch. We told ourselves to have zero expectations. The worst that could happen was no one signed up and we were in the same position as we’re in now. Luckily, within a couple of hours Ticker Nerd was on the homepage of Product Hunt and in the top 10. The results were instant. After 24 hours we had around 200 people enter their payment details to sign up for our free trial. These signups were equal to around $5,800 in monthly recurring revenue. \-- I hope this post was useful! Drop any questions you have below and I’ll do my best to respond :)

Tech founders -- you're being lied to

I've been meaning to post this for a while. I saw a video recently that put me over the edge. You guys need to know what's up. Venture capitalists, angels, and accelerators all want you to build fast and fail faster. They want to you get your mvp buult in as little as a couple weeks. I'm a software dev and I own SaaS company. I'm here to tell you that you're being lied to. It's 2023. Unless some customer is about to drown because of their problem, they are not going to respect, or consider your trashy looking mvp. People these days expect a certain level of polish and professionalism when it comes to software before they give it more than 3s of their time. If your software took 80 hours to build, good chance that even customers from your target market will disregard it unless you're solving some insanely painful problem. And if you're using you're mvp for market research, people aren't going to talk to you if they believe that they spent more time getting dressed that morning than you put into your product. Build things that you can be proud of. Time boxing your first dev cycle into a few days or even weeks limits the scope of what you can build. I've spent more time than this figuring out a single api. Its this time boxing that leads 1000s of people to build the same shit. It's low quality work and exists in a super saturated market. And given the small scope of the product, the amount you'll be able to charge means the LTV of a customer will be lower than you CAC. Meaning your company will always lose money. The negative reception from your pre alpha product will have you think that people don't like you or your work. It's simply not the case. Few on this planet could produce something captivating in 100 hours. VCs tell you to ship your garbage MVP asap because of the following reason. They view every product that ships as a lotto ticket. If they like the look of it, they'll buy a ticket. And the more products there are and the shittier they are, it means a) they have more ticket numbers to select from and b) the cost of the ticket is a lot cheaper than it would otherwise be if the product was nice. VCs are not your friends and often, don't know how to build or market products. They are in it for the money and any advice they give to you or the community will be self serving. The indie community needs to wake up and realize that quality software built by a small team that people will pay for in this saturated market often takes months if not years to build. The idea of building a product and putting it in front of customers in 2 weeks is dumb. I've used some of these products and they are so limited in scope, broken and poorly designed that I don't give them anymore than a minute or two of my time. Note: validate your ideas before writing code. I'm not advocating spending a year writing software for an unproven market or problem. Yes, there are exceptions and stories of people shipping in no time and getting traction, but these are not the norm. Lastly, this philosophy is why you have and will continue to see a million products centered around AI. For those of you who aren't devs, Open AI made chatgpt accessible to developers and it's like 3 lines of code to ask it a question, get a response and save that response within your program. It's super low effort to integrate and that's why everyone will be building the same types of products with it. Tl;dr: Investors and gurus have agendas. Be logical about the level of effort required to build a software company and put forth only work that you're proud of. Being able to code doesn't give you a magical ability to create massive value with only a few weeks of work. You have to grind like pretty much every other successful business owner. I'll likely be banned for this, but fuck it. Ive got a sub where I'll share more insight and ban bullshit and idiotic posts with zero warning. It's not for everyone and I'll usually let you know pretty quick if our relationship isn't going to work. 6000 people and growing. r/cutthebull I'll write a post on that sub in the next few mins on how to guarentee accountability from top level management at your company.

If only someone told me this before my first startup

If only someone told me this before my first startup: Validate idea first. I wasted a decade building stuff nobody needed. Incubators and VCs served to me as a validation, but I was so wrong. Kill my EGO. It’s not about me, but the user. I must want what the user wants, not what I want. My taste isn't important. The user has expectations, and I must fulfill them. Don’t chaise investors. Chase users, and then investors will be chasing me. I've never had more incoming interest from VC than now when I'm the least interested in them. Never hire managers. Only hire doers until PMF. So many people know how to manage people and so few can actually get sh\*t done barehand. Landing page is the least important thing in a startup. Pick a simple template, edit texts with a no-code website builder in less than an hour and that's it! At the early stage, I win traffic outside of my website, people are already interested, so don't make them search for the signup button among the texts! Focus on conversion optimization only when the traffic is consistent. Keep it to one page. Nobody gonna browse this website. Hire only fullstack devs. There is nothing less productive in this world than a team of developers for an early-stage product. One full stack dev building the whole product. That’s it. Chase global market from day 1. If the product and marketing are good, it will work on the global market too, if it’s bad, it won’t work on the local market too. So better go global from day 1, so that if it works, the upside is 100x bigger. I launched all startups for the Norwegian market, hoping we will scale to international at some point. I wish I launched to international from day 1 as I do now. The size of the market is 10000x bigger. I can validate and grow products in days, not in years as it used to be. Do SEO from day 2. As early as I can. I ignored this for 14 years. It’s my biggest regret. It takes just 5 minutes to get it done on my landing page. I go to Google Keyword Planner, enter a few keywords around my product, sort them by traffic, filter out high competition kws, pick the top 10, and place them natively on my home page and meta tags. Add one blog article every week. Either manually or by paying for an AI blogging tool. Sell features, before building them. Ask existing users if they want this feature. I run DMs with 10-20 users every day, where I chat about all my ideas and features I wanna add. I clearly see what resonates with me most and only go build those. If I don't have followers, try HN, Reddit, or just search on X for posts and ask it in the replies. People are helpful, they will reply if the question is easy to understand. Hire only people I would wanna hug. My cofounder, an old Danish man said this to me in 2015. And it was a big shift. I realized that if I don’t wanna hug the person, it means I dislike them on a chemical/animal level. Even if I can’t say why, but that’s the fact. Sooner or later, we would have a conflict and eventually break up. It takes up to 10 years to build a startup, make sure I do it with people I have this connection with. Invest all money into my startups and friends. Not crypt0, not stockmarket, not properties. I did some math, if I kept investing all my money into all my friends’ startups, that would be about 70 investments. 3 of them turned into unicorns eventually. Even 1 would have made the bank. Since 2022, I have invested all my money into my products, friends, and network. If I don't have friends who do startups, invest it in myself. Post on Twitter daily. I started posting here in March last year. It’s my primary source of new connections and growth. I could have started it earlier, I don't know why I didn't. Don’t work/partner with corporates. Corporations always seem like an amazing opportunity. They’re big and rich, they promise huge stuff, millions of users, etc. But every single time none of this happens. Because I talk to a regular employees there. They waste my time, destroy focus, shift priorities, and eventually bring in no users/money. Don’t get ever distracted by hype e.g. crypt0. I lost 1.5 years of my life this way. I met the worst people along the way. Fricks, scammers, thieves. Some of my close friends turned into thieves along the way, just because it was so common in that space. I wish this didn’t happen to me. I wish I was stronger and stayed on my mission. Don’t build consumer apps. Only b2b. Consumer apps are so hard, like a lottery. It’s just 0.00001% who make it big. The rest don’t. Even if I got many users, then there is a monetization challenge. I’ve spent 4 years in consumer apps and regret it. Don’t hold on bad project for too long, max 1 year. Some projects just don’t work. In most cases, it’s either the idea that’s so wrong that I can’t even pivot it or it’s a team that is good one by one but can’t make it as a team. Don’t drag this out for years. Tech conferences are a waste of time. They cost money, take energy, and time and I never really meet anyone there. Most people there are the “good” employees of corporations who were sent there as a perk for being loyal to the corporation. Very few fellow makers. Scrum is a Scam. For small teams and bootstrapped teams. If I had a team that had to be nagged every morning with questions as if they were children in kindergarten, then things would eventually fail. The only good stuff I managed to do happened with people who were grownups and could manage their stuff on their own. We would just do everything over chat as a sync on goals and plans. Outsource nothing at all until PMF. In a startup, almost everything needs to be done in a slightly different way, more creative, and more integrated into the vision. When outsourcing, the external members get no love and no case for the product. It’s just yet another assignment in their boring job. Instead of coming up with great ideas for my project they will be just focusing on ramping up their skills to get a promotion or a better job offer. Bootstrap. I spent way too much time raising money. I raised more than 10 times, preseed, seeded, and series A. But each time it was a 3-9 month project, meetings every week, and lots of destruction. I could afford to bootstrap, but I still went the VC-funded way, I don’t know why. To be honest, I didn’t know bootstrapping was a thing I could do or anyone does. It may take a decade. When I was 20, I was convinced it takes a few years to build and succeed with a startup. So I kept pushing my plans forward, to do it once I exited. Family, kids. I wish I married earlier. I wish I had kids earlier. No Free Tier. I'd launch a tool with a free tier, and it'd get sign-ups, but very few would convert. I'd treat free sign-ups as KPIs and run on it for years. I'd brag about signups and visitors. I'd even raise VC money with these stats. But eventually, I would fail to reach PMF. Because my main feedback would come from free users and the product turned into a perfect free product. Once I switched to "paid only" until I validated the product, things went really well. Free and paid users often need different products. Don't fall into this trap as I did. Being To Cheap. I always started by checking all competitors and setting the lowest price. I thought this would be one of the key advantages of my product. But no, I was wrong. The audience on $5 and $50 are totally different. $5: pain in the \*ss, never happy, never recommend me to a friend, leave in 4 months. $50: polite, give genuine feedback, happy, share with friends, become my big fan if I solve their request. I will fail. When I started my first startup. I thought if I did everything right, it would work out. But it turned out that almost every startup fails. I wish I knew that and I tried to fail faster, to get to the second iteration, then to the third, and keep going on, until I either find out nothing works or make it work. Use boilerplates. I wasted years of dev time and millions of VC money to pay for basic things. To build yet another sidebar, yet another dashboard, and payment integration... I had too much pride, I couldn't see myself taking someone else code as a basis for my product. I wanted it to be 100% mine, original, from scratch. Because my product seems special to me. Spend more time with Family & Friends. I missed the weddings of all my best friends and family. I was so busy. I thought if I didn't do it on time, the world would end. Looking back today, it was so wrong. I meet my friends and can't share those memories with them, which makes me very sad. I realized now, that spending 10% of my time with family and friends would practically make no negative impact on my startups. Build Products For Audiences I Love. I never thought of this. I'd often build products either for corporates, consumers, or for developers. It turns out I have no love for all 3. But I deeply love indie founders. Because they are risk-takers and partly kids in their hearts. Once I switched the focus to indie makers on my products, my level of joy increased by 100x for me. Ignore Badges and Awards I was chasing those awards just like everyone else. Going to ceremonies, signing up for events and stuff. I've won tons of awards, but none of those were eventually useful to my business. I better focused on my business and users. Write Every Single Day. When I was a kid, I loved writing stories. In school, they would give an assignment, and I'd often write a long story for it, however, the teacher would put an F on it. The reason was simple, I had an issue with the direction of the letters and the sequence of letters in the words. I still have it, it's just the Grammarly app helping me to correct these issues. So the teacher would fail my stories because almost every sentence had a spelling mistake that I couldn't even see. It made me think I'm made at writing. So I stopped, for 15 years. But I kept telling stories all these years. Recently I realized that in any group, the setup ends up turning into me telling stories to everyone. So I tried it all again, here on X 10 months ago. I love it, the process, the feedback from people. I write every day. I wish I had done it all these years. The End. \ this is an updated version of my post on the same topic from 2 months ago. I've edited some of the points and added 9 new ones.* \\ This is not advice, it's my self-reflection that might help you avoid same mistakes if you think those were mistakes

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Uzair Javaid, a Ph.D. with a passion for data privacy, co-founded Betterdata to tackle one of AI's most pressing challenges: protecting privacy while enabling innovation. Recently, Betterdata secured a lucrative contract with the US Department of Homeland Security, 1 of only 4 companies worldwide to do so and the only one in Asia. Here's how he did it: The Story So what's your story? I grew up in Peshawar, Pakistan, excelling in coding despite studying electrical engineering. Inspired by my professors, I set my sights on studying abroad and eventually earned a Ph.D. scholarship at NUS Singapore, specializing in data security and privacy. During my research, I ethically hacked Ethereum and published 15 papers—three times the requirement. While wrapping up my Ph.D., I explored startup ideas and joined Entrepreneur First, where I met Kevin Yee. With his expertise in generative models and mine in privacy, we founded Betterdata. Now, nearly three years in, we’ve secured a major contract with the U.S. Department of Homeland Security—one of only four companies globally and the only one from Asia. The Startup In a nutshell, what does your startup do? Betterdata is a startup that uses AI and synthetic data generation to address two major challenges: data privacy and the scarcity of high-quality data for training AI models. By leveraging generative models and privacy-enhancing technologies, Betterdata enables businesses, such as banks, to use customer data without breaching privacy regulations. The platform trains AI on real data, learns its patterns, and generates synthetic data that mimics the real thing without containing any personal or sensitive information. This allows companies to innovate and develop AI solutions safely and ethically, all while tackling the growing need for diverse, high-quality data in AI development. How did you conduct ideation and validation for your startup? The initial idea for Betterdata came from personal experience. During my Ph.D., I ethically hacked Ethereum’s blockchain, exposing flaws in encryption-based data sharing. This led me to explore AI-driven deep synthesis technology—similar to deepfakes but for structured data privacy. With GDPR impacting 28M+ businesses, I saw a massive opportunity to help enterprises securely share data while staying compliant. To validate the idea, I spoke to 50 potential customers—a number that strikes the right balance. Some say 100, but that’s impractical for early-stage founders. At 50, patterns emerge: if 3 out of 10 mention the same problem, and this repeats across 50, you have 10–15 strong signals, making it a solid foundation for an MVP. Instead of outbound sales, which I dislike, we used three key methods: Account-Based Marketing (ABM)—targeting technically savvy users with solutions for niche problems, like scaling synthetic data for banks. Targeted Content Marketing—regular customer conversations shaped our thought leadership and outreach. Raising Awareness Through Partnerships—collaborating with NUS, Singapore’s PDPC, and Plug and Play to build credibility and educate the market. These strategies attracted serious customers willing to pay, guiding Betterdata’s product development and market fit. How did you approach the initial building and ongoing product development? In the early stages, we built synthetic data generation algorithms and a basic UI for proof-of-concept, using open-source datasets to engage with banks. We quickly learned that banks wouldn't share actual customer data due to privacy concerns, so we had to conduct on-site installations and gather feedback to refine our MVP. Through continuous consultation with customers, we discovered real enterprise data posed challenges, such as missing values, which led us to adapt our prototype accordingly. This iterative approach of listening to customer feedback and observing their usage allowed us to improve our product, enhance UX, and address unmet needs while building trust and loyalty. Working closely with our customers also gives us a data advantage. Our solution’s effectiveness depends on customer data, which we can't fully access, but bridging this knowledge gap gives us a competitive edge. The more customers we test on, the more our algorithms adapt to diverse use cases, making it harder for competitors to replicate our insights. My approach to iteration is simple: focus solely on customer feedback and ignore external noise like trends or advice. The key question for the team is: which customer is asking for this feature or solution? As long as there's a clear answer, we move forward. External influences, such as AI hype, often bring more confusion than clarity. True long-term success comes from solving real customer problems, not chasing trends. Customers may not always know exactly what they want, but they understand their problems. Our job is to identify these problems and solve them in innovative ways. While customers may suggest specific features, we stay focused on solving the core issue rather than just fulfilling their exact requests. The idea aligns with the quote often attributed to Henry Ford: "If I asked people what they wanted, they would have said faster horses." The key is understanding their problems, not just taking requests at face value. How do you assess product-market fit? To assess product-market fit, we track two key metrics: Customers' Willingness to Pay: We measure both the quantity and quality of meetings with potential customers. A high number of meetings with key decision-makers signals genuine interest. At Betterdata, we focused on getting meetings with people in banks and large enterprises to gauge our product's resonance with the target market. How Much Customers Are Willing to Pay: We monitor the price customers are willing to pay, especially in the early stages. For us, large enterprises, like banks, were willing to pay a premium for our synthetic data platform due to the growing need for privacy tech. This feedback guided our product refinement and scaling strategy. By focusing on these metrics, we refined our product and positioned it for scaling. What is your business model? We employ a structured, phase-driven approach for out business model, as a B2B startup. I initially struggled with focusing on the core value proposition in sales, often becoming overly educational. Eventually, we developed a product roadmap with models that allowed us to match customer needs to specific offerings and justify our pricing. Our pricing structure includes project-based pilots and annual contracts for successful deployments. At Betterdata, our customer engagement unfolds across three phases: Phase 1: Trial and Benchmarking \- We start with outreach and use open-source datasets to showcase results, offering customers a trial period to evaluate the solution. Phase 2: Pilot or PoC \- After positive trial results, we conduct a PoC or pilot using the customer’s private data, with the understanding that successful pilots lead to an annual contract. Phase 3: Multi-Year Contracts \- Following a successful pilot, we transition to long-term commercial contracts, focusing on multi-year agreements to ensure stability and ongoing partnerships. How do you do marketing for your brand? We take a non-conventional approach to marketing, focusing on answering one key question: Which customers are willing to pay, and how much? This drives our messaging to show how our solution meets their needs. Our strategy centers around two main components: Building a network of lead magnets \- These are influential figures like senior advisors, thought leaders, and strategic partners. Engaging with institutions like IMDA, SUTD, and investors like Plug and Play helps us gain access to the right people and foster warm introductions, which shorten our sales cycle and ensure we’re reaching the right audience. Thought leadership \- We build our brand through customer traction, technology evidence, and regulatory guidelines. This helps us establish credibility in the market and position ourselves as trusted leaders in our field. This holistic approach has enabled us to navigate diverse market conditions in Asia and grow our B2B relationships. By focusing on these areas, we drive business growth and establish strong trust with stakeholders. What's your advice for fundraising? Here are my key takeaways for other founders when it comes to fundraising: Fundraise When You Don’t Need To We closed our seed round in April 2023, a time when we weren't actively raising. Founders should always be in fundraising mode, even when they're not immediately in need of capital. Don’t wait until you have only a few months of runway left. Keep the pipeline open and build relationships. When the timing is right, execution becomes much easier. For us, our investment came through a combination of referrals and inbound interest. Even our lead investor initially rejected us, but after re-engaging, things eventually fell into place. It’s crucial to stay humble, treat everyone with respect, and maintain those relationships for when the time is right. Be Mindful of How You Present Information When fundraising, how you present information matters a lot. We created a comprehensive, easily digestible investment memo, hosted on Notion, which included everything an investor might need—problem, solution, market, team, risks, opportunities, and data. The goal was for investors to be able to get the full picture within 30 minutes without chasing down extra details. We also focused on making our financial model clear and meaningful, even though a 5-year forecast might be overkill at the seed stage. The key was clarity and conciseness, and making it as easy as possible for investors to understand the opportunity. I learned that brevity and simplicity are often the best ways to make a memorable impact. For the pitch itself, keep it simple and focus on 4 things: problem, solution, team, and market. If you can summarize each of these clearly and concisely, you’ll have a compelling pitch. Later on, you can expand into market segments, traction, and other metrics, but for seed-stage, focus on those four areas, and make sure you’re strong in at least three of them. If you do, you'll have a compelling case. How do you run things day-to-day? i.e what's your operational workflow and team structure? Here's an overview of our team structure and process: Internally: Our team is divided into two main areas: backend (internal team) and frontend (market-facing team). There's no formal hierarchy within the backend team. We all operate as equals, defining our goals based on what needs to be developed, assigning tasks, and meeting weekly to share updates and review progress. The focus is on full ownership of tasks and accountability for getting things done. I also contribute to product development, identifying challenges and clearing obstacles to help the team move forward. Backend Team: We approach tasks based on the scope defined by customers, with no blame or hierarchy. It's like a sports team—sometimes someone excels, and other times they struggle, but we support each other and move forward together. Everyone has the creative freedom to work in the way that suits them best, but we establish regular meetings and check-ins to ensure alignment and progress. Frontend Team: For the market-facing side, we implement a hierarchy because the market expects this structure. If I present myself as "CEO," it signals authority and credibility. This distinction affects how we communicate with the market and how we build our brand. The frontend team is split into four main areas: Business Product (Software Engineering) Machine Learning Engineering R&D The C-suite sits at the top, followed by team leads, and then the executors. We distill market expectations into actionable tasks, ensuring that everyone is clear on their role and responsibilities. Process: We start by receiving market expectations and defining tasks based on them. Tasks are assigned to relevant teams, and execution happens with no communication barriers between team members. This ensures seamless collaboration and focused execution. The main goal is always effectiveness—getting things done efficiently while maintaining flexibility in how individuals approach their work. In both teams, there's an emphasis on accountability, collaboration, and clear communication, but the structure varies according to the nature of the work and external expectations.

Turning a Social Media Agency into $1.5 Million in Revenue

Steffie here from Founder Folks, with a recent interview I did with Jason Yormark from Socialistics. Here is his story how he started and grew his social media agency. Name: Jason Yormark Company: Socialistics Employee Size: 10 Revenue: $1,500,000/year Year Founded: 2018 Website: www.socialistics.com Technology Tools: ClickUp, Slack, KumoSpace, Google Workspace, Shift, Zapier, Klayvio, Zoom, Gusto, Calendly, Pipedrive Introduction: I am the founder of Socialistics (www.socialistics.com), a leading social media agency that helps businesses turn their social media efforts into real measurable results. I am a 20+ year marketing veteran whose prior work has included launching and managing social media efforts for Microsoft Advertising, Office for Mac, the Air Force, and Habitat for Humanity. I have been recognized as a top B2B social media influencer and thought leader on multiple lists and publications including Forbes, ranking #30 on their 2012 list. I've recently published the book Anti-Agency: A Realistic Path to a $1,000,000 Business, and host the Anti Agency podcast where I share stories of doing business differently. You can learn more about me at www.jasonyormark.com. The Inspiration To Become An Entrepreneur: I’ve been involved with social media marketing since 2007, and have pretty much carved my career out of that. It was a natural progression for me to transition into starting a social media agency. From Idea to Reality: For me realistically, I had to side hustle something long enough to build it up to a point that I could take the leap and risks going full time on my own. For these reasons, I built the company and brand on the side putting out content regularly, and taking on side hustle projects to build out my portfolio and reputation. This went on for about 18 months at which point I had reached the breaking point of my frustrations of working for someone else, and felt I was ready to take the leap since I had the wheels in motion. While balancing a full-time job, I made sure not to overdo it. My main focus was on building out the website/brand and putting out content regularly to gain some traction and work towards some search visibility. I only took on 1-2 clients at a time to make sure I could still meet their needs while balancing a full time job. Attracting Customers: Initially I tapped into my existing network to get my first few clients. Then it was a mix of trade shows, networking events, and throwing a bit of money at paid directories and paid media. This is really a long game. You have to plant seeds over time with people and nurture those relationships over time. A combination of being helpful, likable and a good resource for folks will position you to make asks in the future. If people respect and like you, it makes it much easier to approach for opportunities when the time comes. Overcoming Challenges in Starting the Business: Plenty. Learning when to say no, only hiring the very best, and ultimately the realization that owning a marketing agency is going to have hills and valleys no matter what you do. Costs and Revenue: My largest expense by FAR is personnel, comprising between 50-60% of the business’ expenses, and justifiably so. It’s a people business. Our revenue doubled from the years 2018 through 2021, and we’ve seen between 10-20% growth year over year. A Day in the Life: I’ve successfully removed myself from the day to day of the business and that’s by design. I have a tremendous team, and a rock start Director of Operations who runs the agency day to day. It frees me up to pursue other opportunities, and to mentor, speak and write more. It also allows me to evangelize the book I wrote detailing my journey to a $1M business titled: Anti-Agency: A Realistic Path To A $1,000,000 Business (www.antiagencybook.com). Staying Ahead in a Changing Landscape: You really have to stay on top of technology trends. AI is a huge impact on marketing these days, so making sure we are up to speed on that, and not abusing it or relying on it too much. You also have to embrace that technology and not hide the fact that it’s used. Non-marketers still don’t and can’t do the work regardless of how much AI can help, so we just need to be transparent and smart on how we integrate it, but the fact is, technology will never replace creativity. As an agency, it’s imperative that we operationally allow our account managers to have bandwidth to be creative for clients all the time. It’s how we keep clients and buck the trend of companies changing agencies every year or two. The Vision for Socialistics: Continuing to evolve to cater to our clients through learning, education, and staying on top of the latest tools and technologies. Attracting bigger and more exciting clients, and providing life changing employment opportunities.

