Feel

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 started a Tech Startup, and I feel totally STUCK.

I made "Visual Love," a Computer Vision/AI-driven matchmaking platform. The idea is that although appearance is one of the biggest factors for starting a relationship, current matchmaking services and dating apps do not have the capability to search for people based on appearance. On Visual Love, you can find your ideal match simply by uploading a picture of your "ideal type." Also, you can connect with someone who thinks of you as their ideal type, simply by uploading your own picture. Or, there might be a perfect (mutually ideal) match. I made this CV/AI algorithm to scan faces, retrieve facial features, and make it possible to find the closest match among millions of others in a second. On average, regular dating app users swipe 8000 times over 8 months until they find their love. On Visual Love, users can find one in a million just in a second. You can try the tech demo on the website if you want to (find the link through my LinkedIn at the bottom of the post; I have to follow the "I will not promote" rule.) I thought this app would have the best chance in Asia, as people care a lot more about appearance in Asia (especially Korea and Japan). Also, my nationality is Korean, and I speak both Korean and Japanese as fluently as I speak English. So I came to Korea, and pitched to a number of VC/AC firms in Korea and Japan, and two of them were typically intersted in making investment. However, they both required me to provide market validation: how much it would cost per user acquisition, how much each user would pay on average, and etc, even after I provided them with a 3-years financial projection including market research based on other dating apps. ​ Everything might be going just as expected, or even better than anticipated, but I'm feeling very stuck now. I am not a business expert, and I don't have much idea on how to proceed from here. The problem is, it wouldn't quite work as expected when there are not many users. If I start with a small group of users, it's not any better than any other dating app. Matching users within a small group doesn't quite reflect the values of Visual Love. So I figured a way around: making a game version of Visual Love targeting 100k to 500k users to work as an initial distribution channel. This version will include finding look-alike celebrities, and solving look-alike face puzzles, and etc. But now, the problem is, I cannot continue this project by myself. I have no social/financial support, and I'm running low on cash. Also, although I'm from Korea, I lived in many different countries. I did my undergraduate in New York (Columbia University) and all my friends are in the US. I don't feel very included here. I can't stop feeling frustrated and distressed :( I'm sure Visual Love can reshape the future of the matchmaking market. But, only if I can continue this project by getting the fund I require. I'm open to any advice, and if you're interested in providing any help or working with me, please contact me through LinkedIn. https://www.linkedin.com/in/don-lee-3853b1264/

I Built a Startup at 18, Shut It Down at 21, and Now I Feel Lost at 22 - What Should I Do?

Here’s My Story: At 18, during my first year of studying computer engineering, I founded my first tech startup. For three years, I wore every hat, programming, marketing, sales, design, HR, product management, and even handling finances. It was a crash course in business and tech, and I learned more than I ever thought possible. By the time I shut it down in 2023, we had 8,000 app downloads, lots of positive feedback, and promising metrics. But despite the progress, I had to let it go (there might be a possibility of launching it again since I didn't shut it because it was a failure). Now at 22, I’m Lost. I’ve realized how much I want to master everything related to business and tech, but I feel scattered. When I tried creating content on LinkedIn, I wrote posts about AI, programming, HR, funding, and product management, and I have more drafts waiting. One day I want to start another startup. The next, I dream of becoming an AI product manager or just finding a stable job. With graduation coming next summer, I’m struggling to focus and figure out which path to take. I Need Your Advice. If you’ve been through something similar or have guidance for someone at this crossroads, I’d love to hear your thoughts. How do I find clarity and decide which direction to pursue? 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

Every time I walk into a big store, I feel like it’s still 2010. Time for AI to change Retail?

The staff are often busy talking to each other or looking at their phones. It feels like they don’t really care about helping customers. And trying to find something on the shelves? This made me think: why is it still normal in 2025, maybe it's finally time for Retail to adopt new technologies. I want to share an idea we’ve started working on. It’s an 3D AI conversational assistant—a screen placed in the middle of the store—that could: Help customers find products in seconds. Give useful recommendations instead of saying, “Try over there.” Always be available to help, without getting tired or distracted. Me and my team have just started working on this, but we’re not sure how businesses will feel about it. It’s a big change, and it might take time for stores to see the value in something like this. And if you’re in retail, do you think businesses are ready for this kind of technology, and would you personally try this AI assistant? So, i’d love to hear what you think guys. If you work in retail, do you think stores would use something like this? https://preview.redd.it/8eicba5czcee1.png?width=1920&format=png&auto=webp&s=676d8c4f25d4ccf85f53f5da6c3ce29075bbf3ec

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.

for a LIMITED AMOUNT OF TIME, I am testing an AI that builds landing pages, describe your business in the comments or in the DMs and I will send you a figma design + code of your landing page. (feel free to pay whatever amount)

I’ve professionalized the family business. Now I feel stuck

I wrote the post below in my own words and then sent to ChatGPT for refinement/clarity. So if it reads like AI, it's because it is, but it's conveying the message from my own words a bit better than my original with a few of my own lines written back in. Hope that's not an issue here. I’m 33, married with two young kids. I have a bachelor’s from a well-regarded public university (though in an underwhelming field—economics adjacent). I used that degree to land a job at a mid-sized distribution company (\~$1B annual revenue), where I rose quickly to a project management role and performed well. In 2018, after four years there, I returned to my family's $3M/yr residential service and repair plumbing business. I saw my father withdrawing from leadership, responsibilities being handed to underqualified middle managers, and overall employee morale declining. I’d worked in the business from a young age, had all the necessary licenses, and earned a degree of respect from the team—not just as “the boss’s kid,” but as someone who had done the work. I spent my first year back in the field, knocking off the rust. From there, I started chipping away at process issues and inefficiencies, without any formal title. In 2020, I became General Manager. Since then, we’ve grown to over $5M in revenue, improved profitability, and automated many of the old pain points. The business runs much smoother and requires less day-to-day oversight from me. That said—I’m running out of motivation. I have no equity in the business. And realistically, I won’t for a long time. The family dynamic is... complicated. There are relatives collecting large salaries despite zero involvement in the business. Profits that should fuel growth get drained, and we can’t make real accountability stick because we rely too heavily on high-producing employees—even when they underperform in every other respect. I want to be clear—this isn’t a sob story. I know how lucky I am. The business supports my family, and for that I’m grateful. But I’ve gone from showing up every day with fresh ideas and energy to slowly becoming the guy who upholds the status quo. I’ve hit most of the goals I set for myself, but I’m stagnating—and that scares me. The safe move is to keep riding this out. My wife also works and has strong earning potential. We’re financially secure, and with two small kids, I’m not eager to gamble that away. But I’m too young to coast for the next decade while I wait for a possible ownership shakeup. At this point, the job isn’t mentally stimulating. One hour I’m building dynamic pricing models; the next, I’m literally dealing with whether a plumber is wiping his ass properly because I've had multiple complaints about his aroma. I enjoy the challenging, high-level work—marketing, systems, strategy—but I’m worn down by the drama, the legacy egos I can’t fire, and the petty dysfunction I’m forced to manage. I'm working on building a middle management gap, but there's something lost in not being as hands-on in a small business like this. I fear that by isolating myself from the bullshit, I'll also be isolating myself from some of the crucial day-to-day that keep us who we are. Hope that makes sense. (To be fair, most of our team is great. We have an outstanding market reputation and loyal employees—but the garbage still hits my desk when it shows up.) I’ve toyed with starting a complementary business or launching a consulting gig for similar-sized companies outside our market. I’ve taken some Udemy and Maven Analytics courses (digital marketing, advanced Excel/Power BI, etc.) to keep learning, but I rarely get to apply that knowledge here. So here I am. Is this burnout? A premature midlife crisis? A motivation slump? I’m not sure what I’m looking for—but if you’ve been here, or have any hard-earned advice, I’d be grateful to hear it.

I'm trying to create a comprehensive table of the best AI tools to Increase Your Productivity + Automate Your Work- feel free to give some recs so I can add it to the list.

Experienced Software Developer looking for startup to help. I will not promote

My passion for programming started at the age of 9 when I began playing video games. It was during this time that I first dived into programming, creating scripts for SA:MP (San Andreas Multiplayer) using the Pawn language. SA:MP is a modification for the popular game Grand Theft Auto: San Andreas, allowing players to experience multiplayer gameplay. My early experiences in programming were all about problem-solving—finding ways to enhance the game and improve the player experience. This was when I realized how satisfying it is to solve a problem through code, and that feeling has stayed with me throughout my career. I am a self-taught programmer, and everything I know today comes from my own initiative to learn and improve. After five years of working with local clients, I decided to expand my knowledge and started learning more widely applicable programming languages like Java and Python. I’ve always been the type of person who thrives on challenges. Whenever I encounter a problem, I don’t just look for a quick fix—I dive deep into researching and understanding the problem, and I find a solution that works in the long run. This is what drives me. The ability to solve problems, no matter how complex, and the satisfaction that comes with it is what fuels my passion for programming. My big break came when I had the opportunity to work at \\\\. There, I replaced two senior and two junior developers, which led to significant cost savings for the company. I completed all tasks ahead of schedule, focusing on Java-based applications that were multithreaded and communicated with embedded systems. This experience taught me how to work under pressure and how to manage and solve complex technical problems efficiently. Following my time at \\\\, I transitioned into freelance work as a FullStack Developer, working with technologies such as HTML, CSS, Bootstrap, JavaScript, Django, Spring, MySQL, and PostgreSQL. As a freelancer, I was responsible for finding solutions to a wide range of problems, often working independently and making decisions on the fly. I learned that self-reliance is key in this industry, and being resourceful is one of the most important qualities a developer can have. Later, I joined \\\\ elecom, where I worked on system integration with foreign teams, BPM process solutions, and the merging of complex systems in Oracle databases. I continued to solve challenges, often working with teams across borders and tackling technical obstacles that required creative and well-thought-out solutions. Eventually, I founded my own company, \\\\, where I focus on developing software solutions, Artificial Intelligence (AI), Cybersecurity, and Ethical Hacking. As an entrepreneur, I take pride in finding innovative solutions to problems, whether they come from clients or from technical obstacles I encounter along the way. I’ve also had the privilege of working with the Serbian Ministry of Defense and the police, handling sensitive projects that demand both technical expertise and trustworthiness. Being a self-taught programmer means that I have had to learn and adapt on my own, and I’ve learned to embrace challenges as opportunities for growth. I am constantly driven by the process of solving problems, and it is what keeps me engaged and fulfilled in my work. I am always open to new collaborations and am eager to take on new challenges that push my boundaries in technology, cybersecurity, and software development.