The delicate balance of building an online community business

Hey /r/Entrepreneur 👋 Just under two years ago I launched an online community business called Traffic Think Tank with two other co-founders, Nick Eubanks and Ian Howells. As a Traffic Think Tank customer you (currently) pay $119 a month to get access to our online community, which is run through Slack. The community is focused on helping you learn various aspects of marketing, with a particular focus on search engine optimization (SEO). Alongside access to the Slack community, we publish new educational video content from outside experts every week that all customers have access to. At the time of writing, Traffic Think Tank has around 650 members spanning across 17 of the 24 different global time zones. I was on a business trip over in Sydney recently, and during my time there I met up with some of our Australia-based community members. During dinner I was asked by several of them how the idea for Traffic Think Tank came about and what steps we took to validate that the idea was worth pursuing.  This is what I told them… How it all began It all started with a personal need. Nick, an already successful entrepreneur and owner of a marketing agency, had tested out an early version Traffic Think Tank in early 2017. He offered real-time consulting for around ten customers that he ran from Slack. He would publish some educational videos and offer his advice on projects that the members were running. The initial test went well, but it was tough to maintain on his own and he had to charge a fairly high price to make it worth his time. That’s when he spoke to me and Ian about turning this idea into something much bigger. Both Ian and I offered something slightly different to Nick. We’ve both spent time in senior positions at marketing agencies, but currently hold senior director positions in 2,000+ public employee companies (HubSpot and LendingTree). Alongside this, as a trio we could really ramp up the quality and quantity of content within the community, spread out the administrative workload and just generally have more resources to throw at getting this thing off the ground. Admittedly, Nick was much more optimistic about the potential of Traffic Think Tank – something I’m very thankful for now – whereas Ian and I were in the camp of “you’re out of your mind if you think hundreds of people are going to pay us to be a part of a Slack channel”. To validate the idea at scale, we decided that we’d get an initial MVP of the community up and running with a goal of reaching 100 paying customers in the first six months. If we achieved that, we’d validated that it was a viable business and we would continue to pursue it. If not, we’d kill it. We spent the next month building out the initial tech stack that enabled us to accept payments, do basic user management to the Slack channel, and get a one-page website up and running with information on what Traffic Think Tank was all about.  After this was ready, we doubled down on getting some initial content created for members – I mean, we couldn’t have people just land in an empty Slack channel, could we? We created around ten initial videos, 20 or so articles and then some long threads full of useful information within the Slack channel so that members would have some content to pour into right from the beginning.  Then, it was time to go live. The first 100 customers Fortunately, both Nick and I had built a somewhat substantial following in the SEO space over the previous 5-10 years, so we at least had a large email list to tap into (a total of around 40,000 people). We queued up some launch emails, set an initial price of $99 per month and pressed send. [\[LINK\] The launch email I sent to my subscribers announcing Traffic Think Tank](https://mailchi.mp/matthewbarby/future-of-marketing-1128181) What we didn’t expect was to sell all of the initial 100 membership spots in the first 72 hours. “Shit. What do we do now? Are we ready for this many people? Are we providing them with enough value? What if something breaks in our tech stack? What if they don’t like the content? What if everyone hates Slack?” All of these were thoughts running through my head. This brings me to the first great decision we made: we closed down new membership intake for 3 months so that we could focus completely on adding value to the first cohort of users. The right thing at the right time SEO is somewhat of a dark art to many people that are trying to learn about it for the first time. There’s hundreds of thousands (possibly millions) of articles and videos online that talk about how to do SEO.  Some of it’s good advice; a lot of it is very bad advice.  Add to this that the barrier to entry of claiming to be an “expert” in SEO is practically non-existent and you have a recipe for disaster. This is why, for a long time, individuals involved in SEO have flocked in their masses to online communities for information and to bounce ideas off of others in the space. Forums like SEObook, Black Hat World, WickedFire, Inbound.org, /r/BigSEO, and many more have, at one time, been called home by many SEOs.  In recent times, these communities have either been closed down or just simply haven’t adapted to the changing needs of the community – one of those needs being real-time feedback on real-world problems.  The other big need that we all spotted and personally had was the ability to openly share the things that are working – and the things that aren’t – in SEO within a private forum. Not everyone wanted to share their secret sauce with the world. One of the main reasons we chose Slack as the platform to run our community on was the fact that it solved these two core needs. It gave the ability to communicate in real-time across multiple devices, and all of the information shared within it was outside of the public domain. The other problem that plagued a lot of these early communities was spam. Most of them were web-based forums that were free to access. That meant they became a breeding ground for people trying to either sell their services or promote their own content – neither of which is conducive to building a thriving community. This was our main motivation for charging a monthly fee to access Traffic Think Tank. We spent a lot of time thinking through pricing. It needed to be enough money that people would be motivated to really make use of their membership and act in a way that’s beneficial to the community, but not too much money that it became cost prohibitive to the people that would benefit from it the most. Considering that most of our members would typically spend between $200-800 per month on SEO software, $99 initially felt like the perfect balance. Growing pains The first three months of running the community went by without any major hiccups. Members were incredibly patient with us, gave us great feedback and were incredibly helpful and accommodating to other members. Messages were being posted every day, with Nick, Ian and myself seeding most of the engagement at this stage.  With everything going smoothly, we decided that it was time to open the doors to another intake of new members. At this point we’d accumulated a backlog of people on our waiting list, so we knew that simply opening our doors would result in another large intake. Adding more members to a community has a direct impact on the value that each member receives. For Traffic Think Tank in particular, the value for members comes from three areas: The ability to have your questions answered by me, Nick and Ian, as well as other members of the community. The access to a large library of exclusive content. The ability to build connections with the wider community. In the early stages of membership growth, there was a big emphasis on the first of those three points. We didn’t have an enormous content library, nor did we have a particularly large community of members, so a lot of the value came from getting a lot of one-to-one time with the community founders. [\[IMAGE\] Screenshot of engagement within the Traffic Think Tank Slack community](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1322/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-in-Traffic-Think-Tank.png) The good thing about having 100 members was that it was just about feasible to give each and every member some one-to-one time within the month, which really helped us to deliver those moments of delight that the community needed early on. Two-and-a-half months after we launched Traffic Think Tank, we opened the doors to another 250 people, taking our total number of members to 350. This is where we experienced our first growing pains.  Our original members had become used to being able to drop us direct messages and expect an almost instant response, but this wasn’t feasible anymore. There were too many people, and we needed to create a shift in behavior. We needed more value to come from the community engaging with one another or we’d never be able to scale beyond this level. We started to really pay attention to engagement metrics; how many people were logging in every day, and of those, how many were actually posting messages within public channels.  We asked members that were logging in a lot but weren’t posting (the “lurkers”) why that was the case. We also asked the members that engaged in the community the most what motivated them to post regularly. We learned a lot from doing this. We found that the large majority of highly-engaged members had much more experience in SEO, whereas most of the “lurkers” were beginners. This meant that most of the information being shared in the community was very advanced, with a lot of feedback from the beginners in the group being that they “didn’t want to ask a stupid question”.  As managers of the community, we needed to facilitate conversations that catered to all of our members, not just those at a certain level of skill. To tackle this problem, we created a number of new channels that had a much deeper focus on beginner topics so novice members had a safe place to ask questions without judgment.  We also started running live video Q&As each month where we’d answer questions submitted by the community. This gave our members one-on-one time with me, Nick and Ian, but spread the value of these conversations across the whole community rather than them being hidden within private messages. As a result of these changes, we found that the more experienced members in the community were really enjoying sharing their knowledge with those with less experience. The number of replies within each question thread was really starting to increase, and the community started to shift away from just being a bunch of threads created by me, Nick and Ian to a thriving forum of diverse topics compiled by a diverse set of individuals. This is what we’d always wanted. A true community. It was starting to happen. [\[IMAGE\] Chart showing community engagement vs individual member value](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1602/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-Balance-Graph.jpg) At the same time, we started to realize that we’ll eventually reach a tipping point where there’ll be too much content for us to manage and our members to engage with. When we reach this point, the community will be tough to follow and the quality of any given post will go down. Not only that, but the community will become increasingly difficult to moderate. We’re not there yet, but we recognize that this will come, and we’ll have to adjust our model again. Advocating advocacy As we started to feel more comfortable about the value that members were receiving, we made the decision to indefinitely open for new members. At the same time, we increased the price of membership (from $99 a month to $119) in a bid to strike the right balance between profitability as a business and to slow down the rate at which we were reaching the tipping point of community size. We also made the decision to repay all of our early adopters by grandfathering them in to the original pricing – and committing to always do this in the future. Despite the price increase, we saw a continued flow of new members come into the community. The craziest part about this was that we were doing practically no marketing activities to encourage new members– this was all coming from word of mouth. Our members were getting enough value from the community that they were recommending it to their friends, colleagues and business partners.  The scale at which this was happening really took us by surprise and it told us one thing very clearly: delivering more value to members resulted in more value being delivered to the business. This is a wonderful dynamic to have because it perfectly aligns the incentives on both sides. We’d said from the start that we wouldn’t sacrifice value to members for more revenue – this is something that all three of us felt very strongly about. First and foremost, we wanted to create a community that delivered value to its members and was run in a way that aligned with our values as people. If we could find a way to stimulate brand advocacy, while also tightening the bonds between all of our individual community members, we’d be boosting both customer retention and customer acquisition in the same motion. This became our next big focus. [\[TWEET\] Adam, one of our members wore his Traffic Think Tank t-shirt in the Sahara desert](https://twitter.com/AdamGSteele/status/1130892481099382784) We started with some simple things: We shipped out Traffic Think Tank branded T-shirts to all new members. We’d call out each of the individuals that would submit questions to our live Q&A sessions and thank them live on air. We set up a new channel that was dedicated to sharing a quick introduction to who you are, what you do and where you’re based for all new members. We’d created a jobs channel and a marketplace for selling, buying and trading services with other members. Our monthly “blind dates” calls were started where you’d be randomly grouped with 3-4 other community members so that you could hop on a call to get to know each other better. The Traffic Think Tank In Real Life (IRL)* channel was born, which enabled members to facilitate in-person meetups with each other. In particular, we saw that as members started to meet in person or via calls the community itself was feeling more and more like a family. It became much closer knit and some members started to build up a really positive reputation for being particularly helpful to other members, or for having really strong knowledge in a specific area. [\[TWEET\] Dinner with some of the Traffic Think Tank members in Brighton, UK](https://twitter.com/matthewbarby/status/1117175584080134149) Nick, Ian and I would go out of our way to try and meet with members in real life wherever we could. I was taken aback by how appreciative people were for us doing this, and it also served as an invaluable way to gain honest feedback from members. There was another trend that we’d observed that we didn’t really expect to happen. More and more members were doing business with each another. We’ve had people find new jobs through the community, sell businesses to other members, launch joint ventures together and bring members in as consultants to their business. This has probably been the most rewarding thing to watch, and it was clear that the deeper relationships that our members were forming were resulting in an increased level of trust to work with each other. We wanted to harness this and take it to a new level. This brought us to arguably the best decision we’ve made so far running Traffic Think Tank… we were going to run a big live event for our members. I have no idea what I’m doing It’s the first week of January 2019 and we’re less than three weeks away from Traffic Think Tank LIVE, our first ever in-person event hosting 150 people, most of which are Traffic Think Tank members. It's like an ongoing nightmare I can’t wake up from. That was Nick’s response in our private admin channel to myself and Ian when I asked if they were finding the run-up to the event as stressful as I was. I think that all three of us were riding on such a high from how the community was growing that we felt like we could do anything. Running an event? How hard can it be? Well, turns out it’s really hard. We had seven different speakers flying over from around the world to speak at the event, there was a pre- and after event party, and we’d planned a charity dinner where we would take ten attendees (picked at random via a raffle) out for a fancy meal. Oh, and Nick, Ian and I were hosting a live Q&A session on stage. It wasn’t until precisely 48 hours before the event that we’d realized we didn’t have any microphones, nor had a large amount of the swag we’d ordered arrived. Plus, a giant storm had hit Philly causing a TON of flight cancellations. Perfect. Just perfect. This was honestly the tip of the iceberg. We hadn’t thought about who was going to run the registration desk, who would be taking photos during the event and who would actually field questions from the audience while all three of us sat on stage for our live Q&A panel. Turns out that the answer to all of those questions were my wife, Laura, and Nick’s wife, Kelley. Thankfully, they were on hand to save our asses. The weeks running up to the event were honestly some of the most stressful of my life. We sold around 50% of our ticket allocation within the final two weeks before the event. All of the event organizers told us this would happen, but did we believe them? Hell no!  Imagine having two weeks until the big day and as it stood half of the room would be completely empty. I was ready to fly most of my extended family over just to make it look remotely busy. [\[IMAGE\] One of our speakers, Ryan Stewart, presenting at Traffic Think Tank LIVE](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1920/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LIVE-Ryan-Presenting.jpg) Thankfully, if all came together. We managed to acquire some microphones, the swag arrived on the morning of the event, all of our speakers were able to make it on time and the weather just about held up so that our entire allocation of ticket holders was able to make it to the event. We pooled together and I’m proud to say that the event was a huge success. While we made a substantial financial loss on the event itself, January saw a huge spike in new members, which more than recouped our losses. Not only that, but we got to hang out with a load of our members all day while they said really nice things about the thing we’d built. It was both exhausting and incredibly rewarding. Bring on Traffic Think Tank LIVE 2020! (This time we’re hiring an event manager...)   The road ahead Fast forward to today (August 2019) and Traffic Think Tank has over 650 members. The biggest challenges that we’re tackling right now include making sure the most interesting conversations and best content surfaces to the top of the community, making Slack more searchable (this is ultimately one of its flaws as a platform) and giving members a quicker way to find the exclusive content that we create. You’ll notice there’s a pretty clear theme here. In the past 30 days, 4,566 messages were posted in public channels inside Traffic Think Tank. If you add on any messages posted inside private direct messages, this number rises to 21,612. That’s a lot of messages. To solve these challenges and enable further scale in the future, we’ve invested a bunch of cash and our time into building out a full learning management system (LMS) that all members will get access to alongside the Slack community. The LMS will be a web-based portal that houses all of the video content we produce. It will also  provide an account admin section where users can update or change their billing information (they have to email us to do this right now, which isn’t ideal), a list of membership perks and discounts with our partners, and a list of links to some of the best threads within Slack – when clicked, these will drop you directly into Slack. [\[IMAGE\] Designs for the new learning management system (LMS)](https://cdn.shortpixel.ai/client/qglossy,retimg,w_2378/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LMS.png) It’s not been easy, but we’re 95% of the way through this and I’m certain that it will have a hugely positive impact on the experience for our members. Alongside this we hired a community manager, Liz, who supports with any questions that our members have, coordinates with external experts to arrange webinars for the community, helps with new member onboarding, and has tightened up some of our processes around billing and general accounts admin. This was a great decision. Finally, we’ve started planning next year’s live event, which we plan to more than double in size to 350 attendees, and we decided to pick a slightly warmer location in Miami this time out. Stay tuned for me to have a complete meltdown 3 weeks from the event. Final thoughts When I look back on the journey we’ve had so far building Traffic Think Tank, there’s one very important piece to this puzzle that’s made all of this work that I’ve failed to mention so far: co-founder alignment. Building a community is a balancing act that relies heavily on those in charge being completely aligned. Nick, Ian and I completely trust each other and more importantly, are philosophically aligned on how we want to run and grow the community. If we didn’t have this, the friction between us could tear apart the entire community. Picking the right people to work with is important in any company, but when your business is literally about bringing people together, there’s no margin for error here.  While I’m sure there will be many more challenges ahead, knowing that we all trust each other to make decisions that fall in line with each of our core values makes these challenges dramatically easier to overcome. Finally, I’d like to thank all of our members for making the community what it is today – it’d be nothing without you and I promise that we’ll never take that for granted. &#x200B; I originally posted this on my blog here. Welcoming all of your thoughts, comments, questions and I'll do my best to answer them :)

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

[CASE STUDY] From 217/m to $2,836/m in 9 months - Sold for $59,000; I grow and monetise web traffic of 5, 6, 7 figures USD valued passive income content sites [AMA]

Hello Everyone (VERY LONG CASE STUDY AHEAD) - 355% return in 9 months Note: I own a 7-figures USD valued portfolio of 41+ content sites that generates 5-6 figures USD a month in passive income. This is my first time posting in this sub and my goal is to NOT share generic advice but precise numbers, data and highly refined processes so you can also get started with this business yourself or if you already have an existing business, drive huge traffic to it and scale it substantially (get more customers). I will use a case study to explain the whole process. As most of us are entrepreneurs here, explaining an actual project would be more meaningful. In this case study I used AI assisted content to grow an existing site from $217/m to $2,836/m in 9 months (NO BACKLINKS) and sold it for $59,000. ROI of 3 months: 355% Previous case studies (before I give an overview of the model) Amazon Affiliate Content Site: $371/m to $19,263/m in 14 MONTHS - $900K CASE STUDY \[AMA\] Affiliate Website from $267/m to $21,853/m in 19 months (CASE STUDY - Amazon?) \[AMA\] Amazon Affiliate Website from $0 to $7,786/month in 11 months Amazon Affiliate Site from $118/m to $3,103/m in 8 MONTHS (SOLD it for $62,000+) Note: You can check pinned posts on my profile. Do go through the comments as well as a lot of questions are answered in those. However, if you still have any questions, feel free to reach out. This is an \[AMA\]. Quick Overview of the Model Approach: High traffic, niche specific, informative content websites that monetise its traffic through highly automated methods like display ads and affiliate. The same model can be applied to existing businesses to drive traffic and get customers. Main idea: Make passive income in a highly automated way Easy to understand analogy You have real estate (here you have digital asset like a website) You get rental income (here you get ads and affiliate income with no physical hassle, in case you have a business like service, product etc. then you can get customers for that too but if not, it's alright) Real estate has value (this digital asset also has value that can be appreciated with less effort) Real estate can be sold (this can be sold too but faster) IMPORTANT NOTE: Search traffic is the BEST way to reach HUGE target audience and it's important when it comes to scaling. This essentially means that you can either monetise that via affiliate, display etc. or if you have a business then you can reach a bigger audience to scale. Overview of this website's valuation (then and now: Oct. 2022 and June 2023) Oct 2022: $217/m Valuation: $5,750.5 (26.5x) - set it the same as the multiple it was sold for June 2023: $2,836/m Traffic and revenue trend: growing fast Last 3 months avg: $2,223 Valuation now: $59,000 (26.5x) Description: The domain was registered in 2016, it grew and then the project was left unattended. I decided to grow it again using properly planned AI assisted content. Backlink profile: 500+ Referring domains (Ahrefs). Backlinks mean the sites linking back to you. This is important when it comes to ranking. Summary of Results of This Website - Before and After Note: If the terms seem technical, do not worry. I will explain them in detail later. Still if you have any questions. Feel free to comment or reach out. |Metric|Oct 2022|June 2023|Difference|Comments| |:-|:-|:-|:-|:-| |Articles|314|804|\+490|AI Assisted content published in 3 months| |Traffic|9,394|31,972|\+22,578|Organic| |Revenue|$217|$2,836|\+$2,619|Multiple sources| |RPM (revenue/1000 web traffic)|23.09|$88.7|\+$65.61|Result of Conversion rate optimisation (CRO). You make changes to the site for better conversions| |EEAT (expertise, experience, authority and trust of website)|2 main authors|8 authors|6|Tables, video ads and 11 other fixations| |CRO|Nothing|Tables, video ads |Tables, video ads and 11 other fixations || &#x200B; Month by Month Growth |Month|Revenue|Steps| |:-|:-|:-| |Sept 2022|NA|Content Plan| |Oct 2022|$217|Content Production| |Nov 2022|$243|Content production + EEAT authors| |Dec 2022|$320|Content production + EEAT authors| |Jan 2023|$400|Monitoring| |Feb 2023|$223|Content production + EEAT authors| |Mar 2023|$2,128|CRO & Fixations| |April 2023|$1,609|CRO & Fixations| |May 2023|$2,223|Content production + EEAT authors| |June 2023|$2,836|CRO and Fixations| |Total|$10,199|| &#x200B; What will I share Content plan and Website structure Content Writing Content Uploading, formatting and onsite SEO Faster indexing Conversion rate optimisation Guest Posting EEAT (Experience, Expertise, Authority, Trust) Costing ROI The plans moving forward with these sites &#x200B; Website Structure and Content Plan This is probably the most important important part of the whole process. The team spends around a month just to get this right. It's like defining the direction of the project. Description: Complete blueprint of the site's structure in terms of organisation of categories, subcategories and sorting of articles in each one of them. It also includes the essential pages. The sorted articles target main keyword, relevant entities and similar keywords. This has to be highly data driven and we look at over 100 variables just to get it right. It's like beating Google's algorithm to ensure you have a blueprint for a site that will rank. It needs to be done right. If there is a mistake, then even if you do everything right - it's not going to work out and after 8-16 months you will realise that everything went to waste. Process For this project, we had a niche selected already so we didn't need to do a lot of research pertaining to that. We also knew the topic since the website was already getting good traffic on that. We just validated from Ahrefs, SEMRUSH and manual analysis if it would be worth it to move forward with that topic. &#x200B; Find entities related to the topic: We used Ahrefs and InLinks to get an idea about the related entities (topics) to create a proper topical relevance. In order to be certain and have a better idea, we used ChatGPT to find relevant entities as well \> Ahrefs (tool): Enter main keyword in keywords explorer. Check the left pain for popular topics \> Inlinks (tool): Enter the main keyword, check the entity maps \> ChatGPT (tool): Ask it to list down the most important and relevant entities in order of their priority Based on this info, you can map out the most relevant topics that are semantically associated to your main topic Sorting the entities in topics (categories) and subtopics (subcategories): Based on the information above, cluster them properly. The most relevant ones must be grouped together. Each group must be sorted into its relevant category. \> Example: Site about cycling. \> Categories/entities: bicycles, gear and equipment, techniques, safety, routes etc. \> The subcategories/subentities for let's say "techniques" would be: Bike handling, pedaling, drafting etc. Extract keywords for each subcategory/subentity: You can do this using Ahrefs or Semrush. Each keyword would be an article. Ensure that you target the similar keywords in one article. For example: how to ride a bicycle and how can I ride a bicycle will be targeted by one article. Make the more important keyword in terms of volume and difficulty as the main keyword and the other one(s) as secondary Define main focus vs secondary focus: Out of all these categories/entities - there will be one that you would want to dominate in every way. So, focus on just that in the start. This will be your main focus. Try to answer ALL the questions pertaining to that. You can extract the questions using Ahrefs. \> Ahrefs > keywords explorer \> enter keyword \> Questions \> Download the list and cluster the similar ones. This will populate your main focus category/entity and will drive most of the traffic. Now, you need to write in other categories/subentities as well. This is not just important, but crucial to complete the topical map loop. In simple words, if you do this Google sees you as a comprehensive source on the topic - otherwise, it ignores you and you don't get ranked Define the URLs End result: List of all the entities and sub-entities about the main site topic in the form of categories and subcategories respectively. A complete list of ALL the questions about the main focus and at around 10 questions for each one of the subcategories/subentities that are the secondary focus Content Writing So, now that there's a plan. Content needs to be produced. Pick out a keyword (which is going to be a question) and... Answer the question Write about 5 relevant entities Answer 10 relevant questions Write a conclusion Keep the format the same for all the articles. Content Uploading, formatting and onsite SEO Ensure the following is taken care of: H1 Permalink H2s H3s Lists Tables Meta description Socials description Featured image 2 images in text \\Schema Relevant YouTube video (if there is) Note: There are other pointers link internal linking in a semantically relevant way but this should be good to start with. Faster Indexing Indexing means Google has read your page. Ranking only after this step has been done. Otherwise, you can't rank if Google hasn't read the page. Naturally, this is a slow process. But, we expedite it in multiple ways. You can use RankMath to quickly index the content. Since, there are a lot of bulk pages you need a reliable method. Now, this method isn't perfect. But, it's better than most. Use Google Indexing API and developers tools to get indexed. Rank Math plugin is used. I don't want to bore you and write the process here. But, a simple Google search can help you set everything up. Additionally, whenever you post something - there will be an option to INDEX NOW. Just press that and it would be indexed quite fast. Conversion rate optimisation Once you get traffic, try adding tables right after the introduction of an article. These tables would feature a relevant product on Amazon. This step alone increased our earnings significantly. Even though the content is informational and NOT review. This still worked like a charm. Try checking out the top pages every single day in Google analytics and add the table to each one of them. Moreover, we used EZOIC video ads as well. That increased the RPM significantly as well. Both of these steps are highly recommended. Overall, we implemented over 11 fixations but these two contribute the most towards increasing the RPM so I would suggest you stick to these two in the start. Guest Posting We made additional income by selling links on the site as well. However, we were VERY careful about who we offered a backlink to. We didn't entertain any objectionable links. Moreover, we didn't actively reach out to anyone. We had a professional email clearly stated on the website and a particularly designated page for "editorial guidelines" A lot of people reached out to us because of that. As a matter of fact, the guy who bought the website is in the link selling business and plans to use the site primarily for selling links. According to him, he can easily make $4000+ from that alone. Just by replying to the prospects who reached out to us. We didn't allow a lot of people to be published on the site due to strict quality control. However, the new owner is willing to be lenient and cash it out. EEAT (Experience, Expertise, Authority, Trust) This is an important ranking factor. You need to prove on the site that your site has authors that are experienced, have expertise, authority and trust. A lot of people were reaching out to publish on our site and among them were a few established authors as well. We let them publish on our site for free, added them on our official team, connected their socials and shared them on all our socials. In return, we wanted them to write 3 articles each for us and share everything on all the social profiles. You can refer to the tables I shared above to check out the months it was implemented. We added a total of 6 writers (credible authors). Their articles were featured on the homepage and so were their profiles. Costing Well, we already had the site and the backlinks on it. Referring domains (backlinks) were already 500+. We just needed to focus on smart content and content. Here is the summary of the costs involved. Articles: 490 Avg word count per article: 1500 Total words: 735,000 (approximately) Cost per word: 2 cents (includes research, entities, production, quality assurance, uploading, formatting, adding images, featured image, alt texts, onsite SEO, publishing/scheduling etc.) Total: $14,700 ROI (Return on investment) Earning: Oct 22 - June 23 Earnings: $10,199 Sold for: $59,000 Total: $69,199 Expenses: Content: $14,700 Misc (hosting and others): $500 Total: $15,200 ROI over a 9 months period: 355.25% The plans moving forward This website was a part of a research and development experiment we did. With AI, we wanted to test new waters and transition more towards automation. Ideally, we want to use ChatGPT or some other API to produce these articles and bulk publish on the site. The costs with this approach are going to be much lower and the ROI is much more impressive. It's not the the 7-figures projects I created earlier (as you may have checked the older case studies on my profile), but it's highly scalable. We plan to refine this model even further, test more and automate everything completely to bring down our costs significantly. Once we have a model, we are going to scale it to 100s of sites. The process of my existing 7-figures websites portfolio was quite similar. I tested out a few sites, refined the model and scaled it to over 41 sites. Now, the fundamentals are the same however, we are using AI in a smarter way to do the same but at a lower cost, with a smaller team and much better returns. The best thing in my opinion is to run numerous experiments now. Our experimentation was slowed down a lot in the past since we couldn't write using AI but now it's much faster. The costs are 3-6 times lower so when it used to take $50-100k to start, grow and sell a site. Now you can pump 3-6 more sites for the same budget. This is a good news for existing business owners as well who want to grow their brand. Anyway, I am excited to see the results of more sites. In the meantime, if you have any questions - feel free to let me know. Best of luck for everything. Feel free to ask questions. I'd be happy to help. This is an AMA.

[Ultimate List] A list of Marketing Tools That I’ve tested over the years and found helpful to do better marketing with less work. More than 50 Tools To Help you with Marketing, Copywriting & Sales!

Starting to focus on marketing for your business, You will come across the same tools mentioned over and over by marketers. I would like to mention here tools that you might haven’t seen going viral in the community but actually will help you grow faster and efficiently. Starting off with My favourite Marketing Channel! #Email Marketing For SMBs Convertkit / Mailerlite / Mailchimp - These 3 Platforms are the best options for SMBs and entrepreneurs just starting out with email marketing. All 3 have free plans up to 1,000 subscribers. Scribe - Email Signature Tool, Create Great Email signatures for your emails. Liramail - Most Email marketing platforms don’t offer great email templates. This tool will help you build great email templates with drag and drop. Quick mail Auto-Warmer - Most Businesses at the beginning don’t know what to do when open rate drops. You need to use an email warmer like this to keep it up. #Email Marketing For Big Businesses SendGrid - Overall Email Marketing Tools, this tool is best for brands that have huge email lists and email marketing is the key marketing channel. Braze - This tool is leading in email marketing for large Email senders. When I was working for agencies, this was one of the best email marketing tools I had used. NeoCertified - Protect your emails for spammers and threats. To keep your email list healthy, this is a must have! Sparkloop - Referral Marketing For Email Campaigns. Email can generate great huge amount of referrals for you and Sparkloop makes it easier. #Cold Emails & Lead Generation Hunter - A Great Tool to scrape emails from domain names. The tool comes with a green free plan but Pro plan is worth the amount of features it provides. Icyleads - It’s better than Hunter as it’s heavily focused on the sales and prospecting to help you derive great results from your campaigns. Mailshake - Beginner Friend Cold Email Tool with Great features like email list warming. #Communication Tools Twilio - One do the best customer engagement platform used by Companies like Stripe and mine too. Chatlio - Use Live chat feature on your website with slack integration. My favourite easier to catch up on conversations through slack integration. Intercom - Used by Most Marketers, Industry Leading customer communication platform. Great for beginners! Chatwoot - Another Amazing Communication Tool but the best part is they have a great free plan useful for new businesses. Loom - Communicate with your audience through Videos. Loom is great for SaaS and to show human interaction to close new visitors effectively. #CRM Outseta - This tool provides great CRM and their billing system is better than other tools out their which makes it stands out! Hubspot - I don’t think this tool needs an introduction because Hubspot’s CRM is the best in industry. Salesflare - This CRM is a great alternative to hubspot as it’s beginner friendly and helpful for SMBs. #SEO Tools Ahrefs - One of the best SEO tool in the industry. They also just launched a bunch of free tools to help SEO beginners. Screaming frog - The only website crawler I have used since I bought my first domain. It’s the best! Ubersuggest- The Tool by Neil Patel is the best SEO tool for you. (I’m Joking, it’s the worst) Contentking - This tool is good at Real-time SEO Auditing, they do a lot of Marketing work through Newsletters. If you are subscribed to any SEO newsletter. You may have seen this tool. SEOquake & Semrush - SEOquake is a great tool to conduct on-page analysis, SERP, and much more. Great tool but it’s owned by Semrush. You should go for Semrush because that tool will cover all SEO aspects for you. #Content Marketing Buzzsumo - This tool is great for content research and but you may find the regular emails pretty annoying sometimes. Contentrow - Analyse Your Content and find it’s strength. Highly recommended who are weak at content structuring like me. Grammarly - If you are not a native English speaker like me, you might think you need it or not. You need it for sure for grammar corrections. #Graphic Design Tools Visme - At agencies, Infographics can be more effective than usual postscript. Visme is a graphic design tool focused on infographics and designs related to B2B and B2C. It’s great for agencies! Glorify - A Graphic Design Tool focused on E-commerce, filled with Designs useful for E-commerce store owners. Canva - All-in-one Industry leading Graphic Design Tool that everyone knows and every template is overused now. Adobe Creative Cloud ( previously Sparkpost) - It’s a great alternative to Canva filled with Amazing Stock images to use in your visuals but the only backlash is the exports in this tool are not high quality. Snaps - A Canva Alternative that might not have overused templates for your Social Accounts. #Advertising Tools Plai - It’s a great PPC tool to create Ads for Instagram and Tiktok. Wordstream - It’s an industry leading PPC Tool, great for Ad Grading and auditing. AdEspresso - This Is a tool by Hootsuite. They have a lot of Data sourced at the backend, which helps in Ad optimisation through this tool. That’s the reason I recommend this tool. #Video Editing Tools Veed Studio - I have been using Veed from last year. It’s one of the best Video Marketing Tool Optimized for Instagram & Tiktok. Synthesia - It’s a new AI video generation platform. From last few months, if you have seen marketing agencies including Videos in Emails. The chances are that’s not a Agency member taking but AI generated Human. Motionbox - It’s also a great video editing tool focused on video editing for Digital Marketers. Jitter Video - It’s a great motion design tool. Comes with great templates, the only place where other tools I mentioned lacks. It’s great and beginner friendly. #Copywriting Jasper AI - Google’s John Mueller says AI generated content is banned on Search but I think with Jasper AI you can generate SEO optimised Content but you have to put in some efforts like at least give 30 minutes for editing the Copy by yourself. Copy AI - Another AI tool to help you write better copy. This one is more focused on helping you write copy suitable for Ads and Social media campaigns. Hemingway App - To help you write more clearly and Bold. This tool is better than Grammarly if you look for writing perspective and it’s free. #Social Media Management App I’ve used a Lot of SMM Tools and that’s why going to mention all of them with a short review. Sprout social - The Best with deep insights coverage. Hootsuite - Great Scheduling tool just under sprout social. Later - Heavily Focused on Instagram from beginning and Now Tiktok too. SkedSocial - It’s like a Later alternative with great addition features like link-in-bio. Facebook’s Business Manager- Great but sometimes bugs can make a huge issue for you and customer support is like dead. Tweet Hunter & Hypefury- Both are Twitter Scheduling tools growing very fast on platform and are great for growth. Buffer - It’s a great tool but I haven’t seen any new updates to help with management. Zoho Social - It’s a great SMM tool and if you use other marketing solutions from Zoho. It’s a must have! #Market Research Tool • SparkToro - That’s the only one I have ever used. It’s great for audience research and comes with great customer service. Founded by Rand Fishkin, it’s one of the best research tool. #Influencer Marketing & UGC InfluenceGrid - A free search engine To find Tiktok & Instagram Influencers for your campaigns. Tiktok Creative Center- TikTok’s in-built tool called “Creative Center” is the best to find content trends, audience demographics and much more. Archive - Find Instagram Stories and Posts mentioning Your brands and use them as Ads for your business Marketing. #Landing Page Builders Leadpages - Its a great landing page builder because the integration and drag-and-drop features makes it easier to work with! Cardd co - A Great Landing page builder with easy step up but it lacks the copywriting and tracking features. Instapage - It’s one of the best out and I think the overall product is effective enough to help you stand out with your landing page. Unbounce - It’s a great alternative to Instapage due its well polished landing page templates that might be helpful for you. #Community Building Mighty Networks - A Great Community building platform, and you can also sell courses within the platform. Circle so - A great alternative to Mighty networks focused on Communities specifically. We are currently using for small community Of ours. #Sales Tools Drift - You can get much more out of Drift than just sales tools but The Sales solutions provided in Drift are one of the best. Salesforce - It’s the industry Sales solution provider. A go-to and have various pricing plans making it suitable for majority of SMBs. #Social Proof Tools People don’t have enough time to search across internet to decide to trust you after seeing your Ad first time. That’s what you might be facing too. Here are two tools I absolutely love for social proof! Use Proof - Show Recent Activities occurring on your website and build the trust of your visitors. Testimonial to - Gather Testimonials across Social Media platforms related to your business with this tool. Capture tweets and comments mentioning your brands and mention them. #Analytics Tools Plausible Analytics- A privacy friendly Analytics alternative to Google Analytics if you hate Analytics 4 like me. Mixpanel - Product Analytics and funnel reports better than Google Analytics. #Reddit Marketing Gummysearch- This tool will help To find your target audience on Reddit and interact with them with its help and close your new customers. Howitzer- It’s another pretty similar tool to Gummysearch focused on Reddit cold outreach to get clients and new customers. Both are great but Gummysearch provides better customer support while Howtizer is helpful on a large scale Reddit Marketing. #Text Marketing Klaviyo - It’s an email + SMS marketing tool, it’s taking up space in marketing industry very quickly as an industry leader due to its great integrations but you need to learn the platform usage to maximise the outcome. Cartloop - This tool provides great text marketing solutions with integration with Spotify and other e-commerce marketing tools. Attentive Mobile - This is my favourite Text marketing tool due to the interactive dashboard + they have a library of Text marketing examples to help you out with your campaigns. #Other Tools I have used throughout my journey! Triple Whale - It’s a great E-commerce marketing tools with Triple pixel to help you track your campaigns more efficiently. Fastory - To create well optimized Instagram & Tiktok Stories for your business. Jotform - Online Form Builder with integrations with leading marketing tools. Gated - As an entrepreneur and marketer, you may receive a bunch of unwanted emails. Use Gated to get rid of them and receive useful mails only! ClickUp- The main Tool for Project Management, one of the best and highly recommended. Riverside - Forget Zoom or Google Meet, For your Podcast Interviews and Marketing conferences. You need riverside with great video quality and recording features. Manychat- Automate your Instagram DMs and interact with your followers more efficiently + sell out your products/ services when you are offline. Calendy - To schedule meetings with your ideal clients. ServiceProviderPro - It’s a client portal for SEO & Growing Agencies, very helpful in scaling agencies. SendCheckit - Compare your Email Subject Lines with 100,000+ others in the database for free. Otter AI - Using AI track your meetings more effectively, you can easily edit, annotate and share notes from the meetings. Ryte - Optimise your website User experience with this tool focused on UX aspects + SEO too. PhantomBuster - Scrape LinkedIn Profile and Data from Facebook/LinkedIn groups. I clearly love this tool! #Honourable Mentions Zapier - The Only tool you need to integrate your favourite tool with a new effective tool. Elementor - That’s what I use for web design and it’s great! Marketer Hire - To hire world class marketers to work with you. InShot & Capcut - I create Instagram Reels and TikTok’s and life without these tools isn’t possible. Nira - It’s a great tool to Manage your workspace and this tool has launched many marketing templates in-built helpful for marketers and also entrepreneurs. X - The tool you love that wasn’t mentioned here is valuable and I honour that tool and share that if you would like to! I mean thanks for reading what I have curated all over my life as a marketer. I share 5 Marketing Tools, 5 Marketing Resources and 1 Free Resourceevery week in my newsletter, you can subscribe here to receive that for free. Also, You can read an expanded list of email marketing tools in this Reddit post!

In 2018, I started an AI chatbot company...today, we have over 4000 paying customers and ChatGPT is changing EVERYTHING

Intro: 5 years ago, my co-founders and I ventured into the space of AI chatbots and started our first truly successful company. Never in a million years did I see myself in this business and we truly stumbled upon the opportunity by chance. Prior to that, we ran a successful lead generation business and questioned whether a simple ai chat product would increase our online conversions. Of the 3 co-founders, I was skeptical that it would, but the data was clear that we had something that really worked. We built a really simple MVP version of the product and gave it to some of our top lead buyers who saw even better conversion improvements on their own websites. In just a matter of weeks, a new business opportunity was born and a major pivot away from our lead generation business started. Our growth story: Startup growth is really interesting and in most cases, founders aren't really educated on what a typical growth curve looks like. While we hear about "hockey stick" growth curves, it's really atypical to actually see or experience this. From my experience, growth curves take place in a "stair curve". For example, you can scrap your way to a $100k run rate without much process or tracking. You can even get to $1 million ARR being super disorganized. As you start going beyond $1M ARR, things start to break and growth can flatten out while you put new processes and systems in place. Eventually you'll get to $2M or 3M with your new strategy and then things start breaking again. I've seen the process repeat itself and as you increase your ARR, the processes and systems become more difficult to work through...mainly because more people get involved and the product becomes more complex. When you do end up cracking the code in each step, the growth accelerates faster and faster before things start to break down and flatten out again. Without getting too much into the numbers, here were some of our initial levers for growth: Our first "stair" step was to leverage our existing customer base from our prior lead generation business. Having prior business relationships and a proven track record made it really simple to have conversations with people who already trusted us to try something new that we had to offer. Stair #2 was to build out a partner channel. Since our chat product involved a web developer or agency installing the chat on client sites, we partnered with these developers and agencies to leverage their already existing customer bases. We essentially piggy-backed off of their relationships and gave them a cut of the revenue. We built an internal partner tracking portal which took 6+ months, but it was well worth it. Stair #3 was our most expensive step, biggest headache, but added the most revenue. After COVID, we had and SDR/Account Executive sales team of roughly 30 people. It added revenue fast, but the payback periods were 12+ months so we had to cut back on this strategy after exhausting our universe of clients. Stair #4 involves a variety of paid advertisement strategies with product changes and the introduction of new onboarding features. We're in the middle of this stair and hope it's multiple years before things breakdown again. Don't give up I know it sounds really cliché, but the #1 indicator of success is doing the really boring stuff day in and day out and making incremental improvements. As the weeks, months, and years pass by, you will slowly gain domain expertise and start to see the gaps in the market that can set you apart from your competition. It's so hard for founders to stay focused and not get distracted so I would say it's equally as important to have co-founders who hold each other accountable on what your collective goals are. How GPT is changing everything I could write pages and pages about how GPT is going to change how the world operates, but I'll keep it specific to our business and chatbots. In 2021, we built an industry specific AI model that did a great job of classifying intents which allowed us to train future actions during a chat. It was a great advancement in our customer's industry at the time. With GPT integrated into our system, that training process that would take an employee hours to do, can be done in 5 minutes. The model is also cheaper than our own and more accurate. Because of these training improvements, we have been able to conduct research that is allowing us to leverage GPT models like no one else in the industry. This is both in the realm of chat and also training during onboarding. I really want to refrain from sharing our company, but if you are interested in seeing a model trained for your specific company or website, just PM me your link and I'll send you a free testing link with a model fully trained for your site to play around with. Where we are headed and the dangers of AI The level of advancement in AI is not terribly dangerous in its current state. I'm sure you've heard it before, but those who leverage the technology today will be the ones who get ahead. In the coming years, AI will inevitably replace a large percentage of human labor. This will be great for overall value creation and productivity for the world, but the argument that humans have always adapted and new jobs will be created is sadly not going to be as relevant in this case. As the possibility of AGI becomes a reality in the coming years or decades, productivity through AI will be off the charts. There is a major risk that human innovation and creative thinking will be completely stalled...human potential as we know it will be capped off and there will need to be major economic reform for displaced workers. This may not happen in the next 5 or 10 years, but you would be naïve not to believe the world we live in today will not be completely different in 20 to 30 years. Using AI to create deepfakes, fake voice agents, scam the unsuspecting, or exploit technical vulnerabilities are just a few other examples I could write about, but don't want to go into to much detail for obvious reasons. Concluding If you found the post interesting or you have any questions, please don't hesitate to ask. I'll do my best to answer whatever questions come from this! &#x200B; \*EDIT: Wasn't expecting this sort of response. I posted this right before I went to sleep so I'll get to responding soon.

Follow Along as I Flip this Website - Case Study

I am starting a new case study where I will be documenting my attempt to flip a website that I just purchased from Flippa. However, unlike most case studies where people hide certain parts and details from the public I will instead be sharing everything. That means you will know the exact URL of the site that I purchased and I will share everything with you all as I progress.I know that case studies are lot more interesting and you can learn better when you can see real examples of what I am talking about. Enough of the chatting, let's jump straight into this new case study and I will explain what this is all about. Before you get into the case study I want to give you the option of reading this one my website where all of the images can be seen within the post and it is easier to read. I also want to say that I have nothing to sell you or anything close to it. So if you want to read it there you can do so here ##Introductory Video I have put together a video that talks about many of the things that I cover in this article. So if you would rather watch a video you can watch that here - https://www.youtube.com/watch?v=EE3SxtNnqts However, I go into more detail in the actual article FYI. Also, I plan on using Youtube very frequently in this case study so be on the lookout for new videos.There is going to be a video that will accompany every single case study post because I like having it being presented in two different mediums. ##The Website I Just Bought Around a week ago I made a new website purchase from Flippa and you can view the website's Flippa listing here - https://flippa.com/6439965-hvactraining101-com Screenshot of the Homepage - http://imgur.com/T6Iv1QN I paid $1,250 for the site and you will soon see that I got a really good deal. As you might be able to tell from the URL, this site is focused around training and education for becoming a HVAC technician. This is a lucrative niche to be in and Adsense pays very well. I do not have control of the site yet due to the transfer process not being completed. However, I am hoping within a few days everything will be finalized and I will take full control of the site. In the meantime, I figured it would be a good time to put together the introduction post for this new case study! ##Why I Bought this Website Now that you have a general idea of the website that I purchased, I now want to explain the reasoning behind the purchase. There are 3 major reasons for this purchase and I will explain each one of them below. GREAT Price As I mentioned earlier, I bought this website for $1,250. However, that doesn't mean a whole lot unless you know how much the site is making each month. Screenshot of the earnings for the last 12 months - http://imgur.com/NptxCHy Average Monthly Profits: 3 Month = $126 6 Month = $128 12 Month = $229.50 Let's use the 6 month average of $128/month as our baseline average. Since it is making on average $128/month and it was sold for $1,250 then that means I bought this site at a multiple of 9.76x! Most sites in today's market go for 20x-30x multiples. As you can see, I got a great deal on this site. Although the great price was the biggest reason for me buying this site there are other factors that persuaded me as well. You need to remember that just because you can get a website for a good price it doesn't mean it is a good deal. There are other factors that you need to look at as well. Extremely Under Optimized This site is currently being monetized mainly by Adsense and a very small amount from Quinstreet. From my experience with testing and optimizing Adsense layouts for my site in my Website Investing case study I know the common ad layouts that work best for maximizing Adsense revenue. With that being said, I can quickly determine if a website is being under optimized in terms of the ad layout. One of the first things I did when analyzing this site was examine the ad layout it was using. Screenshot of the website with the ad layout the previous owner was using - http://imgur.com/wqleLVA There is only ONE ad per page being used, that's it. Google allows up to 6 total ads to be used per page and you can imagine how much money is being left on the table because of this. I am estimating that I can probably double the earnings for the site practically overnight once I add more ads to the site. Adding more ads in combination with my favorite Adsense plugin, AmpedSense, I will be able to easily boost the earnings for this site quickly. It is also worth mentioning how lucrative this niche is and how much advertisers are willing to spend on a per click basis. The average CPC for the top keywords this site is currently ranking for in Google - http://imgur.com/ifxiy8B Look at those average CPC numbers, they are insanely high! I could be making up to $25 per click for some of those keywords, which is so absurd to me. Combine these extremely high CPC with the fact that the site currently only has one ad per page and you can start to understand just how under optimized this site truly is. I also plan on utilizing other ad networks such as Quinstreet and Campus Explorer more as well. These two networks are targeted at the education niche which works very well with my site. I will be testing to see if these convert better than normal Adsense ads. Goldmine of Untapped Keywords One of the biggest opportunities I see for growing this site is to target local keywords related to HVAC training. As of right now, the site has only scratched the surface when it comes to trying to rank for state/city keywords. Currently there are only two pages on the entire website which go after local keywords, those two pages target Texas and Florida HVAC search terms. These two pages are two of the more popular pages in terms of total amount of traffic. See the screenshot of the Google Analytics - http://imgur.com/NB0xJ4G Two out of the top five most popular pages for the entire website are focused on local search terms. However, these are the ONLY two pages that target local search terms on the whole site! There are 48 other states, although there may not be search volume for all states, and countless cities that are not being targeted. Why do I think this is such a good opportunity? For a few reasons: Local keywords are a lot easier to rank for in Google than more general keywords This site has been able to rank for two states successfully already and it proves it is possible Traffic going to these local pages is WAY more targeted and will convert at a much higher rate, which means more commissions for me There are so many more states and cities that get a good amount of searches that I can target To give you an idea of the type of keywords these local pages rank for, you can see the top keywords that the Florida page is ranking for in Google: Top ranking keywords for the Florida page - http://imgur.com/j7uKzl2 As you can see these keywords don't get a ton of searches each month, but ranking 1st for a keyword getting 90 searches a month is better than being ranked 10th for a keyword getting 1,000 searches a month. I have started to do some keyword research for other states and I am liking what I am finding so far. Keywords that I have found which I will be targeting with future articles - http://imgur.com/8CCCCWU I will go into more detail about my keyword research in future articles, but I wanted to give you an idea of what my strategy will be! I also wanted to share why I am super excited about the future potential to grow this site by targeting local keywords. ##Risks Yes, there are many good things about this website, but there are always risks involved no matter what the investment is. The same thing goes for this site. Below are some of the risks that I currently see. HTML Site This website is a HTML site and I will need to transfer it to Wordpress ASAP. I have been doing some research on this process and it shouldn't be too hard to get this over to Wordpress. In doing so it will make adding content, managing the back end and just about everything else easier. Also, I am hoping that when I transfer it to Wordpress that it will become more optimized for Google which will increase keyword rankings. Declining Earnings Looking at the last 12 months of earnings you will notice a drop off from last year till now. Earnings from the last 12 months - http://imgur.com/WsotZsj In May of 2015 it looks like the site earned right around $500, which is much higher than the $128 that it is earning now. However, the last 7 or so months have been consistent which is a good sign. Even though the earnings are much lower now then they were a year ago it is good to know that this site has the potential to earn $500/month because it has done it before. Slightly Declining Traffic In the last 12 months the site's traffic has declined, however, it looks like it is picking back up. Traffic from the last 12 months - http://imgur.com/aiYZW9W The decline is nothing serious, but there is a drop on traffic. Let's take a look at the complete history of this site's traffic so we can get a better idea of what is going on here: Complete traffic history - http://imgur.com/tYmboVn The above screenshot is from 2012 all the way up to right now. In the grand scheme of things you can see that the traffic is still doing well and it looks like it is on the upswing now. Those three risks mentioned above are the three biggest risks with this site at this point. It is always good to note the risks and do everything you can to prevent them from causing a problem. ##My Growth Strategy Whenever I purchase a new site I always create an outline or plan on how I will grow the site. Right now, I have some basic ideas on how I will grow this site, but as I go on I will continue to change and optimize my strategies to be more effective. Below I have outlined my current plans to grow: Add more Adsense Ads The very first thing I will do once I get control of the site is add more ads per page. I am predicting that by just adding a few more ads per page I will be able to more than likely double the earnings. I will touch on exactly how I will be optimizing the ad layouts in future posts. Test other Ad Networks I will be doing a lot of testing and experimenting when it comes to the ad networks. I plan on trying out Adsense, Media.net, Quinstreet, Campus Explorer and finding the combination of those 4 which produces the most revenue. The Adsense and Media.net ads will perform well on the more general pages while Quinstreet and Campus Explorer ads will be geared towards the local search terms. There will probably be other ad networks I will try out but these are the four which I will be using right away. If you are aware of any other ad networks out there which are geared towards the education niche please let me know in the comments below! Target Local Keywords with new Content I have already touched on this, but I will starting to produce content targeting these local keywords ASAP. The sooner I add the content to the site the sooner it will start to rank and bring in traffic. I will not be writing my own content and instead I will be outsourcing all of it via Upwork. I will show you all how I go about outsourcing content production and you can see my process for doing that. ##Goals for this Website My goal for the website is to have it valued at $10,000+ within 12 months. Let's break down this larger goal into smaller chunks which will make achieving it easier and more attainable. Earnings - $500/month To get the site valued at $10,000 the site will need to be making $500/month using a 20x monthly multiple. Right now, the site is making around $130/month so it has a ways to before it reaches the $500 a month mark. However, after doing some Adsense optimization I think we could push the earnings to around $300/month without much work. From there, it will come down to trying to bring in more traffic! Traffic - 5,000 Visitors per Month Why 5,000 visitors? Because that is how much traffic it is going to take to get to the $500/month goal. Let me explain how I came to this conclusion: The average RPM for this site is currently $50, which means for every 1,000 page views the site earns $50. After I optimize the Adsense layout for the site and add more ads per page I think I will be able to double the RPM to $100. Using the RPM of $100 the site will need to have 5,000 monthly visitors to earn $500. So 5,000 monthly visitors is the traffic goal I have set and aiming for! The site is currently getting around 3,000 visitors per month so I will need to add an extra 2,000 visitors to get to this goal. ##Want to Follow this Case Study? I will be using Youtube a lot in this case study so make sure to follow my Youtube channel here - www.youtube.com/c/joshshogren Other than that, I think that is going to bring us to the end of the introductory post for this new case study. I hope that you enjoyed reading and that you are excited to follow along! If you have any suggestions to make this case study better PLEASE let me know in the comment below. I want to make this case study the best one I have done yet. Talk to you all in the comment section.

Started a content marketing agency 6 years ago - $0 to $5,974,324 (2023 update)