Finally Launched My First App Without Any Coding Experience

About Myself I am a structural engineer that are taught to design buildings in the day and I have been dreaming forever to build a SaaS business to get out of the rat race. However, as a structural engineer, coding is definitely not something I am capable of doing (I have some simple knowledge, but its no way close to building an app) The Journey As I've mentioned, I always wanted to build a SaaS business because in my mind the business model is most attractive to me, where you only need to build once and can sell to millions. So I started off searching and exploring on the internet and my first ever "SaaS" was from Wordpress. I am buying plugin from other user and then pluggin into my own Wordpress website. It was a project management tool SaaS. I was so excited about the website and can't even sleep well at night because I'm just so hype about it. But, the reality is because this is my first ever business, I totally didn't realise about the importance of UI UX or my business differentiation, thinking that everyone will be as excited as I am. Then, I went deeper and deeper into the journey (I can write more about this in another post if anyone is interested) and finally landed on Flutterflow to create my first ever app. No Code Journey Thanks to no code builder, I never thought that a non-coder like me can ever create an app and got accepted by the App Store/Play Store. Since that I am using a low-code builder, for any specific requirement that I need that are not covered natively, I will just talk to ChatGPT and boom I pretty much got most of the answer I needed. About The App As someone that always try to keep track of my expenses, I never able to find an app that are simple and interesting enough for me to continue on the journey. I realise that I could have incorporate AI into this journey and hence there go, I created an AI Money Tracker. Let me introduce Rolly: AI Money Tracker - a new AI expense tracker where you can easily record your transactions just by chatting with our bot Rolly and it will automatically record and categorise the transaction into the most suitable category (you can also create any of your own category and it will also take care of it in consideration). I am not sharing the app link here to avoid getting ban, but feel free to search up Rolly: AI Money Tracker on either App Store on Play Store. My Learnings As someone that can't code and never imagine that I could create a production app by myself and publish it on to the App Store and Play Store. Since I am not making any money yet and just at the beginning of my entrepreneur journey, I can't give any substantial advice, all I can say is just my own learnings and feelings. My advice is if you have a dream of building a business, just go for it, don't worry about all the problems that you can think of to convince yourself not making the start at all. From my point of view, as long as you're not giving up everything (eg, putting yourself in huge debt etc), why don't just go for it and you've got nothing much to lose. You'll only lose if you never even get started. And also, I believe that creating an app is always the easiest step out of the entreprenuership journey, marketing and distribution is the key to success. Even though you've spent days and nights on it and it might mean everything to you, the truth is people don't really cares and you'll need to market for it. I am still in journey to learn how to do marketing, content, building a business and everything. I think this is just a very beginning of my journey and hopefully there's more interesting one to share further down the road.

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!

What questions to ask to evaluate an offer from start up?

Hello! I am presently working working as a Data Scientist with a medium sized company. Last year my boss left the company to start his own. Very recently his non-solicitation clause expired, and he asked me to join his startup. While I know almost everything about the product idea, and the technical aspect of the startup - I have very less information on more critical points like funding, equity sharing, etc. He has made a verbal unofficial offer, and I have asked for a week to prepare my list of questions for him for me to be able to evaluate his offer. Since I have no knowledge of the startup scene, I would like some help regarding the questions I should put forward to him. Mentioned below are what I know so far and the offer: The company was started by two people, both working full time on it. I would be the third person on the team. The startup aims to introduce AI in a field which has lagged behind in the introduction of technology by at least 2 decades. The big players in this field are conservative, but now they are opening up towards embracing new technology. Personally I have confidence in their idea, and feel this will be a sustainable and profitable company. The offered salary is about 60% of what I make right now. The equity offered is 2%. I do not know the details of the funding they have received so far or the equity split. Any pointers in helping me frame my questions for the evaluation of the offer would be very helpful! Thank you

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.

Should I Keep Iterating My Web Concept or Build an App to Attract Angel Investors?

Hi everyone, I’m building a start-up called Foodable, which takes your ingredients and leftovers and, using AI and the creator economy, provides personalised, user-generated, video-first recipes based on them and your preferences. Currently, I have a web concept that shows TikTok videos based on user-provided ingredients. It has over 2k people using it and some promising engagement. My next big step is to raise funding (starting with Angels) to take Foodable to the next level. However, I’m torn between two potential strategies and would love your advice. Option 1: Iterate the Web Concept Add 1-2 key features (e.g., dietary filters or improved video suggestions). Introduce a small paywall (e.g., £0.99/month) to validate whether people are willing to pay for what we’ve built. Use this validation to pitch Angels for funding, with the focus of building a more robust app version. Option 2: Build the App Version Bring someone on board to build the app (I have no coding experience). Shift away from TikTok videos and instead allow users to upload their own recipes. Use funding to iterate and improve the app after launch. I feel like validation is key to attracting Angels, but I’m not sure if it’s better to focus on proving willingness to pay with the web concept or build a more polished app version right away. What would you do in this situation?

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.

Practical tips on hiring the best people? Which country? Remote vs. In Person?

Hi Reddit, I run a tech startup that's grown to $20M ARR. While we are relatively big, we are incredibly cash strapped till Q3 due to debt we took on last year and are currently paying back. In Q3, I'll finally have a large budget to sit and focus on building out our team. Now I'm trying to figure out: what are the optimal circumstances? We really screwed it up with our first batch of key hires after our seed round: US Product Manager, US Head of Customer Success - quit; US Head of Sales, US Head of Engineering - fired. We've built a mostly B or C team, and it really annoys me. We are slow, we are not up for big challenges, and people are, on average, not that brilliant. Out of our nearly 150 employees, I think I have ONE A player. However, they are also functioning at 60%. We are building additional "brands" this year, so there might be a way to separate a higher performing culture into our second brand. I have 3 questions, might seem relatively basic, but as we did such a bad job the first time around, I'd love to learn what you all think! I'm trying to build an optimal team with A-players! Q1: Today we are fully remote, should I get an in person office going? In which city? Q2: In general, which city should I hire talent from? I live in San Francisco and sometimes LA, but find the culture here generally too laid back. New York? But to keep a high quality, let's say, marketer, interested long term, they're going to want $200-220k base (and that's not even that competitive). While that is fine, it will slow down my intended plan for hiring. London? Salaries are comparatively much lower, and talent quality is still pretty high, but I am a little unsure of the work culture. In terms of budget, I'd love to aim for $150-180k/key hire and to go as high as $300k if appropriate. Q3: Should I be hiring people with 20 years of relevant experience? 2-3 years with a hunger to prove themselves? Fresh grads we can mould into whatever we need? As for what exactly I'm trying to hire for, lots of key hires: department heads, digital marketers, content people, engineers, AI engineers, operations people, strategy people, and more. I don't know enough about all the working cultures in these places, but I want to find and incentivize people who are willing to own and take responsibility for an area of the business, be trusted to make good decisions, and view it as their responsibility to improve their areas drastically, more than the typical 9-5. I feel today's workforce is not content with base + light equity, and maybe we should consider tying an unlimited-upside incentive to a relevant KPI to incentivize people working harder than just "what is required"? (edit: I know might get some hate for this "work harder than 9-5" mentality, but to clarify, I'm trying to figure out what incentive structures will naturally attract the type of person that wants this type of working life) What do you think? Also, any other practical tips for finding awesome people like this? edit: hooooly! this thread blew up. I'll do my best to reply to everyone, thank you for all your responses!

What if one founder in every startup became an influencer in their space? Will they bring in more business? (I will not promote)

I quit my last startup literally a week ago and I am already starting something new. I raised $2.7 million for my last company. But I feel like that the distribution was not strong enough. Hence I failed. Now as a second time founder distribution is the first thing I am going to focus on. So I have started doing physical events. The first event is IRL in San Francisco. I am inviting the CEO of Product Hunt for a fireside. The event is about how Ai agent founders can launch on Product Hunt. I will also start making videos everyday until the event to promote myself as a influencer in the space of AI agents + Product launches. Then use this momentum and newly created distribution to launch my first Ai agent. Let's see if the strategy works. I will keep people here posted!

Mentally burnt out

My startup is not working and this is the year I probably need to shut down. I have struggled and tried to make this work for 5 years now but I am down to one person and hired consultants. I have a feeling of utter failure and no significant achievements. The minor alerts I have put out to potential future job prospects look bleak too. I am seen as too broad having been a Founder and not deep. I have an Engineering background but played the Go to Market/CEO role at my startup. Part of my mistake was not getting deep into the Engineering (outsourcing it). I have a rare combination of knowledge in Gen AI, Autonomous Vehicles and Strategy. However, there seem to be no takers - the market is too nascent and my skills have become too broad - a founder skillset rather than deep. What do I do now? I am mentally burnt out to make $$ out of this startup but the job market is not helping either.

I just had my best month after 18 months as a solopreneur

Last month I reached important milestones both financially (60+ sales) and in terms of my personal brand (2.500+ new followers) But the most important part is that it has reinforced a belief in myself: it is possible, as long as I keep going, improving, learning and iterating. For the last year and a half, I've been grinding and launching project after project. But there was always something wrong: Product didn't solve a real problem Bad marketing (very often lol) Target market had low purchasing power Super-competitive niche (usually b2c) It's difficult to have failure after failure and keep going on. At times it would feel like everyone was making money, except for me. I was hacking on my projects every single day before and after my 9-5 and had mostly given up all my free time for this. But results were far from being what I wanted. So I would doubt myself all the time. One thing I had going for me is that I really enjoy building things - so that helped me a lot in staying consistent. I always knew this was a long-term thing and that I'd probably have to fail again and again before seeing some success. But even so, it was really hard to keep up the spirits at all time, especially after working so hard for so long. I wasn't going to give up but I also knew that continuing like this would lead nowhere. So I decided that for my next project I would do 2 things: 1) prioritize marketing and 2) build something strategic 1) Prioritize marketing I decided I was going to put in the same amount of effort into marketing as I put into building. Usually my time would be split 90% coding - 10% marketing. Now, for the first time ever it's probably 65% coding - 35% marketing. I organized myself and made an entire gameplan for it. This forced me to learn a lot about: Video editing Cold emails Copywriting Running ads Short-form content There are a lot of items I still need to execute on - but at least I have a good idea of how to approach most things. 2) Build something strategic I had to build something that I would be able to use even if nobody else did. For the last year and a half I had been building AI apps and my plan was to continue doing that. So I decided to leverage that and thought about how I could build something that would give me an unfair advantage + have a compounding effect over the long term: a) Unfair advantage Having AI demo apps that cover all type of AI functionalities would make my life easier & would allow me to ship new apps quickly, regardless of the required model/functionality So even if nobody bought this - I'd have built something really useful for myself & would have a slight edge over other people b) Compound over the long term Building "AnotherWrapper' (my new project) would have a good synergy with my future projects: It would allow me to build new projects faster While building new projects, I'd learn new things, which I would then be able to implement into AnotherWrapper and improve the product that way A win-win. Closing thoughts I did not expect things to go this well - it's been an amazing month and I'm truly grateful to everyone that has been supporting me. But at the end of the day, there is still a lot of work to be done. The initial 'hype' & effects from some viral tweets are starting to wear off. I still don't have a reliable distribution channel that guarantees me traffic. So I need to figure that out. I think the product has a lot of potential - it has been well received and has been a success so far, but my distribution is still lacking. The good thing is that I now have some extra cash to spend on things like ads, influencers, freelancers etc. So it opens some new doors that were previously closed! I also have some other projects down the pipeline which are coming soon. Will keep you guys updated!