Hey friends, My name is Tyler and for the past 6 years, I’ve been documenting my experience building a content marketing agency called Optimist. Year 1 - 0 to $500k ARR Year 2 - $500k to $1MM ARR Year 3 - $1MM ARR to $1.5MM(ish) ARR Year 4 - $3,333,686 Revenue Year 5 - $4,539,659 Revenue How Optimist Works First, an overview/recap of the Optimist business model: We operate as a “collective” of full time/professional freelancers Everyone aside from me is a contractor Entirely remote/distributed team Each freelancer earns $65-85/hour Clients pay us a flat monthly fee for full-service content marketing (research, strategy, writing, editing, design/photography, reporting and analytics, targeted linkbuilding, and more) We recently introduced hourly engagements for clients who fit our model but have some existing in-house support Packages range in price from $10-20k/mo We offer profit share to everyone on our core team as a way to give everyone ownership in the company In 2022, we posted $1,434,665 in revenue. It was our highest revenue year to date and brings our lifetime total to $5,974,324. Here’s our monthly revenue from January 2017 to December of 2022. But, like every year, it was a mix of ups and downs. Here’s my dispatch for 2023. — Running a business is like spilling a drink. It starts as a small and simple thing. But, if you don’t clean it up, the spill will spread and grow — taking up more space, seeping into every crack. There’s always something you could be doing. Marketing you could be working on. Pitches you could be making. Networking you could be doing. Client work you could help with. It can be all-consuming. And it will be — if you don’t clean up the spill. I realized this year that I had no containment for the spill that I created. Running an agency was spilling over into nearly every moment of my life. When I wasn’t working, I was thinking about work. When I wasn’t thinking about work, I was dreaming about it. Over the years, I’ve shared about a lot of my personal feelings and experience as an entrepreneur. And I also discussed my reckoning with the limitations of running the business we’ve built. My acceptance that it was an airplane but not a rocket. And my plan to try to compartmentalize the agency to make room in my life for other things — new business ideas, new revenue streams, and maybe some non-income-producing activity. 🤷 What I found in 2022 was that the business wasn’t quite ready for me to make that move. It was still sucking up too much of my time and attention. There were still too many gaps to fill and I was the one who was often filling them. So what do you do? Ultimately you have two choices on the table anytime you run a business and it’s not going the way you want it: Walk away Turn the ship — slowly For a huge number of reasons (personal, professional, financial, etc), walking away from Optimist was not really even an option or the right move for me. But it did feel like things needed to change. I needed to keep turning the ship to get it to the place where it fit into my life — instead of my life fitting around the business. This means 2022 was a year of transition for the agency. (Again?) Refocusing on Profit Some money is better than no money. Right? Oddly, this was one of the questions I found myself asking in 2022. Over the years, we’ve been fortunate to have many clients who have stuck with us a long time. In some cases, we’ve had clients work with us for 2, 3, or even 4 years. (That’s over half of our existence!) But, things have gotten more expensive — we’ve all felt it. We’ve had to increase pay to remain competitive for top talent. Software costs have gone up. It’s eaten into our margin. Because of our increasing costs and evolving scope, many of our best, most loyal clients were our least profitable. In fact, many were barely profitable — if at all. We’ve tried to combat that by increasing rates on new, incoming clients to reflect our new costs and try to make up for shrinking margin on long-term clients. But we didn’t have a good strategy in place for updating pricing for current clients. And it bit us in the ass. Subsidizing lower-profit, long-term clients with new, higher-margin clients ultimately didn’t work out. Our margins continued to dwindle and some months we were barely breaking even while posting six-figures of monthly revenue. 2022 was our highest revenue year but one of our least profitable. It only left one option. We had to raise rates on some of our long-term clients. But, of course, raising rates on a great, long-term client can be delicate. You’ve built a relationship with these people over the years and you’re setting yourself up for an ultimatum — are you more valuable to the client or is the client more valuable to you? Who will blink first? We offered all of these clients the opportunity to move to updated pricing. Unfortunately, some of them weren’t on board. Again, we had 2 options: Keep them at a low/no profit rate Let them churn It seems intuitive that having a low-profit client is better than having no client. But we’ve learned an important lesson many times over the years. Our business doesn’t scale infinitely and we can only handle so many clients at a time. That means that low-profit clients are actually costing us money in some cases. Say our average client generates $2,500 per month in profit — $30,000 per year. If one of our clients is only generating $500/mo in profit, working with them means missing out on bringing on a more profitable client (assuming our team is currently at capacity). Instead of $30,000/year, we’re only making $6,000. Keeping that client costs us $24,000. That’s called opportunity cost. So it’s clear: We had to let these clients churn. We decided to churn about 25% of our existing clients. On paper, the math made sense. And we had a pretty consistent flow of new opportunities coming our way. At the time, it felt like a no-brainer decision. And I felt confident that we could quickly replace these low-profit clients with higher-margin ones. I was wrong. Eating Shit Right after we initiated proactively churning some of our clients, other clients — ones we planned to keep — gave us notice that they were planning to end the engagement. Ouch. Fuck. We went from a 25% planned drop in revenue to a nearly 40% cliff staring us right in the face. Then things got even worse. Around Q3 of this year, talk of recession and layoffs really started to intensify. We work primarily with tech companies and startups. And these were the areas most heavily impacted by the economic news. Venture funding was drying up. Our leads started to slow down. This put us in a tough position. Looking back now, I think it’s clear that I made the wrong decision. We went about this process in the wrong way. The reality sinks in when you consider the imbalance between losing a client and gaining a client. It takes 30 days for someone to fire us. It’s a light switch. But it could take 1-3 months to qualify, close, and onboard a new client. We have lots of upfront work, research, and planning that goes into the process. We have to learn a new brand voice, tone, and style. It’s a marathon. So, for every client we “trade”, there’s a lapse in revenue and work. This means that, in retrospect, I would probably have made this transition using some kind of staggered schedule rather than a cut-and-dry approach. We could have gradually off-boarded clients when we had more definitive work to replace them. I was too confident. But that’s a lesson I had to learn the hard way. Rebuilding & Resetting Most of the voluntary and involuntary churn happened toward the end of 2022. So we’re still dealing with the fall out. Right now, it feels like a period of rebuilding. We didn’t quite lose 50% of our revenue, but we definitely saw a big hit heading into 2023. To be transparent: It sucks. It feels like a gigantic mistake that I made which set us back significantly from our previous high point. I acted rashly and it cost us a lot of money — at least on the surface. But I remind myself of the situation we were in previously. Nearly twice the revenue but struggling to maintain profitability. Would it have been better to try to slowly fix that situation and battle through months of loss or barely-break-even profits? Or was ripping off the bandaid the right move after all? I’m an optimist. (Heh, heh) Plus, I know that spiraling over past decisions won’t change them or help me move forward. So I’m choosing to look at this as an opportunity — to rebuild, reset, and refocus the company. I get to take all of the tough lessons I’ve learned over the last 6 years and apply them to build the company in a way that better aligns with our new and current goals. It’s not quite a fresh, clean start, but by parting ways with some of our oldest clients, we’ve eliminated some of the “debt” that’s accumulated over the years. We get a chance to fully realize the new positioning that we rolled out last year. Many of those long-term clients who churned had a scope of work or engagement structure that didn’t fit with our new positioning and focus. So, by losing them, we’re able to completely close up shop on the SOWs that no longer align with the future version of Optimist. Our smaller roster of clients is a better fit for that future. My job is to protect that positioning by ensuring that while we’re rebuilding our new roster of clients we don’t get desperate. We maintain the qualifications we set out for future clients and only take on work that fits. How’s that for seeing the upside? Some other upside from the situation is that we got an opportunity to ask for candid feedback from clients who were leaving. We asked for insight about their decision, what factors they considered, how they perceived us, and the value of our work. Some of the reasons clients left were obvious and possibly unavoidable. Things like budget cuts, insourcing, and uncertainty about the economy all played at least some part of these decisions. But, reading between the lines, where was one key insight that really struck me. It’s one of those, “oh, yeah — duh — I already knew that,” things that can be difficult to learn and easy to forget…. We’re in the Relationship Business (Plan Accordingly) For all of our focus on things like rankings, keywords, content, conversions, and a buffet of relevant metrics, it can be easy to lose the forest for the trees. Yes, the work itself matters. Yes, the outcomes — the metrics — matter. But sometimes the relationship matters more. When you’re running an agency, you can live or die by someone just liking you. Admittedly, this feels totally unfair. It opens up all kinds of dilemmas, frustration, opportunity for bias and prejudice, and other general messiness. But it’s the real world. If a client doesn’t enjoy working with us — even if for purely personal reasons — they could easily have the power to end of engagement, regardless of how well we did our actual job. We found some evidence of this in the offboarding conversations we had with clients. In some cases, we had clients who we had driven triple- and quadruple-digital growth. Our work was clearly moving the needle and generating positive ROI and we had the data to prove it. But they decided to “take things in another direction” regardless. And when we asked about why they made the decision, it was clear that it was more about the working relationship than anything we could have improved about the service itself. The inverse is also often true. Our best clients have lasting relationships with our team. The work is important — and they want results. But even if things aren’t quite going according to plan, they’re patient and quick to forgive. Those relationships feel solid — unshakeable. Many of these folks move onto new roles or new companies and quickly look for an opportunity to work with us again. On both sides, relationships are often more important than the work itself. We’ve already established that we’re not building a business that will scale in a massive way. Optimist will always be a small, boutique service firm. We don’t need 100 new leads per month We need a small, steady roster of clients who are a great fit for the work we do and the value we create. We want them to stick around. We want to be their long-term partner. I’m not built for churn-and-burn agency life. And neither is the business. When I look at things through this lens, I realize how much I can cut from our overall business strategy. We don’t need an ultra-sophisticated, multi-channel marketing strategy. We just need strong relationships — enough of them to make our business work. There are a few key things we can take away from this as a matter of business strategy: Put most of our effort into building and strengthening relationships with our existing clients Be intentional about establishing a strong relationship with new clients as part of onboarding Focus on relationships as the main driver of future business development Embracing Reality: Theory vs Practice Okay, so with the big learnings out the way, I want to pivot into another key lesson from 2022. It’s the importance of understanding theory vs practice — specifically when it comes to thinking about time, work, and life. It all started when I was considering how to best structure my days and weeks around running Optimist, my other ventures, and my life goals outside of work. Over the years, I’ve dabbled in many different ways to block time and find focus — to compartmentalize all of the things that are spinning and need my attention. As I mapped this out, I realized that I often tried to spread myself too thin throughout the week. Not just that I was trying to do too much but that I was spreading that work into too many small chunks rather than carving out time for focus. In theory, 5 hours is 5 hours. If you have 5 hours of work to get done, you just fit into your schedule whenever you have an open time slot. In reality, a single 5-hour block of work is 10x more productive and satisfying than 10, 30-minute blocks of work spread out across the week. In part, this is because of context switching. Turning your focus from one thing to another thing takes time. Achieving flow and focus takes time. And the more you jump from one project to another, the more time you “lose” to switching. This is insightful for me both in the context of work and planning my day, but also thinking about my life outside of Optimist. One of my personal goals is to put a finite limit on my work time and give myself more freedom. I can structure that in many different ways. Is it better to work 5 days a week but log off 1 hour early each day? Or should I try to fit more hours into each workday so I can take a full day off? Of course, it’s the latter. Both because of the cost of context switching and spreading work into more, smaller chunks — but also because of the remainder that I end up with when I’m done working. A single extra hour in my day probably means nothing. Maybe I can binge-watch one more episode of a new show or do a few extra chores around the house. But it doesn’t significantly improve my life or help me find greater balance. Most things I want to do outside of work can’t fit into a single extra hour. A full day off from work unlocks many more options. I can take the day to go hiking or biking. I can spend the day with my wife, planning or playing a game. Or I can push it up against the weekend and take a 3-day trip. It gives me more of the freedom and balance that I ultimately want. So this has become a guiding principle for how I structure my schedule. I want to: Minimize context switching Maximize focused time for work and for non-work The idea of embracing reality also bleeds into some of the shifts in business strategy that I mentioned above. In theory, any time spent on marketing will have a positive impact on the company. In reality, focusing more on relationships than blasting tweets into the ether is much more likely to drive the kind of growth and stability that we’re seeking. As I think about 2023, I think this is a recurring theme. It manifests in many ways. Companies are making budget cuts and tough decisions about focus and strategy. Most of us are looking for ways to rein in the excess and have greater impact with a bit less time and money. We can’t do everything. We can’t even do most things. So our #1 priority should be to understand the reality of our time and our effort to make the most of every moment (in both work and leisure). That means thinking deeply about our strengths and our limitations. Being practical, even if it feels like sacrifice. Update on Other Businesses Finally, I want to close up by sharing a bit about my ventures outside of Optimist. I shared last year how I planned to shift some of my (finite) time and attention to new ventures and opportunities. And, while I didn’t get to devote as much as I hoped to these new pursuits, they weren’t totally in vain. I made progress across the board on all of the items I laid out in my post. Here’s what happened: Juice: The first Optimist spin-out agency At the end of 2021, we launched our first new service business based on demand from Optimist clients. Focused entirely on building links for SEO, we called the agency Juice. Overall, we made strong progress toward turning this into a legitimate standalone business in 2022. Relying mostly on existing Optimist clients and a few word-of-mouth opportunities (no other marketing), we built a team and set up a decent workflow and operations. There’s still many kinks and challenges that we’re working through on this front. All told, Juice posted almost $100,000 in revenue in our first full year. Monetizing the community I started 2022 with a focus on figuring out how to monetize our free community, Top of the Funnel. Originally, my plan was to sell sponsorships as the main revenue driver. And that option is still on the table. But, this year, I pivoted to selling paid content and subscriptions. We launched a paid tier for content and SEO entrepreneurs where I share more of my lessons, workflows, and ideas for building and running a freelance or agency business. It’s gained some initial traction — we reached \~$1,000 MRR from paid subscriptions. In total, our community revenue for 2022 was about $2,500. In 2023, I’m hoping to turn this into a $30,000 - $50,000 revenue opportunity. Right now, we’re on track for \~$15,000. Agency partnerships and referrals In 2022, we also got more serious about referring leads to other agencies. Any opportunity that was not a fit for Optimist or we didn’t have capacity to take on, we’d try to connect with another partner. Transparently, we struggled to operationalize this as effectively as I would have liked. In part, this was driven by my lack of focus here. With the other challenges throughout the year, I wasn’t able to dedicate as much time as I’d like to setting goals and putting workflows into place. But it wasn’t a total bust. We referred out several dozen potential clients to partner agencies. Of those, a handful ended up converting into sales — and referral commission. In total, we generated about $10,000 in revenue from referrals. I still see this as a huge opportunity for us to unlock in 2023. Affiliate websites Lastly, I mentioned spending some time on my new and existing affiliate sites as another big business opportunity in 2022. This ultimately fell to the bottom of my list and didn’t get nearly the attention I wanted. But I did get a chance to spend a few weeks throughout the year building this income stream. For 2022, I generated just under $2,000 in revenue from affiliate content. My wife has graciously agreed to dedicate some of her time and talent to these projects. So, for 2023, I think this will become a bit of a family venture. I’m hoping to build a solid and consistent workflow, expand the team, and develop a more solid business strategy. Postscript — AI, SEO, OMG As I’m writing this, much of my world is in upheaval. If you’re not in this space (and/or have possibly been living under a rock), the release of ChatGPT in late 2022 has sparked an arms race between Google, Bing, OpenAI, and many other players. The short overview: AI is likely to fundamentally change the way internet search works. This has huge impact on almost all of the work that I do and the businesses that I run. Much of our focus is on SEO and understanding the current Google algorithm, how to generate traffic for clients, and how to drive traffic to our sites and projects. That may all change — very rapidly. This means we’re standing at a very interesting point in time. On the one hand, it’s scary as hell. There’s a non-zero chance that this will fundamentally shift — possibly upturn — our core business model at Optimist. It could dramatically change how we work and/or reduce demand for our core services. No bueno. But it’s also an opportunity (there’s the optimist in me, again). I certainly see a world where we can become leaders in this new frontier. We can pivot, adjust, and capitalize on a now-unknown version of SEO that’s focused on understanding and optimizing for AI-as-search. With that, we may also be able to help others — say, those in our community? — also navigate this tumultuous time. See? It’s an opportunity. I wish I had the answers right now. But, it’s still a time of uncertainty. I just know that there’s a lot of change happening and I want to be in front of it rather than trying to play catch up. Wish me luck. — Alright friends — that's my update for 2023! I’ve always appreciated sharing these updates with the Reddit community, getting feedback, being asked tough questions, and even battling it out with some of my haters (hey!! 👋) As usual, I’m going to pop in throughout the next few days to respond to comments or answer questions. Feel free to share thoughts, ideas, and brutal takedowns in the comments. If you're interested in following the Optimist journey and the other projects I'm working on in 2023, you can follow me on Twitter. Cheers, Tyler P.S. - If you're running or launching a freelance or agency business and looking for help figuring it out, please DM me. Our subscription community, Middle of the Funnel, was created to provide feedback, lessons, and resources for other entrepreneurs in this space.

12 months ago, I was unemployed. Last week my side hustle got acquired by a $500m fintech company

I’ve learned so much over the years from this subreddit. I thought I’d return the favour and share some of my own learnings. In November 2020 my best friend and I had an idea. “What if we could find out which stocks the Internet is talking about?” This formed the origins of Ticker Nerd. 9 months later we sold Ticker Nerd to Finder (an Australian fintech company valued at around $500m). In this post, I am going to lay out how we got there. How we came up with the idea First off, like other posts have covered - you don’t NEED a revolutionary or original idea to build a business. There are tonnes of “boring” businesses making over 7 figures a year e.g. law firms, marketing agencies, real estate companies etc. If you’re looking for an exact formula to come up with a great business idea I’m sorry, but it doesn’t exist. Finding new business opportunities is more of an art than a science. Although, there are ways you can make it easier to find inspiration. Below are the same resources I use for inspiration. I rarely ever come up with ideas without first searching one of the resources below for inspiration: Starter Story Twitter Startup Ideas My First Million Trends by the Hustle Trends VC To show how you how messy, random and unpredictable it can be to find an idea - let me explain how my co-founder and I came up with the idea for Ticker Nerd: We discovered a new product on Twitter called Exploding Topics. It was a newsletter that uses a bunch of software and algorithms to find trends that are growing quickly before they hit the mainstream. I had recently listened to a podcast episode from My First Million where they spoke about Motley Fool making hundreds of millions from their investment newsletters. We asked ourselves what if we could build a SaaS platform similar to Exploding Topics but it focused on stocks? We built a quick landing page using Carrd + Gumroad that explained what our new idea will do and included a payment option to get early access for $49. We called it Exploding Stock (lol). We shared it around a bunch of Facebook groups and subreddits. We made $1,000 in pre-sales within a couple days. My co-founder and I can’t code so we had to find a developer to build our idea. We interviewed a bunch of potential candidates. Meanwhile, I was trawling through Wall Street Bets and found a bunch of free tools that did roughly what we wanted to build. Instead of building another SaaS tool that did the same thing as these free tools we decided to pivot from our original idea. Our new idea = a paid newsletter that sends a weekly report that summarises 2 of the best stocks that are growing in interest on the Internet. We emailed everyone who pre-ordered access, telling them about the change and offered a full refund if they wanted. tl;dr: We essentially combined two existing businesses (Exploding Topics and Motley Fool) and made it way better. We validated the idea by finding out if people will actually pay money for it BEFORE we decided to build it. The idea we started out with changed over time. How to work out if your idea will actually make money It’s easy to get hung up on designing the logo or choosing the perfect domain name for your new idea. At this stage none of that matters. The most important thing is working out if people will pay money for it. This is where validation comes in. We usually validate ideas using Carrd. It lets you build a simple one page site without having to code. The Ticker Nerd site was actually built using a Carrd template. Here’s how you can do it yourself (at a high level): Create a Carrd pro account (yes it's a $49 one off payment but you’ll get way more value out of it). Buy a cheap template and send it to your Carrd account. You can build your own template but this will save you a lot of time. Once the template reaches your Carrd account, duplicate it. Leave the original so it can be duplicated for other ideas. Jump onto Canva (free) and create a logo using the free logos provided. Import your logo. Add copy to the page that explains your idea. Use the AIDA formula. Sign up to Gumroad (free) and create a pre-sale campaign. Create a discounted lifetime subscription or version of the product. This will be used pre-sales. Add the copy from the site into the pre-sale campaign on Gumroad. Add a ‘widget’ to Carrd and connect it to Gumroad using the existing easy integration feature. Purchase a domain name. Connect it to Carrd. Test the site works. Share your website Now the site is ready you can start promoting it in various places to see how the market reacts. An easy method is to find relevant subreddits using Anvaka (Github tool) or Subreddit Stats. The Anvaka tool provides a spider map of all the connected subreddits that users are active in. The highlighted ones are most relevant. You can post a thread in these subreddits that offer value or can generate discussion. For example: ‘I’m creating a tool that can write all your copy, would anyone actually use this?’ ‘What does everything think of using AI to get our copy written faster?’ ‘It’s time to scratch my own itch, I’m creating a tool that writes marketing copy using GPT-3. What are the biggest problems you face writing marketing copy? I’ll build a solution for it’ Reddit is pretty brutal these days so make sure the post is genuine and only drop your link in the comments or in the post if it seems natural. If people are interested they’ll ask for the link. Another great place to post is r/entrepreuerridealong and r/business_ideas. These subreddits expect people to share their ideas and you’ll likely make some sales straight off the bat. I also suggest posting in some Facebook groups (related to your idea) as well just for good measure. Assess the results If people are paying you for early access you can assume that it’s worth building your idea. The beauty of posting your idea on Reddit or in Facebook groups is you’ll quickly learn why people love/hate your idea. This can help you decide how to tweak the idea or if you should drop it and move on to the next one. How we got our first 100 customers (for free) By validating Ticker Nerd using subreddits and Facebook groups this gave us our first paying customers. But we knew this wouldn’t be sustainable. We sat down and brainstormed every organic strategy we could use to get traction as quickly as possible. The winner: a Product Hunt launch. A successful Product Hunt launch isn’t easy. You need: Someone that has a solid reputation and audience to “hunt” your product (essentially an endorsement). An aged Product Hunt account - you can’t post any products if your account is less than a week old. To be following relevant Product Hunt members - since they get notified when you launch a new product if they’re following you. Relationships with other builders and makers on Product Hunt that also have a solid reputation and following. Although, if you can pull it off you can get your idea in front of tens of thousands of people actively looking for new products. Over the next few weeks, I worked with my co-founder on connecting with different founders, indie hackers and entrepreneurs mainly via Twitter. We explained to them our plans for the Product Hunt launch and managed to get a small army of people ready to upvote our product on launch day. We were both nervous on the day of the launch. We told ourselves to have zero expectations. The worst that could happen was no one signed up and we were in the same position as we’re in now. Luckily, within a couple of hours Ticker Nerd was on the homepage of Product Hunt and in the top 10. The results were instant. After 24 hours we had around 200 people enter their payment details to sign up for our free trial. These signups were equal to around $5,800 in monthly recurring revenue. \-- I hope this post was useful! Drop any questions you have below and I’ll do my best to respond :)

AI for Business- Sharing Strategies, Knowledge and Tools

Hi All, As a small business owner running a tech company that focuses on process automation, I understand the importance of staying up-to-date with the latest advancements in AI and other emerging technologies. I have found the amount of new tools and tech overwhelming to keep track of as of recent. I would like to start a group of entrepreneurs and tech professionals who share a common interest in the latest tools relating to AI, but also tech in general. My goal is to create an environment for members to discuss business strategies, share projects involving how they are introducing AI, new tools... I hope that by pooling knowledge everyone involved can benefit. To ensure the community remains focused and valuable I am thinking that It will be a requirement for all members to share a tool, project ideas, strategies... related to business on a bi-weekly basis. Potentially bi-weekly calls as well, but Ill figure that out based on the interest. We currently have about 15 members and looking to add maybe 10-15 more. If this sounds like something you'd be interested in post below or send me a DM. Add a brief description of what you are interested in / working on. Looking forward to connecting

Building and launching an AI-powered Product Strategy tool, or; a story of nights and weekends

Speaking to peers in the software development sphere I learned of one constant that we had all personally experienced throughout our careers: a bloated product development process that feels like work for the sake of work, centred around the highest-paid person's opinion instead of its customers. We didn't like how current tools assume AI will provide the perfect answer on the first run. Instead, we wanted a tool that allows for manual refining and editing AI suggestions, keeping all previous ideas in context. This way, we can develop a solution step by step, instead of trying to get it perfect on the first try. An approach more similar to how you'd typically approach product discovery as a human. AI is then used to help save time and reduce admin, instead of replace the expert So, we got together and asked over 100 Product Managers questions about it, brought all that feedback goodness together, and started building Squad. We think we've created something really cool and hope you think so too. The ELI5 on what Squad does: 1) Creates alignment that empowers bottom up software development whilst keeping executive in the loop 2) Increases confidence that what you're building is what people actually want - data driven by default 2) Speeds up the time from idea --> execution by ideating with you on an experimentation approach 3) Helps gives PMs time back to focus on strategy (currently stats show they spend 75% of their time on admin, 25% on strategy) The team hustled hard on this as a passion project while working day jobs, and today have launched on Product Hunt. Check it out and see if the mission resonates with you, we'd appreciate the love! https://www.producthunt.com/posts/squad-8b75e29c-d767-4a8f-a60a-fd162e141a72 &#x200B;

Secret behind Airbnb's Billion-Dollar Empire? Spamming Craigslist

Silicon Valley wants you to believe that their unicorn startups succeeded doing things legally. But that couldn't be far from truth. For starters, Airbnb used multiple Gmail accounts to spam Craigslist. "They posted unrealistically (fake) cheap rentals of beautiful apartments in places where normal rent should be 10x more. Once people replied, they auto-responded that the unit has been rented, but they should be looking for another unit on AirBnB." The Game of Blackhat is a cat-and-mouse game. You need a lot of guardrails to protect yourself from people using your Social Site by spamming their products. Craigslist is a team of 30 people. There's stuff AI can automate now with such a small team but back then, it wasn't possible. Airbnb used Craigslist as its playground to spam Craigslist visitors to grow their supply-side. In a 2-sided marketplace, growing both supply and demand is very important. And both must grow at the same time for the marketplace to work. A Blackhat Marketer created a new test site to get vacation rental owners to sign-up so that he can test his Airbnb theory. He grabbed their real email-addresses (not Craigslist anonymous addresses) via Craigslist by specifically targeting those who were advertising their vacation rentals on Craigslist. He skipped over the other categories that were directly related to AirBnB's business model because they didn't fit with the test site he built. Once he got 1000+ sign-ups, he then took it upon himself to post it to the advertising section on Craigslist. The email said this: I am emailing you because you have one of the nicest listings on Craigslist in Idaho and I want to recommend you feature it (for free) on one of the largest Idaho housing sites on the web, Airbnb. The site already has 3,000,000 pages views a month. Check it out here to list now: airbnb(dot)com Sarah Surpisingly, all emails were by ladies. He did the same in Week 2 and Week 3 to test if it wasn't a one-time thing. Surely, it wasn't a fluke. After posting 4 ads on Craigslist in 3 weeks, he received 5 identical emails from 2 ladies who were raving fans of AirBnB and spent their days emailing Craigslist advertisers. This is one of the greatest blackhat strategies used in the real world to build a billion-dollar marketplace by growing the supply-side with pure blackhat. These strategies are not mentioned in Press Interviews, Media, or any Founder stories but this is probably the most important piece of the puzzle. Without it, Airbnb probably wouldn't have survived. "Some very famous investors have alluded to the fact that they look for a dangerous streak in the entrepreneurs they invest in…and while those investors will never come out and tell you what they mean, this kind of thing is probably what they mean." It definitely violates CAN-SPAM act. Some comments from Hacker News: "CAN-SPAM, sending from a fake address (illegal headers). CA has a specific law that pre-empts CAN-SPAM that definitely makes this illegal if sent from CA." But I guess it worked in Airbnb's favour lol as they were never caught or fined until after. "It's commercial email 100%. Probably a fake sender name (illegal), against gmail ToS, against CL ToS and no unsubscribe link and no one even subscribed in the first place. 100% against CAN-SPAM." Thanks for reading. If you'd like to learn more blackhat tactics like this, check this site which is a growth hacking newsletter with real-world blackhat examples. PS: Actual emails & screenshots from the Airbnb x Craigslist spam can be found here.

AI Will Make You Extremely Rich or Kill Your Business in 2024

Preface: I'm a solo-founder in the AI space and previously worked as an ML scientist; the new advancements in AI that I'm seeing are going to impact everyone here. It doesn't matter if you're just starting out, or a bootstrapped brick and mortar founder, or even a VC backed hard tech founder. Last year was when the seeds were laid, and this is the year we'll see them bloom. There will be an onslaught of advancements that take place that are borderline inconceivable due to the nature of exponential progress. This will change every single vertical. I'm making this post because I think AI execution strategy will make or break businesses. Dramatically. Over $50B was put into AI startups in 2023 alone. This figure excludes the hundreds of billions poured into AI from enterprises. So, let's follow the money: &#x200B; 1) AI enterprise software. There's a lot to unpack here and this is what I’m currently working on. AI enterprise software will encompass everything from hyper personalized email outbound to AI cold calls to AI that A/B tests ads on synthetic data to vertical specific software. The impact of the former is relatively self explanatory, so I'll focus on the latter. To illustrate vertical specific AI software, I'll use a simple example in the legal space. Lawyers typically have to comb through thousands of pages of documents. Now, using an LLM + a VDB, an AI can instantly answer all of those questions while surfacing the source and highlighting the specific answer in the contract/document. There are dozens of AI startups for this use case alone. This saves lawyers an immense amount of time and allows them to move faster. Firms that adopt this have a fundamental advantage over law firms that don't adopt this. This was 2023 technology. I'm seeing vertical AI software getting built by my friends in areas from construction, to real estate, to even niche areas like chimney manufacturing. This will exist everywhere. Now, this can be extrapolated much further to be applicable to systems that can do reports and even browse the Internet. This brings me to my next point. &#x200B; 2) AI information aggregation and spread. My gut tells me that this will have a crescendo moment in the future with hardware advancements (Rabbit, Tab, etc.). You won't have to google things because it will be surfaced to you. It's predictive in nature. The people who can get information the fastest will grow their business the fastest. This part is semi-speculative, but due to the nature of LLMs being so expensive to train, I have a strong feeling that large institutions will have access to the \fastest\ and \best\ models that can do this quicker than you and I can. This is why it's important to stay on top. &#x200B; 3) AI content generation This is relevant to running advertisements and any digital marketing aspect of your business. If you can rapidly make content faster than your competitors to put in social media, you will outpace your competitors rapidly. I think most folks are familiar with MidJourney, Stable diffusion, etc. but don't know how to use it. You can generate consistent models for a clothing brand or generate images of a product that you would normally need to hire a professional photographer to take. There's also elevenlabs which is relatively easy to use and can be used to make an MP3 clip as a narration for an ad; this is something I've already done. I'm also still shocked by how many people are unfamiliar with tools like Pika which can do video generation. You could imagine companies having fleets of digital influencers that they control or conjuring up the perfect ad for a specific demographic using a combination of all of the aforementioned tools. &#x200B; In summary, if you feel like I'm being hyperbolic or propagating science fiction fantasies, you're likely already behind. I truly recommend that everyone stays up to date on these advancements as much as possible. If your competitor comes across an AI tool that can increase their ROAS by 5x they can crush you. If your competitor uses a tool that increases the rate at which they receive and aggregate information by 200% (modest estimate) they will crush you. If your competitors have a tool that can reduce their employee size, then they will use it. They'll fire their employees to cut costs and reinvest the money back into their business. It will compound to the point where you're outpaced, and this isn't a level of innovation we've seen since the birth of the industrial revolution. Your customers can get stolen overnight, or you can steal your competition’s customers overnight. TL;DR: This is an opportunity for entrepreneurs to scale faster than they could have possibly imagined, but this also comes with the potential for your company to be obliterated. We've never seen advancements that can have this drastic of an impact this quickly. Adoption will happen fast, and first movers will have a disproportionate and compounding advantage. Watch guides, meet with startups, follow the news, and get rich.