AI will obsolete most young vertical SAAS startups, I will not promote

This is an unpopular opinion, but living in New York City and working with a ton of vertical SaaS startups, meaning basically database wrapper startups that engineer workflows for specific industries and specific users, what they built was at one point in time kind of innovative, or their edge was the fact that they built these like very specific workflows. And so a lot of venture capital and seed funding has gone into these types of startups. But with AI, those database wrapper startups are basically obsolete. I personally feel like all of these companies are going to have to shift like quickly to AI or watch all of their edge and what value they bring to the table absolutely evaporate. It's something that I feel like it's not currently being priced in and no one really knows how to price, but it's going to be really interesting to watch as more software becomes generated and workflows get generated. I’m not saying these companies are worth nothing, but their products need to be completely redone EDIT: for people not understanding: The UX is completely different from traditional vertical saas. Also in real world scenarios, AI does not call the same APIs as the front end. The data handling and validation is different. It’s 50% rebuild. Then add in the technical debt, the fact that they might need a different tech stack to build agents correctly, different experience in their engineers. the power struggles that occur inside companies that need a huge change like this could tank the whole thing alone. It can be done, but these companies are vulnerable. The edge they have is working with existing customers to get it right. But they basically blew millions on a tech implementation that’s not as relevant going forwards. Investors maybe better served putting money into a fresh cap table

Marketing strategy for early-stage startup

Hi! I'm a first-time founder and now we with my co-founder are working on launching our solution. We are working on a b2c service that visualizes what people feel based on their notes. Our potential users are women 18-29 who are interested in feeling better. I'm non-technical so marketing is in my responsibilities. Now I am trying to create something like a marketing strategy for this early-stage launch, and I would like to know your opinions about it, maybe I missed something that could work for us. In my plan, we start by announcing in personal social networks, like LI, Ig and meeting new people on offline events. We also would try to have some paid or unpaid announcements in groups on Fb about health, well-being, new apps, AI (we use AI in our service), women entrepreneurs supportive communities. We were thinking about Tinder Ads, but I didn't have any reviews of it. We also plan to work with influencers on Ig and YT, maybe TikTok. And also would like to try Google Ads, IG ads, YT ads. ​ Have you tried something of it? How it was? Maybe I missed something that worked for you in similar cases?

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. ​ 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. ​ 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). ​ 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.

Accepted To Y Combinator - I will not promote

UPDATE: Thanks to everyone for giving clear and honest advice. It really helped me to make my decisions and know what I should focus on first. This community is awesome! I'm trying to get accepted to Y Combinator and realistically assessing my profile. I'm a non-technical, solo founder, in my early 40s, and balancing startup ambitions with family responsibilities (two kids). I understand the traditional YC profile often skews younger and technical, and solo non-technical founders might face an uphill climb. I'm specifically interested in hearing from anyone in r/startups who can identify with this background and applied (or was accepted) to YC. Were you accepted to YC despite being a non-technical, solo founder, and/or over 40 with family commitments? If you applied and were not accepted, do you feel these factors played a role, and what was your experience? Any advice for someone in my situation to strengthen my application and approach? Does anyone have recommendations for me as a non-technical founder to effectively attract and onboard a technical co-founder in the AI domain? Thank you for sharing your expertise and experiences.

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.

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.

Experienced Software Developer looking for startup to help. I will not promote

My passion for programming started at the age of 9 when I began playing video games. It was during this time that I first dived into programming, creating scripts for SA:MP (San Andreas Multiplayer) using the Pawn language. SA:MP is a modification for the popular game Grand Theft Auto: San Andreas, allowing players to experience multiplayer gameplay. My early experiences in programming were all about problem-solving—finding ways to enhance the game and improve the player experience. This was when I realized how satisfying it is to solve a problem through code, and that feeling has stayed with me throughout my career. I am a self-taught programmer, and everything I know today comes from my own initiative to learn and improve. After five years of working with local clients, I decided to expand my knowledge and started learning more widely applicable programming languages like Java and Python. I’ve always been the type of person who thrives on challenges. Whenever I encounter a problem, I don’t just look for a quick fix—I dive deep into researching and understanding the problem, and I find a solution that works in the long run. This is what drives me. The ability to solve problems, no matter how complex, and the satisfaction that comes with it is what fuels my passion for programming. My big break came when I had the opportunity to work at \\\\. There, I replaced two senior and two junior developers, which led to significant cost savings for the company. I completed all tasks ahead of schedule, focusing on Java-based applications that were multithreaded and communicated with embedded systems. This experience taught me how to work under pressure and how to manage and solve complex technical problems efficiently. Following my time at \\\\, I transitioned into freelance work as a FullStack Developer, working with technologies such as HTML, CSS, Bootstrap, JavaScript, Django, Spring, MySQL, and PostgreSQL. As a freelancer, I was responsible for finding solutions to a wide range of problems, often working independently and making decisions on the fly. I learned that self-reliance is key in this industry, and being resourceful is one of the most important qualities a developer can have. Later, I joined \\\\ elecom, where I worked on system integration with foreign teams, BPM process solutions, and the merging of complex systems in Oracle databases. I continued to solve challenges, often working with teams across borders and tackling technical obstacles that required creative and well-thought-out solutions. Eventually, I founded my own company, \\\\, where I focus on developing software solutions, Artificial Intelligence (AI), Cybersecurity, and Ethical Hacking. As an entrepreneur, I take pride in finding innovative solutions to problems, whether they come from clients or from technical obstacles I encounter along the way. I’ve also had the privilege of working with the Serbian Ministry of Defense and the police, handling sensitive projects that demand both technical expertise and trustworthiness. Being a self-taught programmer means that I have had to learn and adapt on my own, and I’ve learned to embrace challenges as opportunities for growth. I am constantly driven by the process of solving problems, and it is what keeps me engaged and fulfilled in my work. I am always open to new collaborations and am eager to take on new challenges that push my boundaries in technology, cybersecurity, and software development.

Finally Launched My First App Without Any Coding Experience

About Myself I am a structural engineer that are taught to design buildings in the day and I have been dreaming forever to build a SaaS business to get out of the rat race. However, as a structural engineer, coding is definitely not something I am capable of doing (I have some simple knowledge, but its no way close to building an app) The Journey As I've mentioned, I always wanted to build a SaaS business because in my mind the business model is most attractive to me, where you only need to build once and can sell to millions. So I started off searching and exploring on the internet and my first ever "SaaS" was from Wordpress. I am buying plugin from other user and then pluggin into my own Wordpress website. It was a project management tool SaaS. I was so excited about the website and can't even sleep well at night because I'm just so hype about it. But, the reality is because this is my first ever business, I totally didn't realise about the importance of UI UX or my business differentiation, thinking that everyone will be as excited as I am. Then, I went deeper and deeper into the journey (I can write more about this in another post if anyone is interested) and finally landed on Flutterflow to create my first ever app. No Code Journey Thanks to no code builder, I never thought that a non-coder like me can ever create an app and got accepted by the App Store/Play Store. Since that I am using a low-code builder, for any specific requirement that I need that are not covered natively, I will just talk to ChatGPT and boom I pretty much got most of the answer I needed. About The App As someone that always try to keep track of my expenses, I never able to find an app that are simple and interesting enough for me to continue on the journey. I realise that I could have incorporate AI into this journey and hence there go, I created an AI Money Tracker. Let me introduce Rolly: AI Money Tracker - a new AI expense tracker where you can easily record your transactions just by chatting with our bot Rolly and it will automatically record and categorise the transaction into the most suitable category (you can also create any of your own category and it will also take care of it in consideration). I am not sharing the app link here to avoid getting ban, but feel free to search up Rolly: AI Money Tracker on either App Store on Play Store. My Learnings As someone that can't code and never imagine that I could create a production app by myself and publish it on to the App Store and Play Store. Since I am not making any money yet and just at the beginning of my entrepreneur journey, I can't give any substantial advice, all I can say is just my own learnings and feelings. My advice is if you have a dream of building a business, just go for it, don't worry about all the problems that you can think of to convince yourself not making the start at all. From my point of view, as long as you're not giving up everything (eg, putting yourself in huge debt etc), why don't just go for it and you've got nothing much to lose. You'll only lose if you never even get started. And also, I believe that creating an app is always the easiest step out of the entreprenuership journey, marketing and distribution is the key to success. Even though you've spent days and nights on it and it might mean everything to you, the truth is people don't really cares and you'll need to market for it. I am still in journey to learn how to do marketing, content, building a business and everything. I think this is just a very beginning of my journey and hopefully there's more interesting one to share further down the road.

16 years old and thinking about creating a startup

Hi to everyone, this is my first post on Reddit and r/Startups. Sorry in advance if there is any mistake. I'm 16 years old, and I'm already planning to create my startup. Growing up in the digital age has given me both inspiration and doubts. On one side, you hear advice like, “You need connections with powerful people to succeed.” On the other, there are stories of founders coming from poverty and now leading billion-dollar companies.That really sucks. I'm here because I believe this community offers honest and grounded insights. So you can analyze, I leave you my goals. I accept all the advice you have. I’ll finish high school in two years while using my free time to learn about AI, programming, agile methods, and business basics. After that, I plan to pursue a Systems Engineering degree, even though I’ve debated skipping university. My older siblings convinced me it’s worth it for the professional and technical foundation. During college, I aim to freelance, save money, and build connections with entrepreneurs and developers. Beyond that, my 15-year plan includes working in tech companies to gain experience, creating an MVP for my startup, and securing funding through investors or incubators. I want to solve real-world problems using tools that feel future-proof. While I sometimes feel behind, I’m determined to catch up and take advantage of the opportunities ahead. I know the startup journey is uncertain—like a vulnerable animal facing competition, funding issues, and market challenges. But I’m ready to adapt as my vision evolves. Like for example the time. Obviously I would like to keep it exactly but you never know what can happen along the way. I’d love to hear your thoughts or advice. Thanks in advance, and I apologize if anything is unclear

People are overthinking with digital products.

All you really need is a checkout link to start. I failed a lot of times. Literally I could build the whole landing page, admin panel, ai automation to handle moderation and content. After spending months in vacuum building more, more, more features. Launching and getting 0 customers in the end. You are literally just getting depressed. You know that feeling, right ? Me too. We missed one important step before building anything - ASKING. We need to ask more clients, users, and do our research based on Google Keywords, forums and subreddits. You probably won't do it. It is your choice. You have all rights to do it. Let me give one piece of advice, instead of building more features and spendings months on your MVP. Set a deadline in 2-4 weeks. Build it, launch it, and go live as soon as possible. You need to get a real feedback and face a reality. Most of the companies that you see, started with simple Excel file, Google Doc, or even paper with pen. Do you know why ? Because they didn't have anything in the beginning. No money, no customers, NOTHING. Remember that.

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!

Am I on the right track?

This might be a little long for the average reader. But i'll do my best to format it so it's skimmable. Context I left my SaaS company 2 months ago. I was employee number 4 and helped them grow to 8 figures. I had a seat at the executive table and equity in the business. Burnt out and wanted to start my own thing. I forgot how hard it is to go from 0 👉 1 📚 Two schools of thought Build a product that solves your pain point and find others with that pain point Perform customer discovery calls until you get signal and start building + follow up with them 🥇 First approach For the last 45 days I built the product I wished I had when leading a 10 person marketing/sales team for the SaaS I was previously at. It checked all the boxes, pulled data, automated specific steps, showed the conversion tracking, data, etc. I launched it as a beta to my close network and the crowd went MILD. 😒 After some follow up - I realized I built something that already kind of exists and it's hard to convince others (even those who personally know me) that it's different or better. Undiscouraged, I am going to go back to the drawing board and try approach #2 above and schedule some customer discovery calls. 🥈 Second approach After trying and failing to turn the marketing numbers around at my last role I am convicted of 4 brutal truths about digital marketing today Truth #1 – AI-generated content is flooding the internet and ANYONE can and will be creating content with AI. Truth #2 – Ranking for high-volume keywords is harder than ever and probably not worth it anymore. Truth #3 – AI-driven efficiency is non-negotiable. If you haven’t installed AI in your business - you are WAY behind. Truth #4 – Most businesses are thinking about AI completely wrong. Easy button vs quality stair step. I have some early thoughts on how I would like to solve this (backed by data and some user stories). But my main question and the entire point of this post is.... ⁉️ Questions Before I schedule these product discovery calls should I make it clear where I am convicted and find those who want to talk (agree or disagree) with the above. Or just keep that out of the mix and ask them my product discovery questions regardless? I am probably overthinking it - but I just hit up my personal network with a beta launch, feels silly to go back with product discovery questions for them. Is there a good place (besides reddit) to pay people for product discovery calls? A quick Google Search and it's unclear to me.

Why you should consider using small open source fine-tuned models

Context I want to start off by giving some context on what fine-tuning is, why it's useful and who it would be useful for: What is fine-tuning? When controlling the output of an LLM there are, broadly, three levels. Prompt engineering, RAG and fine-tuning. Most of you are likely familiar with the first two. Prompt engineering is when you try to optimize the prompt to get the model to do what you want better. RAG (retrieval augmented generation) is when you first do a search on some data (usually stored in a vector database which allows you to search by similarity), then you insert the results into the prompt so that the model can use that context to more accurately answer any questions. It's like letting the LLM access external information right before answering, using that additional context to improve its response Fine-tuning is when you want to fundamentally teach a model something new or teach it to behave in a particular way. You would provide the model with high quality data (i.e. inputs and outputs) which it will train on. Why is it useful? At the moment, many of you use the largest and best LLMs because they give the best results. However, for a lot of use cases you are likely using a sledgehammer for a small nail. Does it do a great job? Damn yeah! Well... why not use a smaller hammer? Because it might miss or hit your finger. The solution shouldn't be to use a sledgehammer, but rather to learn how to use a smaller hammer properly so you never miss! That's exactly what fine-tuning a smaller model is like. Once you fine-tune it on a specific task with good high quality data, it can surpass even the best models at that specific task. It'll be 10x cheaper to run, much faster and, if you use an open source model, you'll own the model (no vendor lock-in!). If you run a SaaS and your biggest expense is AI costs then you should definitely consider fine-tuning. It'll take some time to set up but it'll be well worth it in the medium/long term (a bit like SEO). You can always resort to the best models for more complex tasks. How to fine-tune? I'm going to give you a breakdown of the process from beginning to end. You do need to be (a bit) technical in order to do this. Getting the data Let's suppose we want to fine-tune a model to make high-quality SEO content. At the moment, you might be using a large sophisticated prompt or using multiple large LLMs to write different parts or utilizing RAG. This is all slow and expensive but might be giving you great results. Our goal is to replace this with a fine-tuned model that is great at one thing: writing high-quality SEO content quickly at a much lower cost. The first step is gathering the appropriate data. If you want the model to write 3 or 4 paragraphs based on a prompt that contains the topic and a few keywords, then your data should match that. There are a few way you can do this: You can manually gather high-quality SEO content. You'd write the prompt and the response that the model should give. You can use a larger more powerful LLM to generate the content for you (also known as synthetic data). It'll be expensive but remember that it'll be a larger one-off cost to get the data. If you already have a pipeline that works great then you can use the prompts and the generated content that you already have from that pipeline. You can buy a high-quality dataset or get someone to make it for you. The data is the most important part of this process. Remember, garbage in garbage out. Your data needs to have a good variety and should not contain any bad examples. You should aim for around 1000 examples. The more the better! The actual fine-tuning. At this stage you are now ready to choose a model and setup the fine-tuning. If you are unsure I'd stick to the Llama 3.1 family of models. They are great and reliable. There are three models: 8b, 70b and 405b. Depending on the complexity of the task you should select an appropriate size. However, to really reap the cost saving benefits and the speed you should try to stick with the 8b model or the the 70b model if the 8b is not good enough. For our SEO example, let's use the 8b model. Important note on selecting a model: You might see multiple models with the 8b flag. You might see 4bit-bnb or instruct. The instruct version of the models have basically been trained to be chatbots. So if you want to keep the chatbot-like instruction-following functionality then you should use the instruct version as the base. The non-instruct version simply generates text. It won't 'act' like a chatbot which is better for use cases like creative writing. The 4bit-bnb means that the model has been 'quantized'. Basically it has been made 4x smaller (the original is in 16 bits) so that it is faster to download and faster to fine-tune. This slightly reduces the accuracy of the model but it's usually fine for most use cases :) Fine-tuning should be done on a good GPU. CPU aren't good enough. So you can't spin up a droplet on digital ocean and use that. You'll specifically need to spin up a GPU. One website that I think is great is Runpod .io (I am not affiliated with them). You simply pay for the GPU by the hour. If you want the training to be fast you can use the H100, if you want something cheaper but slower you can use the A40. Although the A40 won't be good enough to run the 70b parameter model. For the 405b model you'll need multiple H100s but let's leave that for more advanced use cases. Once you've spun up your H100 and ssh-ed into it. I would recommend using the unsloth open source library to do the fine-tuning. They have great docs and good boilerplate code. You want to train using a method called QLoRA. This won't train the entire model but only "part of it". I don't want to get into the technical details as t3hat isn't important but essentially it's a very efficient and effective way of fine-tuning models. When fine-tuning you can provide something called a 'validation set'. As your model is training it will be tested against the 'validation set' to see how well it's doing. You'll get an 'eval loss' which basically means how well is your model doing when compared with the unseen validation data. If you have 1000 training examples I'd recommend taking out 100-200 so it can act as the validation set. Your model may start off with an eval loss of 1.1 and by the end of the training (e.g. 3 epochs - the number of epochs is the number of times your model will be trained on the entire dataset. It's like reading a book more than once so you can understand it better. Usually 3-5 epochs is enough) the eval loss would drop to 0.6 or 0.7 which means your model has made great progress in learning your dataset! You don't want it to be too low as that means it is literally memorizing which isn't good. Post fine-tuning You'll want to save the model with the best eval loss. You actually won't have the whole model, just something called the "QLoRA adapters". These are basically like the new neurons that contain the "understanding" of the data you trained the model on. You can combine these with the base model (using unsloth again) to prompt the model. You can also (and I recommend this) convert the model to GGUF format (using unsloth again). This basically packages the QLoRA adapters and model together into an optimized format so you can easily and efficiently run it and prompt it (using unsloth again... lol). I would then recommend running some evaluations on the new model. You can do this by simply prompting the new model and a more powerful model (or using your old pipeline) and then asking a powerful model e.g. Claude to judge which is better. If your model consistently does better then you've hit a winner! You can then use runpod again to deploy the model to their serverless AI endpoint so you only pay when it's actually being inferenced. (Again, I'm not affiliated with them) I hope this was useful and you at least got a good idea of what fine-tuning is and how you might go about doing it. By the way, I've just launched a website where you can easily fine-tune Llama 3.1 models. I'm actually hoping to eventually automate this entire process as I believe small fine-tuned models will be much more common in the future. If you want more info, feel free to DM me :)

I am selling my tool which converts websites into android and iOS apps within 5 minutes.

Hi, my name is Toshit Garg. I started working on SaaS products around April 2023. The plan was simple: to create tools that help entrepreneurs easily grow their businesses. My first tool was "Convertixo", inspired by my work as a Fiverr seller where I converted websites into apps for clients, earning around $1,000 per month. I thought, why not automate this process? Following Convertixo, I created a few other tools like "Web to PWA". At one point, I developed an AI-based tool called "AppMintAI" , a productized service named "Engage Enhance", and even a WordPress plugin that lets users create pragmatic pages for SEO and a boilerplates. Unfortunately, none of these tools gained significant traction. I would launch them on Product Hunt, get a few users, and then nothing. Other than Convertixo, all my other tools only received a handful of free users. I believe this happened because I’m not very passionate about marketing. So, I decided to pivot and focus on content creation, which is where my true passion lies. Currently, I’m selling all my products one by one. As for Convertixo, it now has 800 users, a $20 MRR, and an email subscriber list of 100+. It was also the third Product of the Day on Product Hunt in January of this year. While the product has gained some traction, I’ve realized my focus is on content creation. However, with the right marketing and drive, I believe Convertixo has great potential to grow. If you’re interested in taking Convertixo to the next level, let’s chat! Here are some key statistics: In the last 20 days, Convertixo has received 4.9K impressions from Google and 338 visitors. More about the product: Convertixo can convert any website into Android and iOS apps using a custom webview. The apps are generated in Android Studio and Xcode. You receive both the APK and the source code for the Android app, along with the source code for the iOS app. The converted apps require no maintenance, and they update exactly like the website. A major benefit is the ability to add push notifications via OneSignal for free, allowing you to re-target your customers at no cost. Feel free to ask if you have any questions!

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.

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

We received 25k investment offer, need advice [I will not promote]

We received a $25k for 2.5% on a convertible note offer from a US based investor. The note matures in 18 months with an interest rate of 5%, but the investor said they can extend it further. It’s an AI SaaS in graphic design. We have been bootstrapping till now, and we feel that this money could help us hire better engineers and marketeers, we want to grow it to a good revenue, but don't see it becoming a billion dollar startup as such. Our initial plans were to build it like an indie-hacker, grow it a decent revenue and sell it to someone who can take better care of it. We built it as a side project with full time jobs. We already have decent traction with 10k+ signups and $600+ in revenue per month with <100 dollars spent on marketing. But our AI model costs are high, 0.2 USD per user that we onboard and provide free credits. But we as founders are more interested in another idea that we have been thinking about and see a bigger potential + founder market fit in. The current product is good, and we can foresee that with better hiring and marketing, we can grow our revenue to about 10-20k a month, like a regular online business. What should we do? We don't want to simply let go of the product because it's not that it doesn't work, it's just that we as founders are better fit for something else. We can't sell it yet as the revenue isn't too high and we haven't even incorporated. Is it okay if we think of growing it to 10-20k+ a month and then intend to sell it to someone who can take better care of it? Should we take the investment in such a case, given this investment is definitely gonna help us grow? Process of incorporation will also help us in selling this business later I think?

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.

From Running a $350M Startup to Failing Big and Rediscovering What Really Matters in Life ❤️

This is my story. I’ve always been a hustler. I don’t remember a time I wasn’t working since I was 14. Barely slept 4 hours a night, always busy—solving problems, putting out fires. After college (LLB and MBA), I was lost. I tried regular jobs but couldn’t get excited, and when I’m not excited, I spiral. But I knew entrepreneurship; I just didn’t realize it was an option for adults. Then, in 2017 a friend asked me to help with their startup. “Cool,” I thought. Finally, a place where I could solve problems all day. It was a small e-commerce idea, tackling an interesting angle. I worked 17-hour days, delivering on a bike, talking to customers, vendors, and even random people on the street. Things moved fast. We applied to Y Combinator, got in, and raised $18M before Demo Day even started. We grew 100% month-over-month. Then came another $40M, and I moved to NYC. Before I knew it, we had 1,000 employees and raised $80M more. I was COO, managing 17 direct reports (VPs of Ops, Finance, HR, Data, and more) and 800 indirect employees. On the surface, I was on top of the world. But in reality, I was at rock bottom. I couldn’t sleep, drowning in anxiety, and eventually ended up on antidepressants. Then 2022 hit. We needed to raise $100M, but we couldn’t. In three brutal months, we laid off 900 people. It was the darkest period of my life. I felt like I’d failed everyone—myself, investors, my company, and my team. I took a year off. Packed up the car with my wife and drove across Europe, staying in remote places, just trying to calm my nervous system. I couldn’t speak to anyone, felt ashamed, and battled deep depression. It took over a year, therapy, plant medicine, intense morning routines, and a workout regimen to get back on my feet, physically and mentally. Now, I’m on the other side. In the past 6 months, I’ve been regaining my mojo, with a new respect for who I am and why I’m here. I made peace with what I went through over those 7 years—the lessons, the people, the experiences. I started reconnecting with my community, giving back. Every week, I have conversations with young founders, offering direction, or even jumping in to help with their operations. It’s been a huge gift. I also began exploring side projects. I never knew how to code, but I’ve always had ideas. Recent advances in AI gave me the push I needed. I built my first app, as my first attempt at my true passion—consumer products for kids. Today, I feel wholesome about my journey. I hope others can see that too. ❤️ EDIT: Wow, I didn’t expect this post to resonate with so many people. A lot of you have DM’d me, and I’ll try to respond. Just a heads-up, though—I’m juggling consulting and new projects, so I can’t jump on too many calls. Since I’m not promoting anything, I won’t be funneling folks to my page, so forgive me if I don’t get back to everyone. Anyway, it’s amazing to connect with so many of you. I’d love to write more, so let me know what topics you’d be interested in!