Beginner to the 1st sale: my journey building an AI for social media marketers

Hey everyone! Here’s my journey building an AI for social media marketers all the way up until my first pre-launch sale, hope that could help some of you: My background: studied maths at uni before dropping out to have some startup experiences. Always been drawn to building new things so I reckoned I would have some proper SaaS experiences and see how VC-funded startups are doing it before launching my own.  I’ve always leaned towards taking more risks in my life so leaving my FT job to launch my company wasn’t a big deal for me (+ I’m 22 so still have time to fail over and over). When I left my job, I started reading a lot about UI/UX, no-code tools, marketing, sales and every tool a worthwhile entrepreneur needs to learn about. Given the complexity of the project I set out to achieve, I asked a more technical friend to join as a cofounder and that's when AirMedia was born. We now use bubble for landing page as I had to learn it and custom-code stack for our platform.  Here's our goal: streamlining social media marketing using AI. I see this technology has only being at the premises of what it will be able to achieve in the near-future. We want to make the experience dynamic i.e. all happens from a discussion and you see the posts being analysed from there as well as the creation process - all from within the chat. Fast forward a few weeks ago, we finished developing the first version of our tool that early users describe as a "neat piece of tech" - just this comment alone can keep me going for months :) Being bootstrapped until now, I decided to sell lifetime deals for the users in the waitlist that want to get the tool in priority as well as secure their spot for life. We've had the first sale the first day we made that public ! Now what you all are looking for: How ?  Here was my process starting to market the platform: I need a high-converting landing page so I reckoned which companies out there have the most data and knows what convert and what doesn’t: Unbounce. Took their landing page and adapted it to my value proposition and my ICP.  The ICP has been defined from day 1 and although I’m no one to provide any advice, I strongly believe the ICP has to be defined from day 1 (even before deciding the name of the company). It helps a lot when the customer is you and you’ve had this work experience that helps you identify the problems your users encounter. Started activating the network, posting on Instagram and LinkedIn about what we've built (I've worked in many SaaS start-ups in the past so I have to admit that's a bit of a cheat code). Cold outreach from Sales NAV to our ICP, been growing the waitlist in parallel of building the tool for months now so email marketings with drip sequences and sharing dev updates to build the trust along the way (after all we're making that tool for our users - they should be the first aware about what we're building). I also came across some Whatsapp groups with an awesome community that welcomed our platform with excitement.) The landing page funnel is the following: Landing page -> register waitlist -> upsell page -> confirmation. I've made several landing pages e.g. for marketing agencies, for real estate agents, for marketing director in several different industries. The goal now is just testing out the profiles and who does it resonate the most with. Another growth hack that got us 40+ people on the waitlist: I identified some Instagram posts from competitors where their CTA was "comment AI" and I'll send you our tool and they got over 2k people commenting. Needless to say, I messaged every single user to check out our tool and see if it could help them. (Now that i think about it, the 2% conversion rate there is not great - especially considering the manual labour and the time put behind it). We’ve now got over 400 people on the waitlist so I guess we’re doing something right but we’ll keep pushing as the goal is to sell these lifetime deals to have a strong community to get started. (Also prevents us from going to VCs and I can keep my time focussing exclusively on our users - I’m not into boardroom politics, just wanna build something useful for marketers). Now I’m still in the process of testing out different marketing strategies while developing and refining our platform to make it next level on launch day. Amongst those:  LinkedIn Sales Nav outreach (first sale came from there) Product Hunt Highly personalised cold emails (there I’m thinking of doing 20 emails a day with a personalised landing page to each of those highly relevant marketers). Never seen that and I think this could impress prospects but not sure it’s worth it time / conversion wise. Make content to could go viral (at least 75 videos) that I’m posting throughout several social media accounts such as airmedia\\, airmedia\reels, airmedia\ai (you get the hack) always redirecting to the main page both in the profile description and tagging the main account. I have no idea how this will work so will certainly update some of you that would like to know the results. Will do the same across Facebook, TikTok, Youtube Shorts etc… I’m just looking for a high potential of virality there. This strategy is mainly used to grow personal brands but never seen it applied to companies. Good old cold calling Reddit (wanna keep it transparent ;) ) I’m alone to execute all these strategies + working in parallel to refine the product upon user’s feedback I’m not sure I can do more than that for now. Let me know if you have any feedback/ideas/ tasks I could implement.  I could also make another post about the proper product building process as this post was about the marketing. No I certainly haven’t accomplished anything that puts me in a position to provide advices but I reckon I’m on my way to learn more and more. Would be glad if this post could help some of you.  And of course as one of these marketing channels is Reddit I’ll post the link below for the entrepreneurs that want to streamline their social media or support us. Hope I was able to provide enough value in this post for you to consider :) https://airmedia.uk/

I need 10 agencies doing $1K+ MRR looking for new clients

For the past year, we've been building Surfkey. It started as a Reddit keyword alert tool focused on helping SaaS get new users from Reddit by jumping into relevant conversations, providing value, and plugging their product when it makes sense. We spent the last 3 months implementing AI to find relevant conversations without noise and once again made the beginner mistake of building for way too long. After the release, it's clear it's hard for product founders to attribute new customers to being part of Reddit conversations. But an interesting pattern appeared - agencies, freelancers, and productized services started subscribing and sending us their success stories. They got new leads from Reddit ranging from $2-$10k deals. I realized it's very hard for a product owner to see the impact of commenting on Reddit, but it's easy to connect your new lead to the conversation you were part of yesterday. And there are so many people on Reddit asking for help, looking for a new hire or just being stuck. But at the right stage of becoming a client. We are mid-pivot looking for 10 agencies that will be happy to test-drive Surfkey with us. It's fairly simple, it serves you all the posts where it makes sense to jump in, share your knowledge and then offer your service.Happy to answer any Q's!

5 Habits to go from Founder to CEO

Over the years, I've gathered some knowledge about transitioning from a startup founder to a CEO. I started my company 7 years ago. We are now not super big (65 people), but we have learned a lot. We raised $19M in total and we are now profitable. The transition from Founder to CEO was crucial. Your startup begins to mature and scale and you need to scale with it. It's often a challenging phase, but I've managed to summarize it into five habbits. Say no to important things every day Being able to say "no" to important tasks every day is an essential practice for a growing leader. It's a reality that as the magnitude of your company or ideas expands, so does the influx of good ideas and opportunities. However, to transform from a mere hustler to a true leader, you have to become selective. This means learning to refuse good ideas, which is crucial if you want to consistently execute the outstanding ones. The concept that "Startups don't starve, they drown" resonates deeply because it underlines how challenging it can be to reject opportunities. A key strategy to develop this skill is time-constraining your to-do list. Here's how you can do it: Weekly: Formulate a weekly to-do list, including only those tasks that you're sure to complete within the week. Leave some buffer room for unexpected issues. If there's any doubt about whether you'll have time for a certain task, it should not feature on your weekly list. I use Todoist and Notion for task management. Daily: Apply the same rule while creating your daily to-do list. Only include tasks that you're confident about accomplishing that day. If a task seems too big to fit into one day, break it down into manageable chunks. Journaling Journaling is a powerful strategy that can help an individual transition from a reactive approach to a proactive one. As founders, we often find ourselves caught up in a cycle of endless tasks, akin to chopping trees in a dense forest. However, to ensure sustainable growth, it is crucial to develop an ability to "zoom out", or to view the bigger picture. I use The Morning Pages method, from Julia Cameron. It consists of writing each morning about anything that comes to mind. The act of writing effectively combines linear, focused thinking with the benefits of a thoughtful conversation. If you just want to journal, you can use Day One app (The free version will be enough). If you want to go a bit deeper, you can try a coaching app. I use Wave.ai and I also hired it for the managers in the company because it combines both journaling with habit building. &#x200B; Building Robust Systems and Processes (I know, it is boring and founders hate this) As a founder, you often need to wear multiple hats and juggle various roles. But as a CEO, it's vital to establish strong systems and processes that enable the business to function smoothly, even without your direct involvement. This includes: Implementing project management systems. Establishing clear lines of communication and accountability. Designing efficient workflows and procedures. To many founders, developing these systems might seem monotonous or even tedious. After all, the allure of envisioning the next big idea often proves more exciting. I experienced the same predicament. In response, I brought onboard a competent COO who excelled in systematizing processes. This strategy allowed me to kickstart initiatives and explore them in a flexible, less structured manner. Once an idea showed signs of gaining traction, my COO stepped in to streamline it, crafting a process that turned the fledgling idea into a consistent business operation. &#x200B; Meditating Meditation is about reprogramming unconscious mental processes by repeatedly performing fundamental tasks with a distinct intention. This practice can be even more crucial to leadership than acquiring a business school education. Because meditation provides the most direct route to understanding your mind's workings and thus, forms the most effective basis for transforming it. To transition from a founder to a CEO, a significant shift in your mindset is required. This shift involves moving from a hustle mentality to precision, from acting as a superhero solving problems to consciously stepping back, thereby providing room for your team members to discover their own superpowers. It's about shifting your success indicators - from individual achievements to the triumphs of your team. This transformation might not feel comfortable initially, and your instincts, shaped by your scrappy founder phase, might resist this change. However, with consistent practice, you can align your instincts with the stage of your company, promoting more effective leadership. This is where the value of meditation truly shines. It allows you to identify your distinct thought patterns in real time and, over time, modify them. I use Headspace a lot, and I also encourage the employees to use it. The company pays the subscription as a perk. &#x200B; Balancing the Macro and the Micro As the CEO, your primary focus should be on the big picture – your company's vision and strategy. However, you also need to keep an eye on the details, as these can make or break your execution. It's all about balance: Delegate the details but stay informed. Prioritize strategic planning but be ready to dive into the trenches when needed. Keep your eye on your long-term vision but adapt to short-term realities. The transition from founder to CEO isn't about giving up what made you successful initially but augmenting it with additional skills, perspectives, and practices. It's a personal and professional evolution that can lead to greater success for both you and your business. Every great CEO was once a founder. It's just about taking the next step. I’d love to hear your experiences or any tips you might have for this transition. In which step of your journey are you right now? Do you have employees already? What are your main challenges right now?

How To Learn About AI Agents (A Road Map From Someone Who's Done It)

If you are a newb to AI Agents, welcome, I love newbies and this fledgling industry needs you! You've hear all about AI Agents and you want some of that action right?  You might even feel like this is a watershed moment in tech, remember how it felt when the internet became 'a thing'?  When apps were all the rage?  You missed that boat right?   Well you may have missed that boat, but I can promise you one thing..... THIS BOAT IS BIGGER !  So if you are reading this you are getting in just at the right time.  Let me answer some quick questions before we go much further: Q: Am I too late already to learn about AI agents? A: Heck no, you are literally getting in at the beginning, call yourself and 'early adopter' and pin a badge on your chest! Q: Don't I need a degree or a college education to learn this stuff?  I can only just about work out how my smart TV works! A: NO you do not.  Of course if you have a degree in a computer science area then it does help because you have covered all of the fundamentals in depth... However 100000% you do not need a degree or college education to learn AI Agents.  Q: Where the heck do I even start though?  Its like sooooooo confusing A: You start right here my friend, and yeh I know its confusing, but chill, im going to try and guide you as best i can. Q: Wait i can't code, I can barely write my name, can I still do this? A: The simple answer is YES you can. However it is great to learn some basics of python.  I say his because there are some fabulous nocode tools like n8n that allow you to build agents without having to learn how to code...... Having said that, at the very least understanding the basics is highly preferable. That being said, if you can't be bothered or are totally freaked about by looking at some code, the simple answer is YES YOU CAN DO THIS. Q: I got like no money, can I still learn? A: YES 100% absolutely.  There are free options to learn about AI agents and there are paid options to fast track you.  But defiantly you do not need to spend crap loads of cash on learning this.  So who am I anyway? (lets get some context)  I am an AI Engineer and I own and run my own AI Consultancy business where I design, build and deploy AI agents and AI automations.  I do also run a small academy where I teach this stuff, but I am not self promoting or posting links in this post because im not spamming this group.  If you want links send me a DM or something and I can forward them to you.  Alright so on to the good stuff, you're a newb, you've already read a 100 posts and are now totally confused and every day you consume about 26 hours of youtube videos on AI agents.....I get you, we've all been there.  So here is my 'Worth Its Weight In Gold' road map on what to do: \[1\]  First of all you need learn some fundamental concepts.  Whilst you can defiantly jump right in start building, I strongly recommend you learn some of the basics.  Like HOW to LLMs work, what is a system prompt, what is long term memory, what is Python, who the heck is this guy named Json that everyone goes on about?  Google is your old friend who used to know everything, but you've also got your new buddy who can help you if you want to learn for FREE.  Chat GPT is an awesome resource to create your own mini learning courses to understand the basics. Start with a prompt such as: "I want to learn about AI agents but this dude on reddit said I need to know the fundamentals to this ai tech, write for me a short course on Json so I can learn all about it. Im a beginner so keep the content easy for me to understand. I want to also learn some code so give me code samples and explain it like a 10 year old" If you want some actual structured course material on the fundamentals, like what the Terminal is and how to use it, and how LLMs work, just hit me, Im not going to spam this post with a hundred links. \[2\] Alright so let's assume you got some of the fundamentals down.  Now what? Well now you really have 2 options.  You either start to pick up some proper learning content (short courses) to deep dive further and really learn about agents or you can skip that sh\*t and start building!  Honestly my advice is to seek out some short courses on agents, Hugging Face have an awesome free course on agents and DeepLearningAI also have numerous free courses. Both are really excellent places to start.  If you want a proper list of these with links, let me know.  If you want to jump in because you already know it all, then learn the n8n platform!   And no im not a share holder and n8n are not paying me to say this.  I can code, im an AI Engineer and I use n8n sometimes.   N8N is a nocode platform that gives you a drag and drop interface to build automations and agents.  Its very versatile and you can self host it.  Its also reasonably easy to actually deploy a workflow in the cloud so it can be used by an actual paying customer.  Please understand that i literally get hate mail from devs and experienced AI enthusiasts for recommending no code platforms like n8n.  So im risking my mental wellbeing for you!!!    \[3\] Keep building!   ((WTF THAT'S IT?????))  Yep. the more you build the more you will learn.  Learn by doing my young Jedi learner.  I would call myself pretty experienced in building AI Agents, and I only know a tiny proportion of this tech.  But I learn but building projects and writing about AI Agents.  The more you build the more you will learn.  There are more intermediate courses you can take at this point as well if you really want to deep dive (I was forced to - send help) and I would recommend you do if you like short courses because if you want to do well then you do need to understand not just the underlying tech but also more advanced concepts like Vector Databases and how to implement long term memory.  Where to next? Well if you want to get some recommended links just DM me or leave a comment and I will DM you, as i said im not writing this with the intention of spamming the crap out of the group. So its up to you.  Im also happy to chew the fat if you wanna chat, so hit me up.  I can't always reply immediately because im in a weird time zone, but I promise I will reply if you have any questions. THE LAST WORD (Warning - Im going to motivate the crap out of you now) Please listen to me:  YOU CAN DO THIS.  I don't care what background you have, what education you have, what language you speak or what country you are from..... I believe in you and anyway can do this.  All you need is determination, some motivation to want to learn and a computer (last one is essential really, the other 2 are optional!) But seriously you can do it and its totally worth it.  You are getting in right at the beginning of the gold rush, and yeh I believe that.   AI Agents are going to be HUGE. I believe this will be the new internet gold rush.

Recently hit 6,600,000 monthly organic traffic for a B2C SaaS website. Here's the 40 tips that helped me make that happen.