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.

Should we give up?

I'm currently very demotivated because we're working on our SaaS startup since 1,5 years and we still haven't found active users, let alone a customer. We're building an AI-first tool that automates user research analysis. We've released two MVPs so far and are planning to build a third. People respond well to outreach (5-7% book a demo from those who received a first message) but then they fail to use it. We are talking with users a lot so we are aware of the problems, and we might be able to solve them if we continue building and testing. I find it hard though to solve these problems efficiently, because there are no similar established AI-first products on the market and it feels like we have to create a new UX standard. Some problems might be very hard to be solved, e.g. there are high cost of switching products for many of our potential users. Also, my time is limited, as I recently (5 months ago) became a mother. I can only work 30 hours per week. It's a competitive area we're in and our competitors have gradually developed into the same direction and it's getting harder to position ourselves. Also, GPTs might soon be able to do what we're doing - for free. I feel like AI tools are generally expected by many to be free. The price we're expecting to be able to bill is getting lower and lower and our finance plan is already looking tight. However, there are adjacent audiences which we could target as well, but none of us knows them. Is it normal as a founder to struggle so much at the beginning? I've read that it took established SaaS 2,5 years on average from founding to first revenue. We haven't founded so far so you could say we're not behind \sarcasm\ Shall we keep pushing? My tech co-founder is optimistic and thinks this is where the wheat is separated from the chaff. We're currently supported financially by a government fund so we haven't spent much private money. However, I feel like my career outlook gets worse with each day that I unsuccessfully try to raise this startup.

30K MRR from a huge barbershop - 100 automated lost meaning

Hello So in the past 2 years I have developed a sort of a beauty hub in Transylvania where I have about 30-35 people working every day. I am not a programmer but I have some skills in a few NO CODE platforms and managed to develop the entire system 100% automated and for a very low cost. When I say 100% automated I mean that I rarely even show up there and things work perfectly.I had a big dream in this industry but along the way I lost interest and decided 6 months ago that this is it. I will no longer do anything that is not necessary and pivot to other industryThe AI era popped up. The problem with me is that I just can't do meaningless stuff like most of the products out there. Tried a couple of things but lots interest very fast. For example I was able to build a sort of a kids app where I generated stories based on parents input where the kid was the super hero in 3 days. Lost interest even faster. I am in a confort zone producing good cash with zero effort. This is a dangerous area since I do not have the ability to scale so I can grow, simply because I decided I want to do something else. I would really like to use my time in something meaningful, creating something that would really help people or businesses.What are you guys building? Did you ever feel this way after you scaled or sold your business?

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

Stable Video 3D creates orbiting videos of objects

The introduction of Stable Video 3D (SV3D) by Stability AI could significantly change how we interact with digital content in several straightforward ways: \- Online Shopping: Products can be viewed in 360-degree videos, making shopping online more like seeing the item in person. This could help shoppers make better decisions and feel more confident about their purchases. \- Design and Gaming: Designers and game developers can quickly turn images into 3D models, speeding up their work and improving the quality of their designs and games. \- Augmented and Virtual Reality: Creating content for AR and VR could become easier and more accessible, leading to more immersive and engaging experiences in these platforms. \- Accessibility for Creators: With SV3D available for non-commercial use, more people can experiment with 3D content creation, potentially leading to innovative applications and uses in various fields. This literally just happened if you want AI news as it drops it launches here first. The whole article has been extrapolated here as well for convenience.

Seeking Feedback: Would a No-Code AI Solution Benefit Your Business?

Hi, fellow small business owners. I'm currently working on an AI startup, with the goal of providing small businesses a seamless and intuitive way to integrate AI into operations without the need for any coding or tech expertise. We're designing an auto machine learning application that's user-friendly and tailored to the unique needs of small businesses. Before we scale, I would really appreciate any insights and feedback. Here are a few questions that would be helpful to get answers to: Pain Points: Are there specific tasks or processes in your operations that you think could be automated or enhanced using AI? This could be anything from customer service chatbots, inventory management, sales forecasting, or anything else you might think of. Features: What features would you want in a no-code AI solution? Perhaps easy integration with existing software? Drag-and-drop model training? Pre-built models for common tasks? Training & Support: How important would training and support be for you in implementing and using an AI solution? Would you prefer video tutorials, live-chat support, or hands-on workshops? Pricing: Would you be willing to invest in such a tool? If so, what would be a reasonable price point for you? We're considering a tiered model based on usage, with a potential starting point of $X/month. Does that sound feasible? Trial Period: Would a free trial period be beneficial for you? How long would you need to assess the tool's impact on your business? Data Concerns: How comfortable are you with sharing data with an AI application? What privacy and security measures would make you feel at ease? Your feedback is really useful. We're building this solution with you in mind, and your insights will guide the next steps. In appreciation for your time and input, we're offering a special discount for early adopters from this community once we launch. Just drop a comment below, and I'll make sure to get in touch when we are ready. Many Thanks, Chris Parker

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age Introduction In an era characterized by rapid technological advancements, the field of finance is undergoing a transformative journey. The emergence of financial technology, or fintech, is reshaping the way businesses manage their finances, and Chartered Accountants (CAs) are at the forefront of this evolution. In this blog post, we'll explore how CAs are embracing fintech and leveraging its potential to enhance financial management, analysis, and advisory services. Fintech's Impact on Financial Services Fintech encompasses a wide range of technologies that leverage data analytics, artificial intelligence, blockchain, and automation to improve financial services. For CAs, this means new tools to streamline processes, enhance decision-making, and offer innovative solutions to clients. Automation of Routine Tasks CAs are increasingly using automation tools to handle repetitive tasks such as data entry, reconciliations, and transaction processing. This not only reduces the risk of human error but also frees up CAs to focus on higher-value tasks like strategic planning and analysis. Advanced Data Analytics Data analytics tools enable CAs to extract meaningful insights from large volumes of financial data. These insights can help businesses identify trends, anticipate risks, and make informed decisions to drive growth. Real-Time Financial Reporting Fintech enables CAs to provide clients with real-time financial reporting, giving businesses immediate access to critical information. This enhances transparency and empowers business owners to respond quickly to changing market conditions. Enhancing Audit Efficiency Fintech tools are revolutionizing the audit process. CAs can use AI-powered algorithms to analyze vast amounts of data, detect anomalies, and identify potential instances of fraud more efficiently. Personalized Financial Planning CAs can leverage fintech to offer personalized financial planning services. With access to detailed financial data, CAs can create tailored strategies that align with a client's unique goals and circumstances. Strengthening Cybersecurity As businesses become more reliant on digital tools, cybersecurity becomes paramount. CAs are playing a critical role in advising clients on cybersecurity measures to protect sensitive financial information. Virtual CFO Services Fintech enables CAs to offer virtual CFO services to startups and small businesses. Through digital platforms, CAs can provide expert financial advice and guidance remotely, making their expertise accessible to a wider range of clients. Embracing Blockchain Technology Blockchain's potential for secure and transparent record-keeping is of interest to CAs. They can explore applications in supply chain finance, smart contracts, and even audit trail verification. Continuous Learning in Fintech CAs recognize the importance of staying updated with fintech trends. Many are investing in continuous learning to master the use of new tools and technologies that can optimize their services. Conclusion The integration of fintech into the realm of finance is reshaping the landscape in profound ways. CAs are embracing these technologies to elevate their roles from traditional number-crunchers to strategic advisors, equipped with tools that enhance efficiency, accuracy, and insight. As fintech continues to evolve, CAs will remain pivotal in guiding businesses through the ever-changing financial landscape, leveraging technology to drive growth, innovation, and success. Find the top verified CA in your City Feel free to let me know if you'd like more blogs on different topics or if you have specific requirements for the content.

Seeking Your Feedback: SeedHustle and Your Small Business Journey✨

Hello, everyone, I'm one of the co-founder of SeedHustle, and I wanted to have an authentic discussion with you about our recent developments. SeedHustle is a project dear to us, with the aim of simplifying the often complex process of connecting startups with venture capitalists. 🌟 Why did we embark on this journey? Well, we've been in your shoes, experiencing the frustration of the never-ending search for the right VC partner and the challenges of establishing meaningful connections. This shared experience led to the creation of (https://seedhustle.ai/ ) . So, what's the deal with SeedHustle? It's our effort to streamline the process of finding the ideal VC match. You provide us with your company details, and our AI system goes to work, suggesting potential VCs and explaining why they might be a good fit based on their past investments and backgrounds. We also provide real-time data on their funds. We're currently in the private beta phase and want to extend an invitation to join our Discord community. It's a space where founders can share their stories and possibly make introductions to VCs. As founders who thrive on AI challenges, we believe this could be a game-changer. 👂 I'm here to have an open dialogue. Is there anything you'd like to discuss? Whether it's SeedHustle, our journey, or your own small business experiences, we're all ears. Here are a few conversation starters: \-Does SeedHustle align with your small business journey? \-Do you have any suggestions for how we can improve our platform? \-Is there anything about what we're doing that's unclear or not quite resonating with you? Your feedback is incredibly valuable to us, so please feel free to reach out. Thank you for being a part of this journey, and we hope to see you in our Discord community for a chat! 😊🚀

Struggling with my dog-themed clothing store – How can I make it better?

TL;DR: I own a dog-inspired store that’s struggling to make sales. I need your honest feedback to make it better. Hey reddit, I’m turning to you because I really need your honest feedback. I run a small online shop, dogloverclothing.com, where I sell dog-inspired fashion items and accessories (product list is growing). I poured my heart into creating it because I’m a huge dog lover (I own a Corgi and a Beagle), and I thought there must be others out there who’d resonate with the style of my designs. I truly believe my shop is fun and creative and I thought other dog lovers would easily connect with the dog-theme behind it. But I’m struggling. I’ve only made 1-2 sales a year and I feel like I’ve hit a wall. Let me be completely transparent about my situation: I have a small child who needs my care in the afternoons. I work part-time in the mornings, and the only time I'm able to work on my shop is in the evenings (once all the usual household chaos is settled) or on weekends. That gives me maybe 1-2 hours a day to focus on this project. I don’t have the money or time for big ad campaigns, influencer cooperations, daily social media activity, or even professional photoshoots for my products. My visuals are mostly created with AI tools, stock imagery, and mockup generators, but I think they look professional enough to be converting. I tried small ad campaigns, and while I got a few sales, the ad costs ended up being higher than my revenue, so I had to stop. I also tried organic Social Media activity, but the time I put into that did not turn into any traffic, followers or sales, so I also stopped that. I know that putting myself/my face out there on social media could help, but I’m not comfortable showing my face or apartment in videos or ads. I could do flatlays or simple videos with the products I have at home. Right now, I’m putting all my energy into SEO, hoping to attract organic traffic and customers. Otherwise, I feel stuck with marketing. I want to make the most of the limited time and resources I have. My dream definitely isn’t to get rich here from this shop. I would love to make an extra $300-500 a month to make life a little easier for my family, while fulfilling my creative streak – and that's about it. I’m not sure if that’s even realistic, but it’s what keeps me going. So, guys: What do you think I’m doing wrong or could do better? Is it the designs? The pricing? The website layout? The lack of time/lack of money? How can I make this work with my limited time and resources? Are there any affordable, creative marketing strategies you’d recommend for someone in my shoes? Is my goal of $300-500/month realistic for a store like mine? I’m open to all your ideas, tips, and even brutal honesty. This isn’t just a business for me, it’s my passion project, and I’d love to make it somewhat of sustainable. I’m not here to sell you something. I’m here to learn. I know Reddit doesn’t hold back, and that’s what I need. Can you take a look at my site, tell me what you think, and help me figure out why this dream hasn’t taken off yet? I know running a business is tough, and I deeply admire everyone in this community who’s making it work. I’d love to hear your insights, experiences, and even your tough love if that’s what it takes to get my dream back on track. Thank you so much for taking the time to read this and for any advice you can offer!