Hey guys! So as title says, we recently hit 6,600,000 monthly organic traffic / month for a B2C SaaS website (screenshot. Can't give name publicly, but can show testimonial to a mod). Here's 40 tips that "helped" me make this happen. If you get some value of the post, I write an SEO tip every other day on /r/seogrowth. There's around 10 more tips already up there other than the ones I mention here. If you want to give back for all my walls of text, I'd appreciate a sub <3 Also, there are a bunch of free stuff I mention in the article: content outline, writer guidelines, SEO checklist, and other stuff. Here's the Google Doc with all that! Tip #1. Take SEO With a Grain of Salt A lot of the SEO advice and best practices on the internet are based on 2 things: Personal experiences and case studies of companies that managed to make SEO work for them. Google or John Mueller (Google’s Senior Webmaster Trends Analyst). And, unfortunately, neither of these sources are always accurate. Personal SEO accounts are simply about what worked for specific companies. Sometimes, what worked for others, won’t work for you. For example, you might find a company that managed to rank with zero link-building because their website already had a very strong backlink profile. If you’re starting with a fresh website, chances are, you won’t be able to get the same results. At the same time, information from Google or John Mueller is also not 100% accurate. For example, they’ve said that guest posting is against Google’s guidelines and doesn’t work… But practically, guest posting is a very effective link-building strategy. So the takeaway is this: Take all information you read about SEO with a grain of salt. Analyze the information yourself, and make your conclusions. SEO Tip #2. SEO Takes Time You’ve already heard this one before, but considering how many people keep asking, thought I'd include this anyway. On average, it’s going to take you 6 months to 2 years to get SEO results, depending on the following factors: Your backlink profile. The more quality backlinks you have (or build), the faster you’ll rank. Age of your website. If your website is older (or you purchased an aged website), you can expect your content to rank faster. Amount of content published. The more quality content you publish on your website, the more “authoritative” it is in the eyes of Google, and thus more likely to rank faster. SEO work done on the website. If a lot of your pages are already ranking on Google (page 2-3), it’s easier to get them to page #1 than if you just published the content piece. Local VS global SEO. Ranking locally is (sometimes) easier and faster than ranking globally. That said, some marketing agencies can use “SEO takes time” as an excuse for not driving results. Well, fortunately, there is a way to track SEO results from month #2 - #3 of work. Simply check if your new content pieces/pages are getting more and more impressions on Google Search Console month-to-month. While your content won’t be driving traffic for a while after being published, they’ll still have a growing number of impressions from month #2 or #3 since publication. SEO Tip #3. SEO Might Not Be The Best Channel For You In theory, SEO sounds like the best marketing channel ever. You manage to rank on Google and your marketing seemingly goes on auto-pilot - you’re driving new leads every day from existing content without having to lift a finger… And yet, SEO is not for everyone. Avoid SEO as a marketing channel if: You’re just getting started with your business and need to start driving revenue tomorrow (and not in 1-2 years). If this is you, try Google ads, Facebook ads, or organic marketing. Your target audience is pretty small. If you’re selling enterprise B2B software and have around 2,000 prospects in total worldwide, then it’s simply easier to directly reach out to these prospects. Your product type is brand-new. If customers don’t know your product exists, they probably won’t be Googling it. SEO Tip #4. Traffic Can Be a Vanity Metric I've seen hundreds of websites that drive 6-7 digits of traffic but generate only 200-300 USD per month from those numbers. “What’s the deal?” You might be thinking. “How can you fail to monetize that much traffic?” Well, that brings us to today’s tip: traffic can be a vanity metric. See, not all traffic is created equal. Ranking for “hormone balance supplement” is a lot more valuable than ranking for “Madagascar character names.” The person Googling the first keyword is an adult ready to buy your product. Someone Googling the latter, on the other hand, is a child with zero purchasing power. So, when deciding on which keywords to pursue, always keep in mind the buyer intent behind and don’t go after rankings or traffic just because 6-digit traffic numbers look good. SEO Tip #5. Push Content Fast Whenever you publish a piece of content, you can expect it to rank within 6 months to a year (potentially less if you’re an authority in your niche). So, the faster you publish your content, the faster they’re going to age, and, as such, the faster they’ll rank on Google. On average, I recommend you publish a minimum of 10,000 words of content per month and 20,000 to 30,000 optimally. If you’re not doing link-building for your website, then I’d recommend pushing for even more content. Sometimes, content velocity can compensate for the lack of backlinks. SEO Tip #6. Use Backlink Data to Prioritize Content You might be tempted to go for that juicy, 6-digit traffic cornerstone keyword right from the get-go... But I'd recommend doing the opposite. More often than not, to rank for more competitive, cornerstone keywords, you’ll need to have a ton of supporting content, high-quality backlinks, website authority, and so on. Instead, it’s a lot more reasonable to first focus on the less competitive keywords and then, once you’ve covered those, move on to the rest. Now, as for how to check keyword competitiveness, here are 2 options: Use Mozbar to see the number of backlinks for top-ranking pages, as well as their Domain Authority (DA). If all the pages ranking on page #1 have <5 backlinks and DA of 20 - 40, it’s a good opportunity. Use SEMrush or Ahrefs to sort your keywords by difficulty, and focus on the less difficult keywords first. Now, that said, keep in mind that both of these metrics are third-party, and hence not always accurate. SEO Tip #7. Always Start With Competitive Analysis When doing keyword research, the easiest way to get started is via competitive analysis. Chances are, whatever niche you’re in, there’s a competitor that is doing great with SEO. So, instead of having to do all the work from scratch, run their website through SEMrush or Ahrefs and steal their keyword ideas. But don’t just stop there - once you’ve borrowed keyword ideas from all your competitors, run the seed keywords through a keyword research tool such as UberSuggest or SEMrush Keyword Magic Tool. This should give you dozens of new ideas that your competitors might’ve missed. Finally, don’t just stop at borrowing your competitor’s keyword ideas. You can also borrow some inspiration on: The types of graphics and images you can create to supplement your blog content. The tone and style you can use in your articles. The type of information you can include in specific content pieces. SEO Tip #8. Source a LOT of Writers Content writing is one of those professions that has a very low barrier to entry. Anyone can take a writing course, claim to be a writer, and create an UpWork account… This is why 99% of the writers you’ll have to apply for your gigs are going to be, well, horrible. As such, if you want to produce a lot of content on the reg, you’ll need to source a LOT of writers. Let’s do the math: If, by posting a job ad, you source 100 writers, you’ll see that only 5 of them are a good fit. Out of the 5 writers, 1 has a very high rate, so they drop out. Another doesn’t reply back to your communication, which leaves you with 3 writers. You get the 3 writers to do a trial task, and only one turns out to be a good fit for your team. Now, since the writer is freelance, the best they can do is 4 articles per month for a total of 5,000-words (which, for most niches, ain’t all that much). So, what we’re getting at here is, to hire quality writers, you should source a LOT of them. SEO Tip #9. Create a Process for Filtering Writers If you follow the previous tip, you'll end up with a huge database of hundreds of writers. This creates a whole new problem: You now have a database of 500+ writers waiting for you to sift through them and decide which ones are worth the hire. It would take you 2-3 days of intense work to go through all these writers and vet them yourself. Let’s be real - you don’t have time for that. Here’s what you can do instead: When sourcing writers, always get them to fill in a Google form (instead of DMing or emailing you). In this form, make sure to ask for 3 relevant written samples, a link to the writer’s portfolio page, and the writer’s rate per word. Create a SOP for evaluating writers. The criteria for evaluation should be: Level of English. Does the writer’s sample have any English mistakes? If so, they’re not a good fit. Quality of Samples. Are the samples long-form and engaging content or are they boring 500-word copy-pastes? Technical Knowledge. Has the writer written about a hard-to-explain topic before? Anyone can write about simple topics like traveling—you want to look for someone who knows how to research a new topic and explain it in a simple and easy-to-read way. If someone’s written about how to create a perfect cover letter, they can probably write about traveling, but the opposite isn’t true. Get your VA to evaluate the writer’s samples as per the criteria above and short-list writers that seem competent. If you sourced 500 writers, the end result of this process should be around 50 writers. You or your editor goes through the short-list of 50 writers and invites 5-10 for a (paid) trial task. The trial task is very important - you’ll sometimes find that the samples provided by the writer don’t match their writing level. SEO Tip #10. Use the Right Websites to Find Writers Not sure where to source your writers? Here are some ideas: ProBlogger \- Our #1 choice - a lot of quality writers frequent this website. LinkedIn \- You can headhunt content writers in specific locations. Upwork \- If you post a content gig, most writers are going to be awful. Instead, I recommend headhunting top writers instead. WeWorkRemotely \- Good if you’re looking to make a full-time remote hire. Facebook \- There are a ton of quality Facebook groups for writers. Some of our faves are Cult of Copy Job Board and Content Marketing Lounge. SEO Tip #11. Always Use Content Outlines When giving tasks to your writing team, you need to be very specific about the instructions you give them. Don’t just provide a keyword and tell them to “knock themselves out.” The writer isn’t a SEO expert; chances are, they’re going to mess it up big-time and talk about topics that aren’t related to the keyword you’re targeting. Instead, when giving tasks to writers, do it through content outlines. A content outline, in a nutshell, is a skeleton of the article they’re supposed to write. It includes information on: Target word count (aim for the same or 50% more the word count than that of the competition). Article title. Article structure (which sections should be mentioned and in what order). Related topics of keywords that need to be mentioned in the article. Content outline example in the URL in the post intro. SEO Tip #12. Focus on One Niche at a Time I used to work with this one client that had a SaaS consisting of a mixture of CRM, Accounting Software, and HRS. I had to pick whether we were going to focus on topics for one of these 3 niches or focus on all of them at the same time. I decided to do the former. Here’s why: When evaluating what to rank, Google considers the authority of your website. If you have 60 articles about accounting (most of which link to each other), you’re probably an authority in the niche and are more likely to get good rankings. If you have 20 sales, 20 HR, and 20 accounting articles, though, none of these categories are going to rank as well. It always makes more sense to first focus on a single niche (the one that generates the best ROI for your business), and then move on to the rest. This also makes it easier to hire writers - you hire writers specialized in accounting, instead of having to find writers who can pull off 3 unrelated topics. SEO Tip #13. Just Hire a VA Already It’s 2021 already guys—unless you have a virtual assistant, you’re missing out big-time. Since a lot of SEO tasks are very time-consuming, it really helps to have a VA around to take over. As long as you have solid SOPs in place, you can hire a virtual assistant, train them, and use them to free up your time. Some SEO tasks virtual assistants can help with are: Internal linking. Going through all your blog content and ensuring that they link to each other. Backlink prospecting. Going through hundreds of websites daily to find link opportunities. Uploading content on WordPress and ensuring that the content is optimized well for on-page SEO. SEO Tip #14. Use WordPress (And Make Your Life Easier) Not sure which CMS platform to use? 99% of the time, you’re better off with WordPress. It has a TON of plugins that will make your life easier. Want a drag & drop builder? Use Elementor. It’s cheap, efficient, extremely easy to learn, and comes jam-packed with different plugins and features. Wix, SiteGround, and similar drag & drops are pure meh. SEO Tip #15. Use These Nifty WordPress Plugins There are a lot of really cool WordPress plugins that can make your (SEO) life so much easier. Some of our favorites include: RankMath. A more slick alternative to YoastSEO. Useful for on-page SEO. Smush. App that helps you losslessly compress all images on your website, as well as enables lazy loading. WP Rocket. This plugin helps speed up your website pretty significantly. Elementor. Not a techie? This drag & drop plugin makes it significantly easier to manage your website. WP Forms. Very simple form builder. Akismet Spam Protection. Probably the most popular anti-spam WP plugin. Mammoth Docx. A plugin that uploads your content from a Google doc directly to WordPress. SEO Tip #16. No, Voice Search Is Still Not Relevant Voice search is not and will not be relevant (no matter what sensationalist articles might say). Sure, it does have its application (“Alexa, order me toilet paper please”), but it’s pretty niche and not relevant to most SEOs. After all, you wouldn’t use voice search for bigger purchases (“Alexa, order me a new laptop please”) or informational queries (“Alexa, teach me how to do accounting, thanks”). SEO Tip #17. SEO Is Obviously Not Dead I see these articles every year - “SEO is dead because I failed to make it work.” SEO is not dead and as long as there are people looking up for information/things online, it never will be. And no, SEO is not just for large corporations with huge budgets, either. Some niches are hypercompetitive and require a huge link-building budget (CBD, fitness, VPN, etc.), but they’re more of an exception instead of the rule. SEO Tip #18. Doing Local SEO? Focus on Service Pages If you’re doing local SEO, you’re better off focusing on local service pages than blog content. E.g. if you’re an accounting firm based in Boston, you can make a landing page about /accounting-firm-boston/, /tax-accounting-boston/, /cpa-boston/, and so on. Or alternatively, if you’re a personal injury law firm, you’d want to create pages like /car-accident-law-firm/, /truck-accident-law-firm/, /wrongful-death-law-firm/, and the like. Thing is, you don’t really need to rank on global search terms—you just won’t get leads from there. Even if you ranked on the term “financial accounting,” it wouldn’t really matter for your bottom line that much. SEO Tip #19. Engage With the SEO Community The SEO community is (for the most part) composed of extremely helpful and friendly people. There are a lot of online communities (including this sub) where you can ask for help, tips, case studies, and so on. Some of our faves are: This sub :) SEO Signals Lab (FB Group) Fat Graph Content Ops (FB Group) Proper SEO Group (FB Group) BigSEO Subreddit SEO Tip #20. Test Keywords Before Pursuing Them You can use Google ads to test how profitable any given keyword is before you start trying to rank for it. The process here is: Create a Google Ads account. Pick a keyword you want to test. Create a landing page that corresponds to the search intent behind the keyword. Allocate an appropriate budget. E.g. if you assume a conversion rate of 2%, you’d want to buy 100+ clicks. If the CPC is 2 USD, then the right budget would be 200 USD plus. Run the ads! If you don’t have the budget for this, you can still use the average CPC for the keyword to estimate how well it’s going to convert. If someone is willing to bid 10 USD to rank for a certain keyword, it means that the keyword is most probably generating pretty good revenue/conversions. SEO Tip #21. Test & Improve SEO Headlines Sometimes, you’ll see that you’re ranking in the top 3 positions for your search query, but you’re still not driving that much traffic. “What’s the deal?” you might be asking. Chances are, your headline is not clickable enough. Every 3-4 months, go through your Google Search Console and check for articles that are ranking well but not driving enough traffic. Then, create a Google sheet and include the following data: Targeted keyword Page link CTR (for the last 28 days) Date when you implemented the new title Old title New title New CTR (for the month after the CTR change was implemented) From then on, implement the new headline and track changes in the CTR. If you don’t reach your desired result, you can always test another headline. SEO Tip #22. Longer Content Isn’t Always Better Content You’ve probably heard that long-form content is where it’s at in 2021. Well, this isn’t always the case. Rather, this mostly depends on the keyword you’re targeting. If, for example, you’re targeting the keyword “how to tie a tie,” you don’t need a long-ass 5,000-word mega-guide. In such a case, the reader is looking for something that can be explained in 200-300 words and if your article fails to do this, the reader will bounce off and open a different page. On the other hand, if you’re targeting the keyword “how to write a CV,” you’ll need around 4,000 to 5,000 words to adequately explain the topic and, chances are, you won’t rank with less. SEO Tip #23. SEO is Not All About Written Content More often than not, when people talk about SEO they talk about written blog content creation. It’s very important not to forget, though, that blog content is not end-all-be-all for SEO. Certain keywords do significantly better with video content. For example, if the keyword is “how to do a deadlift,” video content is going to perform significantly better than blog content. Or, if the keyword is “CV template,” you’ll see that a big chunk of the rankings are images of the templates. So, the lesson here is, don’t laser-focus on written content—keep other content mediums in mind, too. SEO Tip #24. Write For Your Audience It’s very important that your content resonates well with your target audience. If, for example, you’re covering the keyword “skateboard tricks,” you can be very casual with your language. Heck, it’s even encouraged! Your readers are Googling the keyword in their free time and are most likely teens or in their early 20s. Meaning, you can use informal language, include pop culture references, and avoid complicated language. Now, on the other hand, if you’re writing about high-level investment advice, your audience probably consists of 40-something suit-and-ties. If you include Rick & Morty references in your article, you'll most likely lose credibility and the Googler, who will go to another website. Some of our best tips on writing for your audience include: Define your audience. Who’s the person you’re writing for? Are they reading the content at work or in their free time? Keep your reader’s level of knowledge in mind. If you’re covering an accounting 101 topic, you want to cover the topic’s basics, as the reader is probably a student. If you’re writing about high-level finance, though, you don’t have to teach the reader what a balance sheet is. More often than not, avoid complicated language. The best practice is to write on a 6th-grade level, as it’s understandable for anyone. Plus, no one wants to read Shakespeare when Googling info online (unless they’re looking for Shakespeare's work, of course). SEO Tip #25. Create Compelling Headlines Want to drive clicks to your articles? You’ll need compelling headlines. Compare the following headline: 101 Productivity Tips \[To Get Things Done in 2021\] With this one: Productivity Tips Guide Which one would you click? Data says it’s the first! To create clickable headlines, I recommend you include the following elements: Keyword. This one’s non-negotiable - you need to include the target keyword in the headline. Numbers. If Buzzfeed taught us anything, it’s that people like to click articles with numbers in their titles. Results. If I read your article, what’s going to be the end result? E.g. “X Resume tips (to land the job)”.* Year (If Relevant). Adding a year to your title shows that the article is recent (which is relevant for some specific topics). E.g. If the keyword is “Marketing Trends,” I want to know marketing trends in 2021, not in 2001. So, adding a year in the title makes the headline more clickable. SEO Tip #26. Make Your Content Visual How good your content looks matters, especially if you're in a competitive niche. Here are some tips on how to make your content as visual as possible: Aim for 2-4 sentences per paragraph. Avoid huge blocks of text. Apply a 60-65% content width to your blog pages. Pick a good-looking font. I’d recommend Montserrat, PT Sans, and Roboto. Alternatively, you can also check out your favorite blogs, see which fonts they’re using, and do the same. Use a reasonable font size. Most top blogs use font sizes ranging from 16 pt to 22 pt. Add images when possible. Avoid stock photos, though. No one wants to see random “office people smiling” scattered around your blog posts. Use content boxes to help convey information better. Content boxes example in the URL in the intro of the post. SEO Tip #27. Ditch the Skyscraper Technique Already Brian Dean’s skyscraper technique is awesome and all, but the following bit really got old: “Hey \[name\], I saw you wrote an article. I, too, wrote an article. Please link to you?” The theory here is, if your content is good, the person will be compelled to link to it. In practice, though, the person really, really doesn’t care. At the end of the day, there’s no real incentive for the person to link to your content. They have to take time out of their day to head over to their website, log in to WordPress, find the article you mentioned, and add a link... Just because some stranger on the internet asked them to. Here’s something that works much better: Instead of fake compliments, be very straightforward about what you can offer them in exchange for that link. Some things you can offer are: A free version of your SaaS. Free product delivered to their doorstep. Backlink exchange. A free backlink from your other website. Sharing their content to your social media following. Money. SEO Tip #28. Get the URL Slug Right for Seasonal Content If you want to rank on a seasonal keyword, there are 2 ways to do this. If you want your article to be evergreen (i.e. you update it every year with new information), then your URL should not contain the year. E.g. your URL would be /saas-trends/, and you simply update the article’s contents+headline each year to keep it timely. If you’re planning on publishing a new trends report annually, though, then you can add a year to the URL. E.g. /saas-trends-2020/ instead of /saas-trends/. SEO Tip #29. AI Content Tools Are a Mixed Bag Lots of people are talking about AI content tools these days. Usually, they’re either saying: “AI content tools are garbage and the output is horrible,” Or: “AI content tools are a game-changer!” So which one is it? The truth is somewhere in-between. In 2021, AI content writing tools are pretty bad. The output you’re going to get is far from something you can publish on your website. That said, some SEOs use such tools to get a very, very rough draft of the article written, and then they do intense surgery on it to make it usable. Should you use AI content writing tools? If you ask me, no - it’s easier to hire a proficient content writer than spend hours salvaging AI-written content. That said, I do believe that such tools are going to get much better years down the line. This one was, clearly, more of a personal opinion than a fact. I’d love to hear YOUR opinion on AI content tools! Are they a fad, or are they the future of content creation? Let me know in the comments. SEO Tip #30. Don’t Overdo it With SEO Tools There are a lot of SEO tools out there for pretty much any SEO function. Keyword research, link-building, on-page, outreach, technical SEO, you name it! If you were to buy most of these tools for your business, you’d easily spend 4-figures on SEO tools per month. Luckily, though, you don’t actually need most of them. At the end of the day, the only must-have SEO tools are: An SEO Suite (Paid). Basically SEMrush or Ahrefs. Both of these tools offer an insane number of features - backlink analysis, keyword research, and a ton of other stuff. Yes, 99 USD a month is expensive for a tool. But then again, if you value your time 20 USD/hour and this tool saves you 6 hours, it's obviously worth it, right? On-Page SEO Tool (Free). RankMath or Yoast. Basically, a tool that's going to help you optimize web pages or blog posts as per SEO best practices. Technical SEO Tool (Freemium). You can use ScreamingFrog to crawl your entire website and find technical SEO problems. There are probably other tools that also do this, but ScreamingFrog is the most popular option. The freemium version of the tool only crawls a limited number of pages (500 URLs, to be exact), so if your website is relatively big, you'll need to pay for the tool. Analytics (Free). Obviously, you'll need Google Analytics (to track website traffic) and Google Search Console (to track organic traffic, specifically) set up on your website. Optionally, you can also use Google Track Manager to better track how your website visitors interact with the site. MozBar (Free). Chrome toolbar that lets you simply track the number of backlinks on Google Search Queries, Domain Authority, and a bunch of other stuff. Website Speed Analysis (Free). You can use Google Page Speed Insights to track how fast your website loads, as well as how mobile-friendly it is. Outreach Tool (Paid). Tool for reaching out to prospects for link-building, guest posting, etc. There are about a dozen good options for this. Personally, I like to use Snov for this. Optimized GMB Profile (Free). Not a tool per se, but if you're a local business, you need to have a well-optimized Google My Business profile. Google Keyword Planner (Free). This gives you the most reliable search volume data of all the tools. So, when doing keyword research, grab the search volume from here. Tool for Storing Keyword Research (Free). You can use Google Sheets or AirTable to store your keyword research and, at the same time, use it as a content calendar. Hemingway App (Free). Helps keep your SEO content easy to read. Spots passive voice, complicated words, etc. Email Finder (Freemium). You can use a tool like Hunter to find the email address of basically anyone on the internet (for link-building or guest posting purposes). Most of the tools that don’t fit into these categories are 100% optional. SEO Tip #31. Hiring an SEO? Here’s How to Vet Them Unless you’re an SEO pro yourself, hiring one is going to be far from easy. There’s a reason there are so many “SEO experts” out there - for the layman, it’s very hard to differentiate between someone who knows their salt and a newbie who took an SEO course, like, last week. Here’s how you can vet both freelance and full-time SEOs: Ask for concrete traffic numbers. The SEO pro should give you the exact numbers on how they’ve grown a website in the past - “100% SEO growth in 1 year” doesn’t mean much if the growth is from 10 monthly traffic to 20. “1,000 to 30,000” traffic, on the other hand, is much better. Ask for client names. While some clients ask their SEOs to sign an NDA and not disclose their collaboration, most don’t. If an SEO can’t name a single client they’ve worked with in the past, that’s a red flag. Make sure they have the right experience. Global and local SEO have very different processes. Make sure that the SEO has experience with the type of SEO you need. Make sure you’re looking for the right candidate. SEO pros can be content writers, link-builders, web developers, or all of the above simultaneously. Make sure you understand which one you need before making the hire. If you’re looking for someone to oversee your content ops, you shouldn’t hire a technical SEO expert. Look for SEO pros in the right places. Conventional job boards are overrated. Post your job ads on SEO communities instead. E.g. this sub, bigseo, SEO Signals Facebook group, etc. SEO Tip #32. Blog Post Not Ranking? Follow This Checklist I wanted to format the post natively for Reddit, but it’s just SO much better on Notion. Tl;dr, the checklist covers every reason your post might not be ranking: Search intent mismatch. Inferior content. Lack of internal linking. Lack of backlinks. And the like. Checklist URL at the intro of the post. SEO Tip #33. Avoid BS Link-Building Tactics The only type of link-building that works is building proper, quality links from websites with a good backlink profile and decent organic traffic. Here’s what DOESN’T work: Blog comment links Forum spam links Drive-by Reddit comment/post links Web 2.0 links Fiverr “100 links for 10 bucks” bs If your “SEO agency” says they’re doing any of the above instead of actually trying to build you links from quality websites, you’re being scammed. SEO Tip #34. Know When to Use 301 and 302 Redirects When doing redirects, it’s very important to know the distinction between these two. 301 is a permanent page redirect and passes on link juice. If you’re killing off a page that has backlinks, it’s better to 301 it to your homepage so that you don’t lose the link juice. If you simply delete a page, it’s going to be a 404, and the backlink juice is lost forever. 302 is a temporary page redirect and doesn’t pass on link juice. If the redirect is temporary, you do a 302. E.g. you want to test how well a new page is going to perform w/ your audience. SEO Tip #35. Social Signals Matter (But Not How You Think) Social signals are NOT a ranking factor. And yet, they can help your content rank on Google’s front page. Wondering what the hell am I talking about? Here’s what’s up: As I said, social signals are not a ranking factor. It’s not something Google takes into consideration to decide whether your article should rank or not. That said, social signals CAN lead to your article ranking better. Let’s say your article goes viral and gets around 20k views within a week. A chunk of these viewers are going to forget your domain/link and they’re going to look up the topic on Google via your chosen keyword + your brand name. The amount of people looking for YOUR keyword and exclusively picking your result over others is going to make Google think that your content is satisfying search intent better than the rest, and thus, reward you with better ranking. SEO Tip #36. Run Remarketing Ads to Lift Organic Traffic Conversions Not satisfied with your conversion rates? You can use Facebook ads to help increase them. Facebook allows you to do something called “remarketing.” This means you can target anyone that visited a certain page (or multiple pages) on your website and serve them ads on Facebook. There are a TON of ways you can take advantage of this. For example, you can target anyone that landed on a high buyer intent page and serve them ads pitching your product or a special offer. Alternatively, you can target people who landed on an educational blog post and offer them something to drive them down the funnel. E.g. free e-book or white paper to teach them more about your product or service. SEO Tip #37. Doing Local SEO? Follow These Tips Local SEO is significantly different from global SEO. Here’s how the two differ (and what you need to do to drive local SEO results): You don’t need to publish content. For 95% of local businesses, you only want to rank for keywords related to your services/products, you don’t actually need to create educational content. You need to focus more on reviews and citation-building. One of Google Maps’ biggest ranking factors is the of reviews your business has. Encourage your customers to leave a review if they enjoyed your product/service through email or real-life communication. You need to create service pages for each location. As a local business, your #1 priority is to rank for keywords around your service. E.g. If you're a personal injury law firm, you want to optimize your homepage for “personal injury law firm” and then create separate pages for each service you provide, e.g. “car accident lawyer,” “motorcycle injury law firm,” etc. Focus on building citations. Being listed on business directories makes your business more trustworthy for Google. BrightLocal is a good service for this. You don’t need to focus as much on link-building. As local SEO is less competitive than global, you don’t have to focus nearly as much on building links. You can, in a lot of cases, rank with the right service pages and citations. SEO Tip #38. Stop Ignoring the Outreach Emails You’re Getting (And Use Them to Build Your Own Links) Got a ton of people emailing you asking for links? You might be tempted to just send them all straight to spam, and I don’t blame you. Outreach messages like “Hey Dr Jigsaw, your article is A+++ amazing! ...can I get a backlink?” can get hella annoying. That said, there IS a better way to deal with these emails: Reply and ask for a link back. Most of the time, people who send such outreach emails are also doing heavy guest posting. So, you can ask for a backlink from a 3rd-party website in exchange for you mentioning their link in your article. Win-win! SEO Tip #39. Doing Internal Linking for a Large Website? This’ll Help Internal linking can get super grueling once you have hundreds of articles on your website. Want to make the process easier? Do this: Pick an article you want to interlink on your website. For the sake of the example, let’s say it’s about “business process improvement.” Go on Google and look up variations of this keyword mentioned on your website. For example: Site:\[yourwebsite\] “improve business process” Site:\[yourwebsite\] “improve process” Site:\[yourwebsite\] “process improvement” The above queries will find you the EXACT articles where these keywords are mentioned. Then, all you have to do is go through them and include the links. SEO Tip #40. Got a Competitor Copying Your Content? File a DMCA Notice Fun fact - if your competitors are copying your website, you can file a DMCA notice with Google. That said, keep in mind that there are consequences for filing a fake notice.

Started a content marketing agency 8 years ago - $0 to $7,863,052 (2025 update)

Hey friends, My name is Tyler and for the past 8 years, I’ve been documenting my experience building a content marketing agency called Optimist. Year 1 — 0 to $500k ARR Year 2 — $500k to $1MM ARR Year 3 — $1MM ARR to $1.5MM(ish) ARR Year 4 — $3,333,686 Revenue Year 5 — $4,539,659 Revenue Year 6 — $5,974,324 Revenue Year 7 - $6,815,503 Revenue (Edit: Seems like links are banned now. You can check my post history for all of my previous updates with lessons and learnings.) How Optimist Works First, an overview/recap of the Optimist business model: We operate as a “collective” of full time/professional freelancers Everyone aside from me is a contractor Entirely remote/distributed team We pay freelancers a flat fee for most work, working out to roughly $65-100/hour. Clients pay us a flat monthly fee for full-service content marketing (research, strategy, writing, editing, design/photography, reporting and analytics, targeted linkbuilding, and more)\ Packages range in price from \~$10-20k/mo \This is something we are revisiting now* The Financials In 2024, we posted $1,032,035.34 in revenue. This brings our lifetime revenue to $7,863,052. Here’s our monthly revenue from January 2017 to December of 2024. (Edit: Seems like I'm not allowed to link to the chart.) The good news: Revenue is up 23% YoY. EBITDA in Q4 trending up 1-2 points. We hosted our first retreat in 4 years, going to Ireland with about half the team. The bad news: Our revenue is still historically low. At $1MM for the year, we’re down about 33% from our previous years over $1.5MM. Revenue has been rocky. It doesn’t feel like we’ve really “recovered” from the bumps last year. The trend doesn’t really look great. Even though, anecdotally, it feels like we are moving in a good direction. EBITDA is still hovering at around 7%. Would love to get that closer to 20%. (For those who may ask: I’m calculating EBITDA after paying taxes and W2 portion of my income.) — Almost every year, my update starts the same way: This has been a year of growth and change. Both for my business—and me personally. 2024 was no different. I guess that tells you something about entrepreneurship. It’s a lot more like sailing a ship than driving a car. You’re constantly adapting, tides are shifting, and any blip of calm is usually just a moment before the next storm. As with past years, there’s a lot to unpack from the last 12 months. Here we go again. Everything is Burning In the last 2 years, everything has turned upside down in the world of content and SEO. Back in 2020, we made a big decision to re-position the agency. (See post history) We decided to narrow our focus to our most successful, profitable, and consistent segment of clients and re-work our entire operation to focus on serving them. We defined our ICP as: \~Series A ($10mm+ funding) with 6-12 months runway to scale organic as a channel Product-led company with “simple” sales cycle involving fewer stakeholders Demonstrable opportunity to use SEO to drive business growth Our services: Content focused on growing organic search (SEO) Full-service engagements that included research, planning, writing, design, reporting And our engagement structure: Engaged directly with an executive; ownership over strategy and day-to-day execution 1-2 points of contact or stakeholders Strategic partner that drives business growth (not a service vendor who makes content) Most importantly, we decided that we were no longer going to offer a broader range of content that we used to sell. That included everything from thought leadership content to case studies and ebooks. We doubled-down on “SEO content” for product-led SaaS companies. And this worked phenomenally for us. We started bringing on more clients than ever. We developed a lot of internal system and processes that helped us scale and take on more work than we’ve ever had and drive great outcomes for our ideal clients. But in 2023 and 2024, things started going awry. One big change, of course, was the rise of AI. Many companies and executives (and writers) feel that AI can write content just as well as an agency like ours. That made it a lot harder to sell a $10,000 per month engagement when they feel like the bulk of the work could be “done for free.” (Lots of thoughts on this if you want my opinions.) But it wasn’t just that. Google also started tinkering with their algorithm, introducing new features like AI Overviews, and generally changing the rules of the game. This created 3 big shifts in our world: The perceived value of content (especially “SEO content”) dropped dramatically in many people’s minds because of AI’s writing capabilities SEO became less predictable as a source of traffic and revenue It’s harder than ever for startups and smaller companies to rank for valuable keywords (let alone generate any meaningful traffic or revenue from them) The effect? The middle of the content market has hollowed out. People—like us—providing good, human-crafted content aimed on driving SEO growth saw a dramatic decline in demand. We felt it all year. Fewer and fewer leads. The leads we did see usually scoffed at our prices. They were indexing us against the cost of content mills and mass-produced AI articles. It was a time of soul-searching and looking for a way forward. I spent the first half of the year convinced that the only way to survive was to run toward the fire. We have to build our own AI workflows. We have to cut our rates internally. We have to get faster and cheaper to stay competitive with the agencies offering the same number of deliverables for a fraction of our rates. It’s the only way forward. But then I asked myself a question… Is this the game I actually want to play? As an entrepreneur, do I want to run a business where I’m competing mostly on price and efficiency rather than quality and value? Do I want to hop into a race toward cheaper and cheaper content? Do I want to help people chase a dwindling amount of organic traffic that’s shrinking in value? No. That’s not the game I want to play. That’s not a business I want to run. I don’t want to be in the content mill business. So I decided to turn the wheel—again. Repositioning Part II: Electric Boogaloo What do you do when the whole world shifts around you and the things that used to work aren’t working anymore? You pivot. You re-position the business and move in another direction. So that’s what we decided to do. Again. There was only one problem: I honestly wasn’t sure what opportunities existed in the content marketing industry outside of what we were already doing. We lived in a little echo chamber of startups and SEO. It felt like the whole market was on fire and I had fight through the smoke to find an escape hatch. So I started making calls. Good ol’ fashioned market research. I reached out to a few dozen marketing and content leaders at a bunch of different companies. I got on the phone and just asked lots of questions about their content programs, their goals, and their pain points. I wanted to understand what was happening in the market and how we could be valuable. And, luckily, this process really paid off. I learned a lot about the fragmentation happening across content and how views were shifting. I noticed key trends and how our old target market really wasn’t buying what we were selling. Startups and small companies are no longer willing to invest in an agency like ours. If they were doing content and SEO at all, they were focused entirely on using AI to scale output and minimize costs. VC money is still scarce and venture-backed companies are more focused on profitability than pure growth and raising another round. Larger companies (\~500+ employees) are doing more content than ever and drowning in content production. They want to focus on strategy but can barely tread water keeping up with content requests from sales, demand gen, the CEO, and everyone else. Many of the companies still investing in content are looking at channels and formats outside of SEO. Things like thought leadership, data reports, interview-driven content, and more. They see it as a way to stand out from the crowd of “bland SEO content.” Content needs are constantly in flux. They range from data reports and blog posts to product one-pagers. The idea of a fixed-scope retainer is a total mismatch for the needs of most companies. All of this led to the logical conclusion: We were talking to the wrong people about the wrong things\.\ Many companies came to one of two logical conclusions: SEO is a risky bet, so it’s gotta be a moonshot—super-low cost with a possibility for a big upside (i.e., use AI to crank out lots of content. If it works, great. If it doesn’t, then at least we aren’t out much money.) SEO is a risky bet, so we should diversify into other strategies and channels to drive growth (i.e., shift our budget from SEO and keyword-focused content to video, podcasts, thought leadership, social, etc) Unless we were going to lean into AI and dramatically cut our costs and rates, our old buyers weren’t interested. And the segment of the market that needs our help most are looking primarily for production support across a big range of content types. They’re not looking for a team to run a full-blown program focused entirely on SEO. So we had to go back to the drawing board. I’ve written before about our basic approach to repositioning the business. But, ultimately it comes down to identifying our unique strengths as a team and then connecting them to needs in the market. After reviewing the insights from my discussions and taking another hard look at our business and our strengths, I decided on a new direction: Move upmarket: Serve mid-size to enterprise businesses with \~500-5,000 employees instead of startups Focus on content that supports a broader range of business goals instead of solely on SEO and organic growth (e.g., sales, demand gen, brand, etc) Shift back to our broader playbook of content deliverables, including thought leadership, data studies, and more Focus on content execution and production to support an internally-directed content strategy across multiple functions In a way, it’s sort of a reverse-niche move. Rather than zooming in specifically on driving organic growth for startups, we want to be more of an end-to-end content production partner that solves issues of execution and operations for all kinds of content teams. It’s early days, but the response here has been promising. We’ve seen an uptick in leads through Q4. And more companies in our pipeline fit the new ICP. They’re bigger, often have more budget. (But they move more slowly). We should know by the end of the quarter if this maneuver is truly paying off. Hopefully, this will work out. Hopefully our research and strategy are right and we’ll find a soft landing serving a different type of client. If it doesn’t? Then it will be time to make some harder decisions. As I already mentioned, I’m not interested in the race to the bottom of AI content. And if that’s the only game left in town, then it might be time to think hard about a much bigger change. — To be done: Build new content playbooks for expanded deliverables Build new showcase page for expanded deliverables Retooling the Operation It’s easy to say we’re doing something new. It’s a lot harder to actually do it—and do it well. Beyond just changing our positioning, we have to do open-heart surgery on the entire content operation behind the scenes. We need to create new systems that work for a broader range of content types, formats, and goals. Here’s the first rub: All of our workflows are tooled specifically for SEO-focused content. Every template, worksheet, and process that we’ve built and scaled in the last 5 years assumes that the primary goal of every piece of content is SEO. Even something as simple as requiring a target keyword is a blocker in a world where we’re not entirely focused on SEO. This is relatively easy to fix, but it requires several key changes: Update content calendars to make keywords optional Update workflows to determine whether we need an optimization report for each deliverable Next, we need to break down the deliverables into parts rather than a single line item. In our old system, we would plan content as a single row in a Content Calendar spreadsheet. It was a really wide sheet with lots of fields where we’d define the dimensions of each individual article. This was very efficient and simple to follow. But every article had the same overall scope when it came to the workflow. In Asana (our project management tool), all of the steps in the creation were strung together in a single task. We would create a few basic templates for each client, and then each piece would flow through the same steps: Briefing Writing Editing Design etc. If we had anything that didn’t fit into the “standard” workflow, we’d just tag it in the calendar with an unofficial notation \[USING BRACKETS\]. It worked. But it wasn’t ideal. Now we need the steps to be more modular. Imagine, for example, a client asks us to create a mix of deliverables: 1 article with writing + design 1 content brief 1 long-form ebook with an interview + writing + design Each of these would require its own steps and its own workflow. We need to break down the work to accommodate for a wider variety of workflows and variables. This means we need to update the fields and structure of our calendar to accommodate for the new dimensions—while also keeping the planning process simple and manageable. This leads to the next challenge: The number of “products” that we’re offering could be almost infinite. Just looking at the example scope above, you can mix and match all of these different building blocks to create a huge variety of different types of work, each requiring its own workflow. This is part of the reason we pivoted away from this model to focus on a productized, SEO-focused content service back in 2020. Take something as simple as a case study. On the surface, it seems like one deliverable that can be easily scoped and priced, right? Well, unpack what goes into a case study: Is there already source material from the customer or do we need to conduct an interview? How long is it? Is it a short overview case study or a long-form narrative? Does it need images and graphics? How many? Each of these variables opens up 2-3 possibilities. And when you combine them, we end up with something like 10 possible permutations for this single type of deliverable. It gets a bit messy. But not only do we have to figure out how to scope and price all for all of these variables, we also have to figure out how to account for these variables in the execution. We have to specify—for every deliverable—what type it is, how long, which steps are involved and not involved, the timeline for delivery, and all of the other factors. We’re approaching infinite complexity, here. We have to figure out a system that allows for a high level of flexibility to serve the diverse needs of our clients but is also productized enough that we can build workflows, process, and templates to deliver the work. I’ve spent the last few months designing that system. Failed Attempt #1: Ultra-Productization In my first pass, I tried to make it as straight forward as possible. Just sit down, make a list of all of the possible deliverables we could provide and then assign them specific scopes and services. Want a case study? Okay that’ll include an interview, up to 2,000 words of content, and 5 custom graphics. It costs $X. But this solution quickly fell apart when we started testing it against real-world scenarios. What if the client provided the brief instead of us creating one? What if they didn’t want graphics? What if this particular case study really needs to be 3,000 words but all of the others should be 2,000? In order for this system to work, we’d need to individual scope and price all of these permutations of each productized service. Then we’d need to somehow keep track of all of these and make sure that we accurately scope, price, and deliver them across dozens of clients. It’s sort of like a restaurant handling food allergies by creating separate versions of every single dish to account for every individual type of allergy. Most restaurants have figured out that it makes way more sense to have a “standard” and an “allergy-free” version. Then you only need 2 options to cover 100% of the cases. Onto the next option. Failed Attempt #2: Deliverable-Agnostic Services Next, I sat down with my head of Ops, Katy, to try to map it out. We took a big step back and said: Why does the deliverable itself even matter? At the end of the day, what we’re selling is just a few types of work (research, writing, editing, design, etc) that can be packaged up in an infinite number of ways. Rather than try to define deliverables, shouldn’t we leave it open ended for maximum flexibility? From there, we decided to break down everything into ultra-modular building blocks. We started working on this super complex system of modular deliverables where we would have services like writing, design, editing, etc—plus a sliding scale for different scopes like the length of writing or the number of images. In theory, it would allow us to mix and match any combination of services to create custom deliverables for the client. In fact, we wanted the work to be deliverable-agnostic. That way we could mold it to fit any client’s needs and deliver any type of content, regardless of the format or goal. Want a 5,000-word case study with 15 custom graphics? That’ll be $X. Want a 2,000-word blog post with an interview and no visuals? $Y. Just want us to create 10 briefs, you handle the writing, and we do design? It’s $Z. Again, this feels like a reasonable solution. But it quickly spiraled out of amuck. (That’s an Office reference.) For this to work, we need to have incredibly precise scoping process for every single deliverable. Before we can begin work (or even quote a price), we need to know pretty much the exact word count of the final article, for example. In the real world? This almost never happens. The content is as long as the content needs to be. Clients rarely know if the blog post should be 2,000 words or 3,000 words. They just want good content. We have a general ballpark, but we can rarely dial it in within just 1,000 words until we’ve done enough research to create the brief. Plus, from a packaging and pricing perspective, it introduces all kind of weird scenarios where clients will owe exactly $10,321 for this ultra-specific combination of services. We were building an open system that could accommodate any and all types of potential deliverables. On the face that seems great because it makes us incredibly flexible. In reality, the ambiguity actually works against us. It makes it harder for us to communicate to clients clearly about what they’ll get, how much it will cost, and how long it will take. That, of course, also means that it hurts our client relationships. (This actually kind of goes back to my personal learnings, which I’ll mention in a bit. I tend to be a “let’s leave things vague so we don’t have to limit our options” kind of person. But I’m working on fixing this to be more precise, specific, and clear in everything that we do.) Dialing It In: Building a Closed System We were trying to build an open system. We need to build a closed system. We need to force clarity and get specific about what we do, what we don’t do, and how much it all costs. Then we need a system to expand on that closed system—add new types of deliverables, new content playbooks, and new workflows if and when the need arises. With that in mind, we can start by mapping out the key dimensions of any type of deliverable that we would ever want to deliver. These are the universal dimensions that determine the scope, workflow, and price of any deliverable—regardless of the specific type output. Dimensions are: Brief scope Writing + editing scope Design scope Interview scope Revision (rounds) Scope, essentially, just tells us how many words, graphics, interviews, etc are required for the content we’re creating. In our first crack at the system, we got super granular with these scopes. But to help force a more manageable system, we realized that we didn’t need tiny increments for most of this work. Instead, we just need boundaries—you pay $X for up to Y words. We still need some variability around the scope of these articles. Obviously, most clients won’t be willing to pay the same price for a 1,000-word article as a 10,000-word article. But we can be smarter about the realistic break points. We boiled it down to the most common ranges: (Up to) 250 words 1,000 words 3,000 words 6,000 words 10,000 words This gives us a much more manageable number of variables. But we still haven’t exactly closed the system. We need one final dimension: Deliverable type. This tells us what we’re actually building with these building blocks. This is how we’ll put a cap on the potentially infinite number of combinations we could offer. The deliverable type will define what the final product should look like (e.g., blog post, case study, ebook, etc). And it will also give us a way to put standards and expectations around different types of deliverables that we want to offer. Then we can expand on this list of deliverables to offer new services. In the mean time, only the deliverables that we have already defined are, “on the menu,” so to speak. If a client comes to us and asks for something like a podcast summary article (which we don’t currently offer), we’ll have to either say we can’t provide that work or create a new deliverable type and define the dimensions of that specific piece. But here’s the kicker: No matter the deliverable type, it has to still fit within the scopes we’ve already defined. And the pricing will be the same. This means that if you’re looking for our team to write up to 1,000 words of content, it costs the same amount—whether it’s a blog post, an ebook, a LinkedIn post, or anything else. Rather than trying to retool our entire system to offer this new podcast summary article deliverable, we’ll just create the new deliverable type, add it to the list of options, and it’s ready to sell with the pre-defined dimensions we’ve already identified. To do: Update onboarding workflow Update contracts and scope documents Dial in new briefing process Know Thyself For the last year, I’ve been going through personal therapy. (Huge shout out to my wife, Laura, for her support and encouragement throughout the process.) It’s taught me a lot about myself and my tendencies. It’s helped me find some of my weaknesses and think about how I can improve as a person, as a partner, and as an entrepreneur. And it’s forced me to face a lot of hard truths. For example, consider some of the critical decisions I’ve made for my business: Unconventional freelance “collective” model No formal management structure Open-ended retainers with near-infinite flexibility General contracts without defined scope “Take it or leave it” approach to sales and marketing Over the years, I’ve talked about almost everything on this list as a huge advantage. I saw these things as a reflection of how I wanted to do things differently and better than other companies. But now, I see them more as a reflection of my fears and insecurities. Why did I design my business like this? Why do I want so much “flexibility” and why do I want things left open-ended rather than clearly defined? One reason that could clearly explain it: I’m avoidant. If you’re not steeped in the world of therapy, this basically means that my fight or flight response gets turned all the way to “flight.” If I’m unhappy or uncomfortable, my gut reaction is usually to withdraw from the situation. I see commitment and specificity as a prelude to future conflict. And I avoid conflict whenever possible. So I built my business to minimize it. If I don’t have a specific schedule of work that I’m accountable for delivering, then we can fudge the numbers a bit and hope they even out in the end. If I don’t set a specific standard for the length of an article, then I don’t have to let the client know when their request exceeds that limit. Conflict….avoided? Now, that’s not to say that everything I’ve built was wrong or bad. There is a lot of value in having flexibility in your business. For example, I would say that our flexible retainers are, overall, an advantage. Clients have changing needs. Having flexibility to quickly adapt to those needs can be a huge value add. And not everything can be clearly defined upfront (at least not without a massive amount of time and work just to decide how long to write an article). Overly-rigid structures and processes can be just as problematic as loosey-goosey ones. But, on the whole, I realized that my avoidant tendencies and laissez faire approach to management have left a vacuum in many areas. The places where I avoided specificity were often the places where there was the most confusion, uncertainty, and frustration from the team and from clients. People simply didn’t know what to expect or what was expected of them. Ironically, this often creates the conflict I’m trying to avoid. For example, if I don’t give feedback to people on my team, then they feel uneasy about their work. Or they make assumptions about expectations that don’t match what I’m actually expecting. Then the client might get upset, I might get upset, and our team members may be upset. Conflict definitely not avoided. This happens on the client side, too. If we don’t define a specific timeline when something will be delivered, the client might expect it sooner than we can deliver—creating frustration when we don’t meet their expectation. This conflict actually would have been avoided if we set clearer expectations upfront. But we didn’t do that. I didn’t do that. So it’s time to step up and close the gaps. Stepping Up and Closing the Gaps If I’m going to address these gaps and create more clarity and stability, I have to step up. Both personally and professionally. I have to actually face the fear and uncertainty that drives me to be avoidant. And then apply that to my business in meaningful ways that aren’t cop-out ways of kinda-sorta providing structure without really doing it. I’ve gotta be all in. This means: Fill the gaps where I rely on other people to do things that aren’t really their job but I haven’t put someone in place to do it Set and maintain expectations about our internal work processes, policies, and standards Define clear boundaries on things like roles, timelines, budgets, and scopes Now, this isn’t going to happen overnight. And just because I say that I need to step up to close these gaps doesn’t mean that I need to be the one who’s responsible for them (at least not forever). It just means that, as the business leader, I need to make sure the gaps get filled—by me or by someone else who has been specifically charged with owning that part of the operation. So, this is probably my #1 focus over the coming quarter. And it starts by identifying the gaps that exist. Then, step into those gaps myself, pay someone else to fill that role, or figure out how to eliminate the gap another way. This means going all the way back to the most basic decisions in our business. One of the foundational things about Optimist is being a “different kind” of agency. I always wanted to build something that solved for the bureaucracy, hierarchy, and siloed structure of agencies. If a client has feedback, they should be able to talk directly to the person doing the work rather than going through 3 layers of account management and creative directors. So I tried to be clever. I tried to design all kinds of systems and processes that eliminated these middle rungs. (In retrospect, what I was actually doing was designing a system that played into my avoidant tendencies and made it easy to abdicate responsibility for lots of things.) Since we didn’t want to create hierarchy, we never implemented things like Junior and Senior roles. We never hired someone to manage or direct the individual creatives. We didn’t have Directors or VPs. (Hell, we barely had a project manager for the first several years of existence.) This aversion to hierarchy aligned with our values around elevating ownership and collective contribution. I still believe in the value a flat structure. But a flat structure doesn’t eliminate the complexity of a growing business. No one to review writers and give them 1:1 feedback? I guess I’ll just have to do that….when I have some spare time. No Content Director? Okay, well someone needs to manage our content playbooks and roll out new ones. Just add it to my task list. Our flat structure didn’t eliminate the need for these roles. It just eliminated the people to do them. All of those unfilled roles ultimately fell back on me or our ops person, Katy. Of course, this isn’t the first time we’ve recognized this. We’ve known there were growing holes in our business as it’s gotten bigger and more complex. Over the years, we’ve experimented with different ways to solve for it. The Old Solution: Distributed Ops One system we designed was a “distributed ops” framework. Basically, we had one person who was the head of ops (at the time, we considered anything that was non-client-facing to be “ops”). They’d plan and organize all of the various things that needed to happen around Optimist. Then they’d assign out the work to whoever was able to help. We had a whole system for tying this into the our profit share and even gave people “Partner” status based on their contributions to ops. It worked—kinda. One big downfall is that all of the tasks and projects were ad hoc. People would pick up jobs, but they didn’t have much context or expertise to apply. So the output often varied. Since we were trying to maintain a flat structure, there was minimal oversight or management of the work. In other words, we didn’t always get the best results. But, more importantly, we still didn’t close all of the gaps entirely. Because everything was an ad-hoc list of tasks and projects, we never really had the “big picture” view of everything that needed to be done across the business. This also meant we rarely had clarity on what was important, what was trivial, and what was critical. We need a better system. Stop Reinventing the Wheel (And Create a Damn Org Chart) It’s time to get serious about filling the gaps in our business. It can’t be a half-fix or an ad hoc set of projects and tasks. We need clarity on the roles that need to be filled and then fill them. The first step here is to create an org chart. A real one. Map out all of the jobs that need to be done for Optimist to be successful besides just writers and designers. Roles like: Content director Design director SEO manager Reporting Finance Account management Business development Sales Marketing Project management It feels a bit laughable listing all of these roles. Because most are either empty or have my name attached to them. And that’s the problem. I can’t do everything. And all of the empty roles are gaps in our structure—places where people aren’t getting the direction, feedback, or guidance they need to do their best work. Or where things just aren’t being done consistently. Content director, for example, should be responsible for steering the output of our content strategists, writers, and editors. They’re not micromanaging every deliverable. But they give feedback, set overall policy, and help our team identify opportunities to get better. Right now we don’t have anyone in that role. Which means it’s my job—when I have time. Looking at the org chart (a real org chart that I actually built to help with this), it’s plain as day how many roles look like this. Even if we aren’t going to implement a traditional agency structure and a strict hierarchy, we still need to address these gaps. And the only way for that to happen is face the reality and then create a plan to close the gaps. Now that we have a list of theoretical roles, we need to clearly define the responsibilities and boundaries of those roles to make sure they cover everything that actually needs to happen. Then we can begin the process of delegating, assigning, hiring, and otherwise addressing each one. So that’s what I need to do. To be done: Create job descriptions for all of the roles we need to fill Hire Biz Dev role Hire Account Lead role(s) Hire Head of Content Playing Offense As we move into Q1 of 2025 and I reflect on the tumultuous few years we’ve had, one thought keeps running through my head. We need to play offense. Most of the last 1-2 years was reacting to changes that were happening around us. Trying to make sense and chart a new path forward. Reeling. But what I really want—as a person and as an entrepreneur—is to be proactive. I want to think and plan ahead. Figure out where we want to go before we’re forced to change course by something that’s out of our control. So my overarching focus for Q1 is playing offense. Thinking longer term. Getting ahead of the daily deluge and creating space to be more proactive, innovative, and forward thinking. To do: Pilot new content formats Audit and update our own content strategy Improve feedback workflows Build out long-term roadmap for 1-2 years for Optimist Final Note on Follow-Through and Cadence In my reflection this year, one of the things I’ve realized is how helpful these posts are for me. I process by writing. So I actually end up making a lot of decisions and seeing things more clearly each time I sit down to reflect and write my yearly recap. It also gives me a space to hold myself accountable for the things I said I would do. So, I’m doing two things a bit differently from here on out. First: I’m identifying clear action items that I’m holding myself accountable for getting done in the next 3 months (listed in the above sections). In each future update, I’ll do an accounting of what I got done and what wasn’t finished (and why). Second: I’m going to start writing shorter quarterly updates. This will gives me more chances each year to reflect, process, and make decisions. Plus it gives me a shorter feedback loop for the action items that I identified above. (See—playing offense.) — Okay friends, enemies, and frenemies. This is my first update for 2025. Glad to share with y’all. And thanks to everyone who’s read, commented, reached out, and shared their own experiences over the years. We are all the accumulation of our connections and our experiences. As always, I will pop in to respond to comments and answer questions. Feel free to share your thoughts, questions, and general disdain down below. Cheers, Tyler

Switching Gears: Implementing AI for My Agency’s Marketing After a Decade

Hi there, I’ve been running a software development and design agency for the last 10 years, mainly focusing on building custom solutions for businesses and SaaS. For the last 2 years, I’ve consistently recommended that clients use AI technologies, especially for social media and content creation to generate traffic. Funny enough, I wasn’t practicing what I preached. Most of my client projects came from platforms like Upwork and word-of-mouth referrals from clients or people from networking events. Background I started my journey in 2014, switching from an employee to a freelancer. Within the first 10 months, my initial projects grew beyond what I could handle alone, prompting me to hire additional developers. This shift turned my role from a full-stack developer to a team lead and developer. Over the years, my focus has been a blend of tech and product. About five years ago, I realized the importance of design, leading me to adding designers to the agency to provide full-cycle service development—from product ideation and design to development, testing, launch, and support. I still continue to set up dedicated teams for some clients, maintaining a strong technical role as a tech lead, solution architect, and head product designer. To enhance my skills, I even completed UI/UX design courses to offer better product solutions. Despite these changes, building products has always been the easy part. The challenge was ensuring these client products didn’t end up in the graveyard due to poor product-market fit, often caused by inadequate marketing and sales strategies but more often just absence of them. (we are talking about startup and first time founders here 🙂 ) My Journey and Observations Advising Clients: I often found myself advising clients on increasing traffic for their SaaS products and crafting strategic marketing plans. Learning: I’ve gained most of my knowledge from consuming internet materials, courses, and blog posts and learning from successful client project launches. Realization: Despite giving this advice, I wasn’t applying these strategies to my own business, leading to low visits to my agency’s website. Initial Solution: Hiring a Marketer Hiring: I brought in a marketer with a solid background in content creating and interview video editing from an educational organization. Goal: The aim was to increase website visits through a comprehensive marketing strategy. Outcome: Although the content produced was high-quality and useful for pitching services, it didn’t lead to significant traffic increases. Issue: The marketer focused more on content creation rather than distribution channels, which limited effectiveness. Shift to AI-Driven Strategy Experiment: I decided to try using AI for content creation and distribution, which aligns with my agency’s specialization in design-driven development and AI integrations. Implementation plan: I will be generating all content with minimal edits using AI and implementing a strategic backlinking approach. Backlinking Strategy Initial Plan: I initially thought of hiring a specialist for backlinks. Realization: The costs and profiles of freelancers didn’t seem promising. Solution: I found AI-driven services for backlinks, which seem more efficient and cost-effective. Plan: My plan is to use these tools for programmatic SEO-driven AI-generated articles and third-party backlinking services over the next two to three months. Current Approach Management: This approach can be managed and executed by 1 person and monitored weekly, reducing human error and optimizing efficiency. I will start it myself and then replace myself with an editor with managing skills. Reflection: It’s a bit ironic and funny that it took me 10 years to start implementing these strategies in my own agency business, but I now feel more confident with AI and automation in place. Why Increase Website Visitors? You might ask, why do I want to increase the number of visitors to the site, and how can I ensure these visitors will be qualified? Hands-On Experience: To gain hands-on experience and perform this exercise effectively. Introduce Packaged Services: I want to introduce a set of low-cost packaged services tailored for non-technical people who want to build things for themselves - the DIY kits for non-technical folks. These services will provide a foundational template for them to build upon on top of existing established solutions such as Wix, Square Why am I Posting and Sharing Here? You might also wonder, why am I posting it here and sharing this? Well, I'm doing this more for myself. Most of my career, the things I’ve done have been behind the curtains. With this small project, I want to make it public to see the reaction of the community. Perhaps there will be good and smart suggestions offered, and maybe some insights or highlights of tools I wasn’t aware of or didn’t consider. I’ll keep sharing updates on this journey of website promotion, marketing, and SEO. My current goal is to reach 2,000 visits per month, which is a modest start. Looking forward to any thoughts or advice from this community! Disclaimer: This content was not generated by AI, but it was edited by it 😛

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

My (23M) first $10k month installing internal GPT-4 for businesses

It all started in this very own subreddit just a month ago. I posted “How I made a secure GPT-4 for my company knowledge base” and left a cheeky Google Form in the comments. The post got 162 upvotes, 67 comments and, most importantly… ~30 form answers 😈 From there I got on 12 calls and even though I initially offered to do it for free… I closed 2 clients for $5k each. Data privacy was my main selling point: 1st company was a manufacturer with private instructions/manuals on how to operate certain systems. I trained GPT on them and let their employees talk with these 100-page PDFs. (When I say “train”, I refer to RAG, not fine-tune) 2nd company had customers sending them photos of sensitive documents for a customs clearing service. They had people manually extracting the info so we automated all of that. How did I ensure data privacy and security? I simply used MS Azure AI. They have all of the same stuff OpenAI has, but offer data privacy guarantees and network isolation. That’s both SOC 2 and GDPR compliant. Companies love it. Now I’m cold emailing my first 2 clients’ competitors for a quick rinse and repeat. P.S. I’m extremely curious of different use cases since I’m looking to niche down, so I’d be happy to talk to businesses with ideas of how to use this. You’d give me a use case idea and I’d give you advice on how to implement it. Edit: I’m getting TONS of DMs so please be comprehensive in your first message!

I just sold my startup for $200,000 after 11 months. AMA

Last August, I was looking for a startup idea I could grow and made a MVP in a week then launched it. I received the $200,000 wire from the buyer a couple of days ago I found tons of useful info online for free, so I hope this can be my way of giving back :) Here is some background: Idea I got the idea when trying to write a tweet using Google Doc's transcription tool, which was terrible. I was pretty sure I wasn't the only one too lazy to type, I made my own solution using AI to transcribe and reformat voice notes into any kind of content. I called it Talknotes, mainly because it was the only domain available lol Validation: My rule is to only reinvest what the project generates. After listing on startup directories and posting on Twitter, I generated $700 in 10 days. It wasn't much, but enough to show interest and keep me motivated. I added user-requested features, but the launch effect wore off, and daily revenues dropped to $0 after a few weeks. I almost gave up, but friends encouraged me to continue. In October, I launched on ProductHunt and it blew up. It became Product of the Day and reached $1500 MRR thanks to media coverage. I initially built everything using vanilla JS/CSS/HTML + Node for backend. But it's pretty limited for apps with lots of interactivity so, I rebuilt the app using Nuxt.js to make it easier to ship new features. Then, I launched ads on Facebook and I implemented a feedback loop: Get new users Learn about them through onboarding Make more ads based on onboarding data This doubled MRR in about 2 months. Burnout and Sale: In May, I had a bad burnout after emergency bug fixes. This made it hard to work on the app after. At this point MRR was around $7000 and total revenues around $70,0000 I listed it on Acquire.com for $200,000, a very good price for the buyer considering revenues and growth. I could've gotten $300,000 with buyer financing or earn-outs, but I wanted cash, $200,000 today is better than $300,000 in a year. Everything was smooth until we tried using Escrow, which almost fucked up the deal (details here). Long story short, had to threaten them to make a sponsored post on Twitter explaining what they did + legal action. They sent the refund the very next day, and we completed the transfer directly. Now, this isn't an overnight success. It's the result of 7 years of grind. I launched over 40 projects since I started, and most of them failed. I often worked 100 hours per week, and I rarely go out or meet many people. It's not for everyone, but I'm fine with it With the profit from the app + sale, and other projects, I have close to 1/3 of a million dollar. I could retire in Asia if I wanted Just mind blowing to think I wrote funny characters in a code editor and sold it for the price of a house lol Edit 1: A few people got confused. I said it's 7 years of grind and most of my projects failed, not that I was not making money. I also said I OFTEN worked 100h/week, not every week :) Since I learned to code 2 years ago I've made close to $400k from my app's profit + exit (this one + another one for $65k last year). And before that I was making money as a marketing freelancer. Also, I dropped after high-school, so, I had to learn everything from scratch, it takes time! Edit 2: Lots of people asked how/where I learned to code in 2 months. I wrote a blog/journal about it back then with links to resources, you can find it here if you're interested

26 Ways to Make Money as a Startup Founder (for coders & noncoders)

I've launched 24 projects (here is the proof johnrush.me). None of my projects is making millions a month, but many of them make over $1k a month, some do over $10k, and few do even more. I'd not recommend anyone to start by trying to build a unicorn. Better start simple. Aim for $2-4k a month first. Once you get there, either scale it or start a new project with large TAM. From my own experience, the 26 Ways to Make Money as a Startup Founder: One-Feature SaaS. Extract a feature from a popular tool and build a micro SaaS around it. Idea: A SaaS that only offers automated email follow-ups. Launchpads. Develop a launch platform for a specific industry. Idea: A launchpad for growth tools. SEO Tools. Create a tool that focuses on a single aspect of SEO. Idea: A tool that generates alt texts for images. Productized Services. Offer standardized services that are repeatable. Idea: design, coding or social media management. Marketplace Platforms. Create a platform that connects buyers and sellers, earning transaction fees. Idea: An online marketplace for domains. Membership Sites. A subscription-based site with exclusive content. Idea: A founder 0-to-1 site. White Labeling. A product that other businesses can rebrand as their own. Idea: A white-labeled website builder. Selling Data. Provide anonymized data insights to companies. Idea: Selling user behavior data. Affiliate Marketing. Promote products/services and earn commissions on sales. Idea: Recommending hosting services on a tech blog. Selling Leads. Generate and sell business leads. Idea: Selling leads who raised a fresh seed round. Niche Social Networks. Create a paid community around a specific interest. Idea: A network for SEO experts. Sell Domains. Buy and sell domain names for profit. Virtual Products. Sell digital products like templates or graphics. Idea: Website themes for nextjs or boilerplates. On-Demand Services. Build a platform for gigs like delivery or tutoring. Idea: An app for freelance tutors. Niche Job Boards. Start a job board focused on a specific industry. Idea: A job board for remote tech jobs. Crowdsourced Content. Create a user-generated content platform and monetize through ads. Idea: Site to share startup hacks. Buy and Flip Businesses. Purchase underperforming businesses, improve them, and sell for profit. Idea: Acquiring a low-traffic blog, optimizing it, and selling. AI-Powered agents. Develop AI tools that solve specific business problems. Idea: An AI tool that automates customer support. Microservices. Offer small, specialized tools, sdks or APIs. Idea: An api for currency conversion. Influencer Platforms. Create a platform connecting influencers with brands. Idea: Connect AI influencers with AI founders. Niche Directories. Build a paid directory for a specific industry. Idea: A directory of developers who can train models. E-Learning Platforms. Build a platform for educators to sell courses. Idea: A site where AI experts sell AI courses. Virtual assistants. Hire them and sell on subscription. No-Code Tools. Create tools that allow non-technical users to build things. Idea: A no-code website builder for bakeries. Labor arbitrage. Idea: Connect support agents from Portugal with US clients and charge commission.