Seeking Advice on Online Lead Generation and Tools for a New Service-Based Brokerage

I recently launched an online, B2B, service-based brokerage that's heavily reliant on web-based marketing for lead generation. As a bootstrapped business owner, I'm feeling a bit overwhelmed trying to determine the most effective strategies for driving online leads—whether through Google Ads, SEO, or other methods. In addition, I'm looking for the best software and tools to help organize and manage leads, or even assist in the lead generation process. I've been exploring AI-powered tools like AI Call Agents and others, but I’m unsure of what would be most effective for a growing business like mine. If anyone has experience with tools or strategies that have worked well early in your business journey, I’d love to hear your insights!

How do you make your client presentations stand out?

Hey folks! I’ve been working on improving how I pitch to clients, and I feel like my presentations are always missing that extra “wow” factor. I try to keep things professional and clean, but it still feels like something’s missing—whether it’s storytelling, design, or just better ways to structure ideas. Do you have any strategies or tips for creating client presentations that leave a strong impression? Would love to hear what’s worked for you or any resources you’d recommend! Update: some of the good advice I got: use story to attract people, use Fiverr to get help form designers, use ChatGPT or ChatSlide to help with the content, use DeathToStock to help with images.

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!

Struggling with Emotions Automating Jobs

Hey everyone, I run a small logistics company alongside my father that I recently began taking a more active role in. Many of the \~50 employees are quite behind on the tech side of things and therefore are lacking serious productivity, lots of pen and paper still. As part of my efforts to streamline things I worked with an automation/ai company that took a look at our processes and helped us implement some new tech, however I’m struggling emotionally with the outcome. &#x200B; Unfortunately we no longer need several of our staff anymore, particularly those that handled tasks like our data entry, text customer service, invoicing, and dispatchers. It’s never fun letting anyone go, but I’m worried about some of the implications for our culture and other employees… &#x200B; In a perfect world I’d love to keep these 4-5 full-time staff members on the team and train them to do other roles, but frankly after calculating it out and running the numbers we’re better off just reducing staff and taking the significant cost savings for now, and reallocating resources. &#x200B; My question: How to toe this delicate line to do right by our staff that we respect and care about, while also keeping our business up to date with modern tech? I am leaning towards generous exit packages and providing support helping them find new jobs, but still don’t quite feel right.

Anyone actually using ai in their business?

Feels like every day there’s another AI ad, another person trying to sell some tool. But are other small business owners actually using AI in a way that makes a real difference? Or is it just something people talk about but never really implement? I’ve been messing around with it and have seen it work in some cases, curious if anyone here has actually made it part of their business or tried and gave up on it. If you’ve got thoughts, I’d love to hear them. Feel free to DM me too if you just wanna talk shop.

What is your biggest challenge when finding and implementing AI tools for your business?

I've been looking into AI tools lately to help streamline my business, but the whole process can feel like a huge challenge. With so many options out there, it’s hard to figure out which ones are worth the time (and money) to implement. Even when I find something promising, there’s always the question of how it will integrate with my current systems or whether it will actually make things easier rather than more complicated. I’m curious to hear from others who are going through the same thing. What’s been the hardest part for you when finding or setting up AI tools? Is it choosing the right one? The cost? Figuring out how to implement it without a ton of headaches? Let’s share some of our challenges—maybe we can learn from each other’s experiences and make the process a little smoother!

Seeking co-founder to build LinkedIn’s biggest rival(curated version)

How do you connect with likeminded people? You see the polished wins everywhere, but what about the messy drafts , the awkward pitches and the moments you’re not sure you’ve got it right? Problem: The whole idea of founding and starting a business can be super intimidating for some people, specially those who don’t know any founders personally, those who don’t have a large network, those who don’t have rich parents with large networks, those not inserted in an entrepreneurial culture like in the US for example (which is my case). Sometimes all you need is the right support network, and too see others do what you want, to know that it’s possible! Everyone has an “ultimate guide” to make 7 figures or build a business on YouTube but NO ONE shoes you the HOW, just the results… I’ve tried joining founder communities, LinkedIn ,Reddit … you name it. Most of these founder communities are inaccessible for regular people and often ask for you to have an already existing business with a min ARR… or their simply geography based and if you’re not in a certain area you can’t really participate… As of LinkedIn… full of empty AI generated posts about how some random dude raised $10m in 7 days. Okay Jonathan, but what about the HOW?? How did you write your first pitch? How many rejection calls did you get? What is an MVP? There simply isn’t a platform out there to document your founding journey and find inspiration within a community of people who are doing the same as you. What better way to feel motivated then to see someone actually document their process? Solution: I’m working on building a social media platform for aspiring/founders to connect through the RAW, UNFILTERED process of turning ideas into reality in REAL time. It’s all gonna be around the “building in public “ concept and content creation. Picture an instagram/tiktok profile where instead of seeing someone’s dog you see them documenting their founding process—from the moment they had the idea, to the moment they launched, you’re going to see the successes, the fails, the rejected calls, all documented through actual content and not some AI generated LinkedIn post. Imagine if you wanted to learn about how Steve Jobs started Apple , you could simply go through his profile on this app—exactly. To make sure all interactions are meaningful people would have to apply. It’s a truly curated community, with REAL people, building REAL things in REAL time, and not just tell us the story of how they did it… Audience: I’m targeting people who have a burning desire of building a business and early stage founders starting their founder journeys, that don’t have a support network and simply don’t know where to start. People who are tired of watching 30 min “ultimate guides “ on how to make it on YouTube from “business gurus” selling courses. People who haven’t reached the min ARR required to join an “exclusive “ founder a community. People who can’t simply just move to the US to get into the “exclusive” YC combinator. People who want to connect with real people building real things and not anonymous people on Reddit, or LinkedIn influencers again trying to promote their services. I believe in the idea because I’m also part of my audience. Have always wanted to start my own thing just never knew how to and where to find a community of likeminded people . I don’t know any founders myself, I come from a non-entrepreneurial society and I’d pay good money to access a community of REAL passionate founders building REAL things, in REAL time. This would be my first ever business, and I want to share my journey building it and hopefully inspire others to just start so I’ve created a mailing list to keep anyone interested in the project updated on my fails , learnings and successes. I’m not worried about “making it” but just “starting” and hopefully reach the right audience and inspire anyone to start whatever they have marinating in their thoughts. If you’re a founder struggling with staying consistent or an aspiring founder with an insane desire of starting and don’t know how to start, I’d love to get your feedback on what’s stopping you, your challenges starting out and what you’d find useful in such platform. And finally would this be something that interests you?? PS: casually looking for a technical co-founder

Small business teaching and implementing ai

Purely a question as a "poll" and will not accept business if interested on this platform. My name is anonymous. Question: I want to teach people, seniors, and small businesses to use chatgpt/other ai tools. Ideally it would be a small profit venture by charging per support ticket and prompt engineering sessions. Is this a bad idea? I know people who know and do not know chatgpt, those who do use it but only at a basic level. I feel even if I charge a few dollars but empower people I could reach several thousand and make a living?

Looking for Feedback on this Idea

Hey everyone, I’d love some honest feedback on an idea I’ve been working on (currently just in paper). A little about me: I started in hospitality across South America and Asia, then moved into social entrepreneurship in a rural area, and eventually ecommerce using WordPress. Now, I’m deep into programming here in Europe, which I’ve really come to enjoy. So yes, I understand the perspective of businesses, entrepreneurs and programmers.  Back when I had tons of ideas for businesses and optimizing processes, I always hit the same drama: "You need a developer." But hiring one was too expensive or unreliable or shady business practice, and partnering with a programmer, someone I barely knew often felt too risky (I've learned the hard way that partnerships can feel like marriages). Now, as a programmer, I get a lot of requests from small businesses needing help and sometimes with very simple ideas. And while I can do it, I often don’t have the time, so I have to tell them I can't. And when I do have time, I know the cost can be too much for their budget. This got me thinking: What if I created a course to teach business owners just enough programming to solve their own problems? Not to become full time coders, but to gain enough knowledge to build simple tools or, better yet, understand code enough to ask the right questions whether it's to AI or a future developer. The course would focus on programming but talking business language, starting with building more flexible websites, managing your own content and creating custom tools without the limitations of templates or paid widgets. I’m thinking of creating a supportive community where we learn and grow together (maybe using your business as an example), and I’d be available to help along the way, plus I will be adding tools that you could reuse for your business (mostly because you will be able to read it and understand it → that's the goal). Talking about money, I can only tell you will be way more affordable compared to multiple payments in different places. So, does this resonate with you? I’d really appreciate your honest thoughts. Do you feel you have the time to learn or you still prefer looking for a developer? Feel free to share any frustrations or ideas. And if this sounds interesting, write me a PM, and I’ll keep you updated. Thanks for reading. I'm excited to hear what you think! :)

Seeking Feedback & Support: Launching a Nut Mix Startup to Improve Gut Health

This txt is AI summarized but I read it, he just restructured my thoughts accurately. Hey all, I’m Ilia, a Seattle-based entrepreneur working on a product that’s all about making healthy eating easier. I’m creating a premium nut mix with 16+ different nuts (70% organic) aimed at helping people improve their microbiome and overall health. The concept is simple: diverse ingredients lead to better gut health, reduced inflammation, and more energy. No more juggling 20 bags of different foods—my nut mix is a convenient, delicious solution. I’m in the early stages and raising about $7,000 to cover things like regulatory compliance, a commercial kitchen rental, quality ingredients, packaging, and a basic brand presence. I’ve poured my own savings into this and am now turning to the community for support, advice, and maybe even early funding. I made a short (12-min) video walking through the concept, the budget breakdown, and my long-term vision (expanding to seeds, fruit mixes, and maybe even a billion-dollar brand one day!). I’d love your honest feedback, connections, or suggestions. If you’re interested in supporting, even by sharing this post, I really appreciate it. Feel free to ask me anything—transparency is key for me, and I want to build something that genuinely helps people live healthier. https://www.gofundme.com/f/support-my-goal-to-make-healthy-eating-easy-and-convenient

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age

The Evolution of Financial Technology: How CAs Are Embracing the Digital Age Introduction In an era characterized by rapid technological advancements, the field of finance is undergoing a transformative journey. The emergence of financial technology, or fintech, is reshaping the way businesses manage their finances, and Chartered Accountants (CAs) are at the forefront of this evolution. In this blog post, we'll explore how CAs are embracing fintech and leveraging its potential to enhance financial management, analysis, and advisory services. Fintech's Impact on Financial Services Fintech encompasses a wide range of technologies that leverage data analytics, artificial intelligence, blockchain, and automation to improve financial services. For CAs, this means new tools to streamline processes, enhance decision-making, and offer innovative solutions to clients. Automation of Routine Tasks CAs are increasingly using automation tools to handle repetitive tasks such as data entry, reconciliations, and transaction processing. This not only reduces the risk of human error but also frees up CAs to focus on higher-value tasks like strategic planning and analysis. Advanced Data Analytics Data analytics tools enable CAs to extract meaningful insights from large volumes of financial data. These insights can help businesses identify trends, anticipate risks, and make informed decisions to drive growth. Real-Time Financial Reporting Fintech enables CAs to provide clients with real-time financial reporting, giving businesses immediate access to critical information. This enhances transparency and empowers business owners to respond quickly to changing market conditions. Enhancing Audit Efficiency Fintech tools are revolutionizing the audit process. CAs can use AI-powered algorithms to analyze vast amounts of data, detect anomalies, and identify potential instances of fraud more efficiently. Personalized Financial Planning CAs can leverage fintech to offer personalized financial planning services. With access to detailed financial data, CAs can create tailored strategies that align with a client's unique goals and circumstances. Strengthening Cybersecurity As businesses become more reliant on digital tools, cybersecurity becomes paramount. CAs are playing a critical role in advising clients on cybersecurity measures to protect sensitive financial information. Virtual CFO Services Fintech enables CAs to offer virtual CFO services to startups and small businesses. Through digital platforms, CAs can provide expert financial advice and guidance remotely, making their expertise accessible to a wider range of clients. Embracing Blockchain Technology Blockchain's potential for secure and transparent record-keeping is of interest to CAs. They can explore applications in supply chain finance, smart contracts, and even audit trail verification. Continuous Learning in Fintech CAs recognize the importance of staying updated with fintech trends. Many are investing in continuous learning to master the use of new tools and technologies that can optimize their services. Conclusion The integration of fintech into the realm of finance is reshaping the landscape in profound ways. CAs are embracing these technologies to elevate their roles from traditional number-crunchers to strategic advisors, equipped with tools that enhance efficiency, accuracy, and insight. As fintech continues to evolve, CAs will remain pivotal in guiding businesses through the ever-changing financial landscape, leveraging technology to drive growth, innovation, and success. Find the top verified CA in your City Feel free to let me know if you'd like more blogs on different topics or if you have specific requirements for the content.

As a Business Owner, what are your technology challenges?

Premise: I've spent way too long in IT (as a developer) and worked primarily with technical clients for past 17+ years. I am a bit in a bubble. Lately I've been considering pivoting from freelancing into a different kind of business and need some feedback from SMB community. So I would like to hear from non-technical business owners. If you consider yourself non-technical owner what are some challenges you face with modern day technology (including AI, social media, digital advertising)? For example (some areas non-technical owners have challenges), 👉 digital marketing, social media, content, etc? 👉 Or more in terms of operations, inventory tracking, customer management is manual? 👉 /Or does it feel like you have a lot of manual tasks that should have been automated, but you just don't know how or don't know if possible? 👉 Perhaps you're using frankenstein-system of documents, email attachments, spreadsheets, written notes that lack organization? 👉 Or you're not marketing your business online? Obviously solution would have a price tag, but if it reduces overhead costs or increase ROI, why wouldn't you? Some ideas, but feel free to throw in more. I have not figured out my current offer nor service, just doing my market research. Thank you for feedback 🙏

Seeking Feedback on My Business Idea – SaaS + Lead Generation for Small Businesses

Edit: TL;DR I’m Sarvesh, a digital marketer with 10 years of experience in paid ads. After losing my job last year, I started freelancing and discovered how much small businesses struggle with getting reviews (Google, Yelp, TrustPilot, etc.). My Business Idea – SaaS + Paid Ads Free Plan: Businesses can track & reply to reviews across 40+ platforms in one dashboard. Paid Plan ($99/month): Automates review collection, AI-powered responses, social media posting, and spam detection. Custom Plan: Paid ads to generate leads, offered only to businesses on my paid plan for 3+ months. Goal: SaaS platform attracts users → Some upgrade to paid plan → Best clients get lead-generation help → More leads → More reviews → More organic customers → A profitable business cycle. Need Feedback: Does this idea have potential? How can I get my first beta users? Any features I should add/remove? Would love your thoughts—thanks for reading! 😊 TL: Hi everyone, I’m Sarvesh, and I’m in the process of starting my own business. Since my target audience is small businesses, I’d love to get some input, advice, or critiques from this community. A Little About Me I’ve spent the last 10 years working in paid advertising, helping medium and large businesses generate leads through Facebook and Google Ads. I also have experience running e-commerce campaigns. You can check out my background on LinkedIn: LinkedIn Profile Last year, my second daughter was born, and around the same time, my company shut down all its offices (India & UK), leaving me without a job. I decided to take a break and spend time with my wife and newborn, something I regretted not doing with my first child. By November, I started job hunting again, but in the meantime, I got some freelance work through Reddit, helping small businesses with ads for the first time. For context, in my previous jobs, I managed ad campaigns with daily budgets of £4K–£8K. Working with small businesses was a new challenge, but to my surprise, I was able to generate solid leads for beauty salons, hair salons, and nail salons, helping them grow. What stood out to me was how much impact my work had—unlike my corporate job, where I was just another person in the system, here I felt truly valued. That feeling led me to explore starting my own business. The Problem I Noticed While working with small businesses, I realized that online reviews (Google, Yelp, Trustpilot, etc.) are critical for them, yet many struggle to get them. Customers often don’t leave reviews, and employees are either too shy or don’t prioritize asking for them. This gave me an idea—to build a system that helps businesses get more genuine Google reviews from customers. I developed the system but struggled to find businesses willing to test it, even for free. My target audience is U.S. small businesses, but since I’m based in India, cold emails and Reddit outreach didn’t get much traction. My Business Idea – SaaS + Custom Plans I’m now thinking of pivoting my business model into a SaaS platform with optional paid upgrades. Here’s how it would work: Free Plan (Review Tracking & Management) Businesses can track their reviews across 40+ platforms (Google, Yelp, Facebook, Trustpilot, TripAdvisor, etc.) in one dashboard. They can reply to reviews manually from a single place instead of switching between platforms. This will be completely free forever. Paid Plan ($99/month, Plus SMS/Email Costs) For businesses that struggle to get reviews, they can upgrade to a paid plan that includes: Automated Review Requests – Automatically send review requests via SMS & email. Website Widget – Showcase 4- and 5-star reviews dynamically. Social Media Automation – Automatically post positive reviews on Facebook/Instagram. AI-Powered Responses – AI can reply to reviews automatically. Spam Detection – The system will notify businesses of suspicious reviews (but won’t take direct action). Custom Plan (Lead Generation via Paid Ads) I will personally manage paid ad campaigns to generate leads. Pricing depends on the niche, budget, and contract duration. Money-Back Guarantee – If I don’t deliver results, I refund the month’s fee. Small businesses can’t afford wasted ad spend, and I want to ensure I provide real value. Limited spots per month to maintain quality and avoid burnout. How Everything Ties Together The SaaS platform serves as a lead generation tool for my custom plans: Businesses use the free plan to track their reviews. Some upgrade to the paid plan to automate and improve reviews. A select few, after 3 months on the paid plan, can join my custom plan for paid ads to generate more leads. More leads → More reviews → Better Google Maps ranking → More organic customers → A more profitable business. Would Love Your Feedback! What do you think about this approach? Do you see potential for this business to take off? Any features I should add or remove? Any suggestions on how I can get my first beta users to test the SaaS platform? What about pricing? Do you think $99 is good pricing? I know this is a long post, but I really appreciate anyone taking the time to read and share their thoughts. Thanks in advance!

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?

(Academic) AI Readiness Survey for Small and Medium Businesses (SMB's) in Food and Beverage Industry. (Everyone 18+, Growing & Managing Small Business in Food and Beverage Industry, Canadian market)

Hi everyone! 👋 I'm conducting a research study on how AI-driven automation and hyper-personalization can enhance customer-centric innovation for small bakeries and food businesses. This survey will help understand and assess the awareness, key challenges, opportunities, and ethical concerns surrounding AI adoption among SMBs in the food and beverage industry. The results will help tailor AI adoption strategies, resources, and training programs. This survey will take about 10-15 minutes, and your responses will remain confidential. This study is also approved by Research Ethics Board (REB) #2024-70. Link: AI Readiness Survey for Small Businesses across Food and Beverage Industry Your insights will contribute to real-world AI adoption strategies, AI toolkits, and experiential learning programs for small businesses. I'd love to hear your thoughts! Feel free to drop any comments or questions. We will share the results of the study on this subreddit once we analyze the result. Thank you very much in advance for your time and help!

Would You Pay for a Simple Course on How Small Businesses Can Integrate AI Without the Noise?

Helli, I’m Dan, and I’ve spent a lot of time exploring and working with various business tools. Over the years, I’ve self-taught myself how to navigate the overwhelming amount of information out there about AI and its potential for small businesses. One thing I’ve noticed is that many small business owners are struggling to cut through the noise and figure out how AI can actually help their businesses—without needing a tech background or spending a fortune. So, I’m working on a simple, actionable course designed specifically for small businesses. It would cover: Filtering through the hype and picking the right AI tools Practical applications like automating social media, customer service, or invoicing Using data to make better decisions Balancing automation with the human touch The idea is to make it straightforward and practical, showing real tools in action that you can implement right away. Would you find value in a course like this? If so, what would you want to learn, and what price point feels reasonable for such content? Thanks for your input—I’d love to make something that’s genuinely helpful for the community!

(Academic) AI Readiness Survey for Small and Medium Businesses (SMB's) in Food and Beverage Industry. (Everyone 18+, Growing & Managing Small Business in Food and Beverage Industry, Canadian market)

Hi everyone! 👋 I'm conducting a research study on how AI-driven automation and hyper-personalization can enhance customer-centric innovation for small bakeries and food businesses. This survey will help understand and assess the awareness, key challenges, opportunities, and ethical concerns surrounding AI adoption among SMBs in the food and beverage industry. The results will help tailor AI adoption strategies, resources, and training programs. This survey will take about 10-15 minutes, and your responses will remain confidential. This study is also approved by Research Ethics Board (REB) #2024-70. Link: AI Readiness Survey for Small Businesses across Food and Beverage Industry Your insights will contribute to real-world AI adoption strategies, AI toolkits, and experiential learning programs for small businesses. I'd love to hear your thoughts! Feel free to drop any comments or questions. We will share the results of the study on this subreddit once we analyze the result. Thank you very much in advance for your time and help!

Would You Pay for a Simple Course on How Small Businesses Can Integrate AI Without the Noise?

Helli, I’m Dan, and I’ve spent a lot of time exploring and working with various business tools. Over the years, I’ve self-taught myself how to navigate the overwhelming amount of information out there about AI and its potential for small businesses. One thing I’ve noticed is that many small business owners are struggling to cut through the noise and figure out how AI can actually help their businesses—without needing a tech background or spending a fortune. So, I’m working on a simple, actionable course designed specifically for small businesses. It would cover: Filtering through the hype and picking the right AI tools Practical applications like automating social media, customer service, or invoicing Using data to make better decisions Balancing automation with the human touch The idea is to make it straightforward and practical, showing real tools in action that you can implement right away. Would you find value in a course like this? If so, what would you want to learn, and what price point feels reasonable for such content? Thanks for your input—I’d love to make something that’s genuinely helpful for the community!

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.

As a Business Owner, what are your technology challenges?