Unmasking Fake Testimonials on a YC backed company

As developers, marketeers and builders, we often rely on trusted platforms to guide us in finding tools that meet our unique needs. Recently, I stumbled upon Overlap, a site marketed as a haven for collaboration tools. Its sleek interface and glowing testimonials initially convinced me I had found a gem. But as I dug deeper, I uncovered a jaw-dropping reality: their testimonials featured stock images, all of which were easily identified through a quick reverse image search. Even more shocking was the realization that Overlap is a Y Combinator-backed company—an organization renowned for nurturing some of the most innovative startups in the world. With significant funding at their disposal, the decision to cut corners with fake testimonials felt like a slap in the face to their user base. They could easily afford a robust testimonial platform, yet chose a path that undermined their credibility. As developers, marketeers and builders, we often rely on trusted platforms to guide us in finding tools that meet our unique needs. Recently, I stumbled upon Overlap, a site marketed as a haven for video AI tools. Its sleek interface and glowing testimonials initially convinced me I had found a gem. But as I dug deeper, I uncovered a jaw-dropping reality: their testimonials featured stock images, all of which were easily identified through a quick reverse image search. Even more shocking was the realization that Overlap is a Y Combinator-backed company—an organization renowned for nurturing some of the most innovative startups in the world. With significant funding at their disposal, the decision to cut corners with fake testimonials felt like a slap in the face to their user base. They could easily afford a robust testimonial platform, yet chose a path that undermined their credibility. A screenshot of Overlap's landing page https://preview.redd.it/zosmdl0v01ce1.png?width=1000&format=png&auto=webp&s=83ced4af92ca284486281f00b020f1f0114b4fcd This discovery was nothing short of a wake-up call. For a developer-focused website—an audience that prizes authenticity and technical precision above all else—faking testimonials with stock photos isn’t just misleading, it’s a catastrophic betrayal of trust. It left me questioning the integrity of their entire operation and serves as a stark reminder for businesses everywhere: your audience notices when you’re not authentic, and they won’t forgive it easily. Position of Fake Testimonials One of the stock images https://preview.redd.it/a7ugasrw01ce1.png?width=341&format=png&auto=webp&s=5261df741f1198a92e537f1e61640e7d6ec60a7f Lessons for Startup Founders and Developers This experience offers several critical lessons for startup founders and developers alike: Authenticity is Non-Negotiable: In a competitive market, trust and transparency can make or break your brand. Fake testimonials might provide a short-term boost, but the long-term damage to credibility far outweighs any temporary gains. Invest in Genuine Solutions: If you have the resources, like a Y Combinator-backed company, prioritize tools and practices that enhance authenticity. Platforms like RapidFeedback allow businesses to dynamically update reviews and manage feedback efficiently. Leverage Real User Feedback: Authentic testimonials not only build trust but also provide actionable insights into your product’s strengths and weaknesses. This feedback loop can be invaluable for refining and growing your business. Understand Your Audience: Developers value precision, integrity, and honesty. Catering to this audience requires a commitment to these principles in every aspect of your business. Let’s ensure that the tools we build and the businesses we run prioritize authenticity. In the long run, a commitment to transparency and user trust will always yield greater rewards than any shortcut could provide. Why Fake Testimonials Are a Problem Fake testimonials damage your brand in more ways than one: Loss of Credibility: Developers are a discerning audience. Trust is everything, and losing it can be catastrophic for your reputation. Hurt User Experience: Knowing a platform misrepresents itself makes users skeptical about its features and promises. Missed Opportunities: Genuine feedback can provide valuable insights for growth and improvement, which fake testimonials completely overlook. A Smarter Way: Authentic Testimonials with RapidFeedback This experience reminded me of why tools like RapidFeedback are invaluable. RapidFeedback helps businesses maintain authenticity by dynamically updating reviews and images in real time. Here’s why it stands out: Real-Time Updates: Reviews are fetched and displayed dynamically, ensuring they’re always up-to-date. Dashboard Management: Businesses can monitor and manage good vs. bad reviews from a centralized dashboard, enabling them to address concerns promptly. Authenticity Guaranteed: Dynamic updates ensure that testimonials reflect real users and their experiences, which builds trust and credibility. Lessons for Developers and Businesses If there’s one takeaway from my Overlap experience, it’s this: authenticity isn’t optional. Whether you’re building tools for developers or selling consumer products, your audience values transparency. Using tools like RapidFeedback ensures your business maintains trust while gaining actionable insights to grow. Let’s commit to prioritizing honesty in our work. Because in the end, authentic relationships with users are what truly drive success.

Switching Gears: Implementing AI for My Agency’s Marketing After a Decade

Hi there, I’ve been running a software development and design agency for the last 10 years, mainly focusing on building custom solutions for businesses and SaaS. For the last 2 years, I’ve consistently recommended that clients use AI technologies, especially for social media and content creation to generate traffic. Funny enough, I wasn’t practicing what I preached. Most of my client projects came from platforms like Upwork and word-of-mouth referrals from clients or people from networking events. Background I started my journey in 2014, switching from an employee to a freelancer. Within the first 10 months, my initial projects grew beyond what I could handle alone, prompting me to hire additional developers. This shift turned my role from a full-stack developer to a team lead and developer. Over the years, my focus has been a blend of tech and product. About five years ago, I realized the importance of design, leading me to adding designers to the agency to provide full-cycle service development—from product ideation and design to development, testing, launch, and support. I still continue to set up dedicated teams for some clients, maintaining a strong technical role as a tech lead, solution architect, and head product designer. To enhance my skills, I even completed UI/UX design courses to offer better product solutions. Despite these changes, building products has always been the easy part. The challenge was ensuring these client products didn’t end up in the graveyard due to poor product-market fit, often caused by inadequate marketing and sales strategies but more often just absence of them. (we are talking about startup and first time founders here 🙂 ) My Journey and Observations Advising Clients: I often found myself advising clients on increasing traffic for their SaaS products and crafting strategic marketing plans. Learning: I’ve gained most of my knowledge from consuming internet materials, courses, and blog posts and learning from successful client project launches. Realization: Despite giving this advice, I wasn’t applying these strategies to my own business, leading to low visits to my agency’s website. Initial Solution: Hiring a Marketer Hiring: I brought in a marketer with a solid background in content creating and interview video editing from an educational organization. Goal: The aim was to increase website visits through a comprehensive marketing strategy. Outcome: Although the content produced was high-quality and useful for pitching services, it didn’t lead to significant traffic increases. Issue: The marketer focused more on content creation rather than distribution channels, which limited effectiveness. Shift to AI-Driven Strategy Experiment: I decided to try using AI for content creation and distribution, which aligns with my agency’s specialization in design-driven development and AI integrations. Implementation plan: I will be generating all content with minimal edits using AI and implementing a strategic backlinking approach. Backlinking Strategy Initial Plan: I initially thought of hiring a specialist for backlinks. Realization: The costs and profiles of freelancers didn’t seem promising. Solution: I found AI-driven services for backlinks, which seem more efficient and cost-effective. Plan: My plan is to use these tools for programmatic SEO-driven AI-generated articles and third-party backlinking services over the next two to three months. Current Approach Management: This approach can be managed and executed by 1 person and monitored weekly, reducing human error and optimizing efficiency. I will start it myself and then replace myself with an editor with managing skills. Reflection: It’s a bit ironic and funny that it took me 10 years to start implementing these strategies in my own agency business, but I now feel more confident with AI and automation in place. Why Increase Website Visitors? You might ask, why do I want to increase the number of visitors to the site, and how can I ensure these visitors will be qualified? Hands-On Experience: To gain hands-on experience and perform this exercise effectively. Introduce Packaged Services: I want to introduce a set of low-cost packaged services tailored for non-technical people who want to build things for themselves - the DIY kits for non-technical folks. These services will provide a foundational template for them to build upon on top of existing established solutions such as Wix, Square Why am I Posting and Sharing Here? You might also wonder, why am I posting it here and sharing this? Well, I'm doing this more for myself. Most of my career, the things I’ve done have been behind the curtains. With this small project, I want to make it public to see the reaction of the community. Perhaps there will be good and smart suggestions offered, and maybe some insights or highlights of tools I wasn’t aware of or didn’t consider. I’ll keep sharing updates on this journey of website promotion, marketing, and SEO. My current goal is to reach 2,000 visits per month, which is a modest start. Looking forward to any thoughts or advice from this community! Disclaimer: This content was not generated by AI, but it was edited by it 😛

New Entrepreneur Looking to Learn

Hi all, long-time lurker, and first-time poster. About six weeks ago, I left my full-time career in tech to dive headfirst into launching an AI-focused startup. It’s my first time as a founder (well, co-founder), and the journey already feels exhilarating and terrifying at the same time! I’ve got a tech team onboard, and we are starting to build out our platform. To make sure I'm building the right thing, it's a top priority for me to connect with our target audience of small business owners for discovery conversations. I’m eager to learn about: How (and if) you’re currently using AI in your business. What kind of value/impact does AI need to deliver for you to be willing to use it in your business. What challenges or blockers do you perceive around implementing AI solutions. I’m open to speaking with US-based business owners with companies ranging from 5-50 employees or so, and am particularly interested if you are non-technical. If you’re willing to share your experience, I’d love to chat for 15-30 minutes. Feel free to comment here or DM me if you’re interested—your insights (and trolling) would mean the world as I navigate this journey. Thanks in advance! P.S. - I know I'm being a little cagey about the details of what my start-up is doing. While I don't think we have the most innovative idea in the world, I'd prefer to hold off on posting details publicly. This isn't a backdoor sales call, I'm just looking to ask questions and learn.

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Uzair Javaid, a Ph.D. with a passion for data privacy, co-founded Betterdata to tackle one of AI's most pressing challenges: protecting privacy while enabling innovation. Recently, Betterdata secured a lucrative contract with the US Department of Homeland Security, 1 of only 4 companies worldwide to do so and the only one in Asia. Here's how he did it: The Story So what's your story? I grew up in Peshawar, Pakistan, excelling in coding despite studying electrical engineering. Inspired by my professors, I set my sights on studying abroad and eventually earned a Ph.D. scholarship at NUS Singapore, specializing in data security and privacy. During my research, I ethically hacked Ethereum and published 15 papers—three times the requirement. While wrapping up my Ph.D., I explored startup ideas and joined Entrepreneur First, where I met Kevin Yee. With his expertise in generative models and mine in privacy, we founded Betterdata. Now, nearly three years in, we’ve secured a major contract with the U.S. Department of Homeland Security—one of only four companies globally and the only one from Asia. The Startup In a nutshell, what does your startup do? Betterdata is a startup that uses AI and synthetic data generation to address two major challenges: data privacy and the scarcity of high-quality data for training AI models. By leveraging generative models and privacy-enhancing technologies, Betterdata enables businesses, such as banks, to use customer data without breaching privacy regulations. The platform trains AI on real data, learns its patterns, and generates synthetic data that mimics the real thing without containing any personal or sensitive information. This allows companies to innovate and develop AI solutions safely and ethically, all while tackling the growing need for diverse, high-quality data in AI development. How did you conduct ideation and validation for your startup? The initial idea for Betterdata came from personal experience. During my Ph.D., I ethically hacked Ethereum’s blockchain, exposing flaws in encryption-based data sharing. This led me to explore AI-driven deep synthesis technology—similar to deepfakes but for structured data privacy. With GDPR impacting 28M+ businesses, I saw a massive opportunity to help enterprises securely share data while staying compliant. To validate the idea, I spoke to 50 potential customers—a number that strikes the right balance. Some say 100, but that’s impractical for early-stage founders. At 50, patterns emerge: if 3 out of 10 mention the same problem, and this repeats across 50, you have 10–15 strong signals, making it a solid foundation for an MVP. Instead of outbound sales, which I dislike, we used three key methods: Account-Based Marketing (ABM)—targeting technically savvy users with solutions for niche problems, like scaling synthetic data for banks. Targeted Content Marketing—regular customer conversations shaped our thought leadership and outreach. Raising Awareness Through Partnerships—collaborating with NUS, Singapore’s PDPC, and Plug and Play to build credibility and educate the market. These strategies attracted serious customers willing to pay, guiding Betterdata’s product development and market fit. How did you approach the initial building and ongoing product development? In the early stages, we built synthetic data generation algorithms and a basic UI for proof-of-concept, using open-source datasets to engage with banks. We quickly learned that banks wouldn't share actual customer data due to privacy concerns, so we had to conduct on-site installations and gather feedback to refine our MVP. Through continuous consultation with customers, we discovered real enterprise data posed challenges, such as missing values, which led us to adapt our prototype accordingly. This iterative approach of listening to customer feedback and observing their usage allowed us to improve our product, enhance UX, and address unmet needs while building trust and loyalty. Working closely with our customers also gives us a data advantage. Our solution’s effectiveness depends on customer data, which we can't fully access, but bridging this knowledge gap gives us a competitive edge. The more customers we test on, the more our algorithms adapt to diverse use cases, making it harder for competitors to replicate our insights. My approach to iteration is simple: focus solely on customer feedback and ignore external noise like trends or advice. The key question for the team is: which customer is asking for this feature or solution? As long as there's a clear answer, we move forward. External influences, such as AI hype, often bring more confusion than clarity. True long-term success comes from solving real customer problems, not chasing trends. Customers may not always know exactly what they want, but they understand their problems. Our job is to identify these problems and solve them in innovative ways. While customers may suggest specific features, we stay focused on solving the core issue rather than just fulfilling their exact requests. The idea aligns with the quote often attributed to Henry Ford: "If I asked people what they wanted, they would have said faster horses." The key is understanding their problems, not just taking requests at face value. How do you assess product-market fit? To assess product-market fit, we track two key metrics: Customers' Willingness to Pay: We measure both the quantity and quality of meetings with potential customers. A high number of meetings with key decision-makers signals genuine interest. At Betterdata, we focused on getting meetings with people in banks and large enterprises to gauge our product's resonance with the target market. How Much Customers Are Willing to Pay: We monitor the price customers are willing to pay, especially in the early stages. For us, large enterprises, like banks, were willing to pay a premium for our synthetic data platform due to the growing need for privacy tech. This feedback guided our product refinement and scaling strategy. By focusing on these metrics, we refined our product and positioned it for scaling. What is your business model? We employ a structured, phase-driven approach for out business model, as a B2B startup. I initially struggled with focusing on the core value proposition in sales, often becoming overly educational. Eventually, we developed a product roadmap with models that allowed us to match customer needs to specific offerings and justify our pricing. Our pricing structure includes project-based pilots and annual contracts for successful deployments. At Betterdata, our customer engagement unfolds across three phases: Phase 1: Trial and Benchmarking \- We start with outreach and use open-source datasets to showcase results, offering customers a trial period to evaluate the solution. Phase 2: Pilot or PoC \- After positive trial results, we conduct a PoC or pilot using the customer’s private data, with the understanding that successful pilots lead to an annual contract. Phase 3: Multi-Year Contracts \- Following a successful pilot, we transition to long-term commercial contracts, focusing on multi-year agreements to ensure stability and ongoing partnerships. How do you do marketing for your brand? We take a non-conventional approach to marketing, focusing on answering one key question: Which customers are willing to pay, and how much? This drives our messaging to show how our solution meets their needs. Our strategy centers around two main components: Building a network of lead magnets \- These are influential figures like senior advisors, thought leaders, and strategic partners. Engaging with institutions like IMDA, SUTD, and investors like Plug and Play helps us gain access to the right people and foster warm introductions, which shorten our sales cycle and ensure we’re reaching the right audience. Thought leadership \- We build our brand through customer traction, technology evidence, and regulatory guidelines. This helps us establish credibility in the market and position ourselves as trusted leaders in our field. This holistic approach has enabled us to navigate diverse market conditions in Asia and grow our B2B relationships. By focusing on these areas, we drive business growth and establish strong trust with stakeholders. What's your advice for fundraising? Here are my key takeaways for other founders when it comes to fundraising: Fundraise When You Don’t Need To We closed our seed round in April 2023, a time when we weren't actively raising. Founders should always be in fundraising mode, even when they're not immediately in need of capital. Don’t wait until you have only a few months of runway left. Keep the pipeline open and build relationships. When the timing is right, execution becomes much easier. For us, our investment came through a combination of referrals and inbound interest. Even our lead investor initially rejected us, but after re-engaging, things eventually fell into place. It’s crucial to stay humble, treat everyone with respect, and maintain those relationships for when the time is right. Be Mindful of How You Present Information When fundraising, how you present information matters a lot. We created a comprehensive, easily digestible investment memo, hosted on Notion, which included everything an investor might need—problem, solution, market, team, risks, opportunities, and data. The goal was for investors to be able to get the full picture within 30 minutes without chasing down extra details. We also focused on making our financial model clear and meaningful, even though a 5-year forecast might be overkill at the seed stage. The key was clarity and conciseness, and making it as easy as possible for investors to understand the opportunity. I learned that brevity and simplicity are often the best ways to make a memorable impact. For the pitch itself, keep it simple and focus on 4 things: problem, solution, team, and market. If you can summarize each of these clearly and concisely, you’ll have a compelling pitch. Later on, you can expand into market segments, traction, and other metrics, but for seed-stage, focus on those four areas, and make sure you’re strong in at least three of them. If you do, you'll have a compelling case. How do you run things day-to-day? i.e what's your operational workflow and team structure? Here's an overview of our team structure and process: Internally: Our team is divided into two main areas: backend (internal team) and frontend (market-facing team). There's no formal hierarchy within the backend team. We all operate as equals, defining our goals based on what needs to be developed, assigning tasks, and meeting weekly to share updates and review progress. The focus is on full ownership of tasks and accountability for getting things done. I also contribute to product development, identifying challenges and clearing obstacles to help the team move forward. Backend Team: We approach tasks based on the scope defined by customers, with no blame or hierarchy. It's like a sports team—sometimes someone excels, and other times they struggle, but we support each other and move forward together. Everyone has the creative freedom to work in the way that suits them best, but we establish regular meetings and check-ins to ensure alignment and progress. Frontend Team: For the market-facing side, we implement a hierarchy because the market expects this structure. If I present myself as "CEO," it signals authority and credibility. This distinction affects how we communicate with the market and how we build our brand. The frontend team is split into four main areas: Business Product (Software Engineering) Machine Learning Engineering R&D The C-suite sits at the top, followed by team leads, and then the executors. We distill market expectations into actionable tasks, ensuring that everyone is clear on their role and responsibilities. Process: We start by receiving market expectations and defining tasks based on them. Tasks are assigned to relevant teams, and execution happens with no communication barriers between team members. This ensures seamless collaboration and focused execution. The main goal is always effectiveness—getting things done efficiently while maintaining flexibility in how individuals approach their work. In both teams, there's an emphasis on accountability, collaboration, and clear communication, but the structure varies according to the nature of the work and external expectations.

10 Side Projects in 10 Years: Lessons from Failures and a $700 Exit

Hey folks, I'm sharing my journey so far in case it can help others. Entrepreneurship can sometimes be demotivating. In my case, I've always been involved in side projects and what I've realized is that every time you crash a project, the next one makes it a bit further. So this is a long-term game and consistency ends up paying off The $1 Android Game (2015, age 18) What Happened: 500 downloads, 1€ in ad revenue Ugly UI, performance issues Key Lessons: Don’t be afraid of launching. Delaying for “perfection” is often a sign that you fear being ignored. I was trying to perfect every aspect of the game. In reality, I was delaying the launch because I feared no one would download the app. Commit to the project or kill it. At some point, this project was no longer fun (it was just about fixing device responsiveness). Most importantly, I wasn't learning anything new so I moved to smth else. The Forex Bot Regret (2016, age 19) What Happened: Lost months identifying inexistent chart patterns Created a Trading bot that was never profitable Key Lessons: Day trading’s real winners are usually brokers. There are plenty of guys selling a bot or systems that are not making money trading, why would they sell a “money-printing machine” otherwise... Develop an unfair advantage. With these projects, I developed a strong coding foundation that gave me an edge when dealing with non-technical business people. Invest countless hours to create a skills gap between you and others, one that becomes increasingly difficult for them to close (coding, public speaking, networking, etc.) The $700 Instagram Exit (2018, age 21) What Happened: Grew a motivational account to 60k followers Sold it for $700 90% of followers were in low-income countries (hard to monetize) Key Lessons: Follower quality > quantity. I focused on growth and ended up with an audience I couldn’t truly define. If brands don’t see value, you won’t generate revenue. Also, if you do not know who you are creating content for, you'll end up demotivated and stop posting. Great 3rd party product + domain authority = Affiliate marketing works. In this case, I could easily promote an IG growing service because my 50k+ followers conveyed trust. Most importantly, the service I was promoting worked amazingly. The Illegal Amazon Review Marketplace (2020, age 23) What Happened: Sellers were reimbursing buyers for positive reviews Built a WordPress marketplace to facilitate “free products for reviews” Realized it violated Amazon’s terms Key Lessons: Check for “red flags” when doing idea assessment. There will always be red and orange flags. It’s about learning to differentiate between them (e.g. illegality, 100% dependence on a platform, etc.) If there’s competition, it’s good, if they are making money it’s even better. I was thrilled when I saw no competition for my “unique idea”. Later, I discovered the obvious reason. Copying a “Proven” Business Model (2020, age 23) What Happened: Tried recreating an Instagram “comment for comment” growth tool Instagram changed the algorithm and killed the growth strategy that the product used. Key Lessons: Do not build a business that depends 100% on another business, it is too risky. Mr. Musk can increase Twitter on API pricing to $42,000 monthly without notice and Tik Tok can be banned in the US. Due to the IG algorithm change, we had built a product that was not useful, and worse, now we had no idea how to grow an IG account. Consider future project synergies before selling. I regret having sold the 60k follower IG account since it could have saved me a lot of time when convincing users to try the service. NFT Marathon Medals (2021, age 24) What Happened: Created NFT race medals Sold 20 for 5€ each, but spent 95% of meetings explaining “what is an NFT?” Key Lessons: Market timing is crucial. As with every new technology, it is only useful as long as society is ready to adopt it. No matter how promising the tech is in the eyes of SV, society will end up dictating its success (blockchain, AI, etc). In this case, the runner community was not ready to adopt blockchain (it is not even prepared today). Race organizers did not know what they were selling, and runners did not know what they were buying. The 30-day rule in Fanatical Prospecting. Do not stop prospecting. I did prospecting and closed deals 3 months after the outbound efforts. Then I was busy executing the projects and had no clients once the projects were finished. AI Portal & Co-Founder Misalignment (2023, age 26) What Happened: Built a portal for SMEs to find AI use cases Co-founders disagreed on vision and execution Platform still gets \~1 new user/day Key Lessons: Define roles and equity clearly. Our biggest strength ended up killing us. Both founders had strong strategic skills and we were constantly arguing about decisions. NextJS + Vercel + Supabase: Great stack to create a SaaS MVP. (but do not use AI with frameworks unless you know how they work conceptually) SEO is king. One of our users creates a use case on “Changing Song Lyrics with AI.” Not being our target use case, it brings 90% of our traffic. Building an AI Tool & Getting Ghosted (2024, age 27) What Happened: SEO agency wanted to automate rewriting product descriptions Built it in 3 weeks, but the client vanished Key Lessons: Validate manually first. Don’t code a full-blown solution for a problem you haven’t tested in real-world workflows. I kept rewriting code only to throw it away. Jumping straight into building a solution ended up costing more time than it saved. Use templates, no-code, and open-source for prototyping. In my case, using a Next.js template saved me about four weeks of development only to hit the same dead end, but much faster. Fall in love with your ICP or walk away. I realized I didn’t enjoy working with SEO agencies. Looking back, I should have been honest with myself and admitted that I wasn’t motivated enough by this type of customer. Ignoring Code Perfection Doubled Traffic (2025, age 28) What Happened: Partnered with an ex-colleague to build an AI agents directory Focused on content & marketing, not endless bug fixes Traffic soared organically Key Lessons: Measure the impact of your actions and double down on what works. We set up an analytics system with PostHog and found wild imbalances (e.g. 1 post about frameworks outperformed 20 promotional posts). You have to start somewhere. For us, the AI agents directory is much more than just a standalone site, it's a strategic project that will allow us to discover new products, gain domain authority, and boost other projects. It builds the path for bigger opportunities. Less coding, more traction. Every day I have to fight against myself not to code “indispensable features”. Surprisingly, the directory keeps gaining consistent traffic despite being far from perfect Quitting My Job & Looking Ahead (2025, age 28) What Happened: Left full-time work to go all-in Plan to build vertical AI agents that handle entire business workflows (support, marketing, sales) Key Lessons: Bet on yourself. The opportunity cost of staying in my full-time job outweighed the benefits. It might be your case too I hope this post helps anyone struggling with their project and inspires those considering quitting their full-time job to take the leap with confidence.

Why the value of writing code and other digital services is going to zero

I must preface this with a trigger warning because I make some statements in this post that might be upsetting to some. This post discusses my experience building in the new era of entrepreneurship, which is one where the founder is the center of the universe, and the consultants, overpriced SaaS, and corporate swamp creatures are replaced by single-user custom software, bots, and self-hosted automations. If you work in the legacy economy, I really don't intend to stress you out or say things you are doing are quickly becoming irrelevant, but I must share the reality of how I am operating, because I would like to hear from others who are doing the same, or desire to do the same. I am currently operating with the belief that AI-powered tools are going to make 1-person million dollar businesses much more common. Building anything digital is becoming extremely easy, cheap, and quick to implement. The value of code and digital tools is approaching zero, or at most 5% of what it currently is. Right now, the most powerful AI tools are aimed at developers, so folks who have some technical and business ability basically have nothing holding them back aside from the speed of their brain right now. I happen to be a part of the cohort, and am building like there is no tomorrow, but I don't believe this cohort is actually all that big. The next hurdle to unlock the new era of entrepreneurship is empowering every entrepreneur to build at the same pace that is currently locked behind having technical ability. This cohort is huge (millions, if the number of people in this sub is any indication). This post is aimed at them (you?). If you are part of this cohort, what is holding you back from launching a new product for near-zero cost? What is too complicated, too expensive, too unknown for you to be able to build your new/current business at maximum speed? I look forward to seeing the replies, I hope some insights shared can help the community, and be a catalyst for more tools to enable non-technical founders to launch. I will now share some of how I am testing, launching, and selling as a one-man-show. This will be a little bit technical, but if the output of any layer of my stack is something you want, please comment because maybe someone will build a cheap way of accessing it without needing to manage the code yourself. \#1 BOTS I cannot overstate how much leverage bots have created for me. I run all of my bots locally and interface with with via Telegram. Bots do things like: \- watch social media pages, forums, subreddits, etc related to my customers and notify me of what is going on, and suggest SEO blog posts that could be published to capture traffic related to the topic. with a single message, my bot will generate a blog post, send it to me for review, apply edits i suggest, and then publish it live, all from within telegram \- pay attention to all my key metrics/analytics, and attempt to find insights/corrolations (ex. there is a lot of traffic on this page, blog post, video, etc. here's why, and how we can take advantage of it to drive business goals) \- repurposing content. i have dozens of social media profiles that are 100% run by bots, they are all related to my customer niches and will do things like post news, snippets from my blogs, interact with human creators in the niche, etc. this builds my audience automatically which I can then advertise to/try to convert into paying customers, since they are interested in the things my bot is posting and become followers, it's like automated qualified lead gen 24/7 across every social platform and every niche I care about. you may be thinking by now that this post is made by a bot, but you will have to trust me that this is 100% hand-written by my sleep-deprived brain. let's continue: \#2 replacing every SaaS with a shitty version of it designed for what i need out of it it's absurd that we pay ten's of dollars per seat per month for basic digital functions like chat (slack), CRM (active camppaign, sales force, hubspot, etc), email stuff (mailchip, etc), link sharing (linktree, etc), website builders (wix, squarespace, etc), etc. all of these SaaS tools are overpriced and overbuilt. I believe many of them are going to be caught in the innovators dilemma and will go to 0. I don't use any of these anymore, I build and self-host my own shitty version of each of them that does only what i need out of the tool. for example, my CRM doesn't have a fancy drag and drop email builder and 10000 3rd party plugins, because i dont need any of that shit I just need to segment and communicate with my customers. if i need more features, i can generate them on the fly. \#3 working alone I have worked with cofounders in the past, raised money from investors, hired consultants, burned money and time, suffered sleepless nights from stress caused by other people not delivering, trying to convince others they are wrong, or they are pushing the company off a cliff, waste waste waste. no more of that. In the new age of entrepreneurship, the BUILDER (you and I) are the ones creating the value, and AI empowers us to do it alone. this might seem daunting, but there is no business problem that can't be solved with a detailed discussion sesh with chatgpt, no facts that can't be found with perplexity, and no task that can't be automated with claude. there is no need for anymore swamp creatures. you are the start and the end point, you don't need to rely on anyone else for anything. this may sound ignorant, but this is the conclusion I have come to believe, and it continues to be proven every day my businesses progress with me being the only human involved. This is getting quite long so I'll cut it here. I look forward to hearing about how you are operating in this new era and hopefully getting inspired/learning some new ideas to add to my current stack.

101 best SEO tips to help you drive traffic in 2k21