Premise: I've spent way too long in IT (as a developer) and worked primarily with technical clients for past 17+ years. I am a bit in a bubble. Lately I've been considering pivoting from freelancing into a different kind of business and need some feedback from SMB community. So I would like to hear from non-technical business owners. If you consider yourself non-technical owner what are some challenges you face with modern day technology (including AI, social media, digital advertising)? For example (some areas non-technical owners have challenges), 👉 digital marketing, social media, content, etc? 👉 Or more in terms of operations, inventory tracking, customer management is manual? 👉 /Or does it feel like you have a lot of manual tasks that should have been automated, but you just don't know how or don't know if possible? 👉 Perhaps you're using frankenstein-system of documents, email attachments, spreadsheets, written notes that lack organization? 👉 Or you're not marketing your business online? Obviously solution would have a price tag, but if it reduces overhead costs or increase ROI, why wouldn't you? Some ideas, but feel free to throw in more. I have not figured out my current offer nor service, just doing my market research. Thank you for feedback 🙏

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)

What Two AI Agents would Help SMBs The Most

Hey everyone, I want to create a couple of AI agents for the SMB space. I would like to get a feel for what the best two agents to build for the SMB would be. I was thinking of an AI assistant and an AI sales assistant. Are these too similar, and would you suggest if so?

SMB Owners: Would You Use an AI-Powered Tool to Increase Revenue?

Hey everyone! I'm working on a tool designed to help small business owners optimize revenue using AI. It would provide automated insights for things like forecasting, customer retention, and cross-platform sales optimization without the complexity of enterprise tools. If you’re a small business owner, I’d love to hear your thoughts. Would a tool like this solve a pain point for you? Feel free to share any feedback on features or things you’d like to see. Appreciate any insights!

(Academic) AI Readiness Survey for Small and Medium Businesses (SMB's) in Food and Beverage Industry. (Everyone 18+, Growing & Managing Small Business in Food and Beverage Industry, Canadian market)

Hi everyone! 👋 I'm conducting a research study on how AI-driven automation and hyper-personalization can enhance customer-centric innovation for small bakeries and food businesses. This survey will help understand and assess the awareness, key challenges, opportunities, and ethical concerns surrounding AI adoption among SMBs in the food and beverage industry. The results will help tailor AI adoption strategies, resources, and training programs. This survey will take about 10-15 minutes, and your responses will remain confidential. This study is also approved by Research Ethics Board (REB) #2024-70. Link: AI Readiness Survey for Small Businesses across Food and Beverage Industry Your insights will contribute to real-world AI adoption strategies, AI toolkits, and experiential learning programs for small businesses. I'd love to hear your thoughts! Feel free to drop any comments or questions. We will share the results of the study on this subreddit once we analyze the result. Thank you very much in advance for your time and help!

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?

SMB Owners: Would You Use an AI-Powered Tool to Increase Revenue?

Hey everyone! I'm working on a tool designed to help small business owners optimize revenue using AI. It would provide automated insights for things like forecasting, customer retention, and cross-platform sales optimization without the complexity of enterprise tools. If you’re a small business owner, I’d love to hear your thoughts. Would a tool like this solve a pain point for you? Feel free to share any feedback on features or things you’d like to see. Appreciate any insights!

Heeelp - How are you using AI and automations to actually benefit you?

Hey fellow small business owners! 👋 I have been trying to use Ai and automations to streamline my every day business tasks, but sometimes it feels like setting things up is more complicated and time consuming than the actual benefit. So here is my question - what AI tools and automations are really working for your small businesses. What tools do you swear by?How have they helped you save time or money?

How did you guys start enjoying coding?

Hey everyone, I'm currently in my first year studying AI, and while I feel like I can grasp the theoretical concepts pretty well, I haven’t been practicing as much as I should. I know this will eventually affect my skills, but I’m just not the type to spend hours coding for fun. That said, when I have an obligation or feel pressured, I actually learn concepts really fast and can apply them effectively. I guess I just struggle with finding motivation when there’s no immediate need. For those of you who genuinely enjoy coding, was it always like that? Did you do something specific that made it more fun or engaging? Would love to hear your experiences!

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.

Introduction to Large Language Models for Generative AI

Hey everyone! I've recently written an introduction to large language models for generative ai \- it's a comprehensive introduction to the topic for anyone that is interested! We go over: What language models are How language models are trained The abilities of large language models The scaling of language models And more! Feel free to let me know what you think :)

MIT Introduction to Data-Centric AI

Announcing the first-ever course on Data-Centric AI. Learn how to train better ML models by improving the data. Course homepage | Lecture videos on YouTube | Lab Assignments The course covers: Data-Centric AI vs. Model-Centric AI Label Errors Dataset Creation and Curation Data-centric Evaluation of ML Models Class Imbalance, Outliers, and Distribution Shift Growing or Compressing Datasets Interpretability in Data-Centric ML Encoding Human Priors: Data Augmentation and Prompt Engineering Data Privacy and Security MIT, like most universities, has many courses on machine learning (6.036, 6.867, and many others). Those classes teach techniques to produce effective models for a given dataset, and the classes focus heavily on the mathematical details of models rather than practical applications. However, in real-world applications of ML, the dataset is not fixed, and focusing on improving the data often gives better results than improving the model. We’ve personally seen this time and time again in our applied ML work as well as our research. Data-Centric AI (DCAI) is an emerging science that studies techniques to improve datasets in a systematic/algorithmic way — given that this topic wasn’t covered in the standard curriculum, we (a group of PhD candidates and grads) thought that we should put together a new class! We taught this intensive 2-week course in January over MIT’s IAP term, and we’ve just published all the course material, including lecture videos, lecture notes, hands-on lab assignments, and lab solutions, in hopes that people outside the MIT community would find these resources useful. We’d be happy to answer any questions related to the class or DCAI in general, and we’d love to hear any feedback on how we can improve the course material. Introduction to Data-Centric AI is open-source opencourseware, so feel free to make improvements directly: https://github.com/dcai-course/dcai-course.

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.

Getting Back Into AI/ML After a Career Break – Seeking Advice

Hi everyone, I’m a stay-at-home mom looking to restart my career in AI/ML. I have a Bachelor’s in AI and a Master’s in IT, along with experience teaching undergraduate courses like Fundamentals of AI and Artificial Neural Networks (ANN). However, I have a significant gap in my resume, which makes me feel a bit demotivated about re-entering the field. Despite the gap, my passion for AI hasn’t faded—I’m still fascinated by the field and would love to learn Machine Learning from scratch to build a strong foundation and transition into an ML career. I’d really appreciate any advice on: • The best way to relearn ML from scratch (courses, books, hands-on projects) • How to fill the resume gap and make myself a strong candidate again • Any communities, mentorship programs, or networking strategies that might help If anyone has been through a similar situation or has guidance on how to break back into AI/ML after a career break, I’d love to hear your thoughts! Thanks in advance.

Teaching an AI to Play Mario: A Learning Journey

TLDR: I've always wanted to learn reinforcement learning, but the notation and concepts often seemed overwhelming (and scary). So, \~3 months ago, I set myself a challenge: Train an AI to Speedrun Mario Watch the progression here: https://youtu.be/OQitI066aI0 &#x200B; Full Story: Three months ago, I stared at the dense forest of Reinforcement Learning (RL) papers and felt like Mario facing Bowser for the first time: unequipped and overwhelmingly outmatched. The notation seemed like hieroglyphics, and terms like "policy gradients" felt like they belonged in a sci-fi novel, not a beginner's project. But RL always seemed so cool, and I was really determined to achieve my goal. So, I started with the Sutton & Barto RL textbook, learning things like the Multi-Armed Bandit problem and MDPs working my way up to Actor-Critic methods. That book is literal gold & I highly recommend you work through it (even though it can be tough at times). I tried everything from random courses online to books on amazon & this textbook has been by far the most clear and effective way to learn RL. The biggest issue with the textbook is you learn a lot of theory, but don't learn implementation. So, I would go through a chapter a week & set aside Friday + the weekend to actually implement what I learned (usually by watching youtube tutorials & looking at Github Repos). Eventually, while searching for practical resources for implementing PPO, I stumbled upon a GitHub repository that literally trained an AI to play Mario. Rather than just cloning and running the code, I took a deeper approach. I aimed to understand the repository thoroughly, ensuring each line of code made sense in the context of what I had studied. But of course, this wasn't easy. One of the biggest issues was my hardware limitation. I was working on an old Mac. So, I started using Google Collab, but that had its own problems (session timeouts & limited GPU access). Ultimately, I found AWS Sagemaker to be pretty good. &#x200B; After rewriting the code, I felt confident it would work because I understood every aspect of it. So, I trained the AI to play Mario across a variety of different levels (took a long time and a lot of trial and error with the learning rate). It feels amazing seeing your theoretical knowledge translate into tangible results & this project gave me a big confidence boost. &#x200B; Anyways I made a video showing off the results (Note that I simplified the technical parts for it to reach a wider audience): https://youtu.be/OQitI066aI0 &#x200B; Feel free to drop any questions or feedback, I'm more than happy to help or chat about my experiences. I hope my journey can inspire some of you who might be feeling overwhelmed with the idea of diving into reinforcement learning or any other area of AI. Remember, the hardest part is often taking the first step. Once you start, the momentum will carry you forward. Thank you for reading my super long post and sharing in my little success story! 🚀🕹️🎮

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.

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.

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!

Advise Needed] Mechanical engineer trying to venture into ML

Hello fellow redditors, &#x200B; As the title suggests, I am a mechanical engineer with a masters in mechanical design from a top institute in India. Directly after my masters, I got a job but left it after exactly one year to pursue civil services. And that decision has left a 3 year void in my career sheet. During these three years, the most I have been in touch with tech/science was through random personal automations using python and digital notetaking systems or a few readings here and there. I don't know if they have anything to do with each other, but I am lazy (for repetitive work) and have an eye to optimize /automate my workflow. The later led to me learning python, a bit of git and css/html. With regard to my prgramming skills, I learn quickly and had good grades in all the computer science courses we had at the college (C++, DSA and Modelling-Simulation). I have also programmed in Matlab for basic usage in research and also in LAMDA for nanomechanics/molecular simulation. At my work, I had written a python code to automate the process of model setup for FE which reduced the human intervention from very menial routine work (hindi: gadha majdoori). As for my mechanical engineering skills, I am good with CAE softwares and can readily work with them. So first thing I am doing right now is applying in various positions in the same domain as I had worked 3 years ago. All this while, I got introduced to the world of Machine Learning, AI and Deep Learning. So, I wish to learn ML to slowly venture into that line. So yeah, my question here to the CS veterans is, how to start with the learning, from where, what can I expect from the field and how much time is necessary for be able to get a decent opportunity in that domain? Currently, I have started with Andrew Ng's course on Courcera: Course 1 of Deep Learning Specialisation. https://www.coursera.org/learn/neural-networks-deep-learning but it seems rather theoretical to me and without implementation it will be difficult for me to grasp (I feel). Also, I explored fast.ai course which follows top-down approach unlike Andrew. I haven't committed to it. Kindly guide. All kinds of opinon are welcome. PS. I am 28yo

ML/AI and Digital Marketing

M28, studied Economics in school, have 5 years of experience in Digital Marketing, and have a good grasp of Python. More and more, I see that my full time job in Digital Advertising is becoming automated due to Machine Learning on platforms like Meta/Google. I'm concerned that in the long run I won't be very valuable. Advertising is already a mid-paying career as is. My thought is to learn about machine learning/AI for the first half of this year and then create a side project to showcase to future employers. My questions are: How should I learn about ML/AI? Is Andrew Ng's Coursera course a good place to start? I often feel that with courses I struggle to retain the information as I don't use it. Should I start a side project before or after completing a course? Also thought about creating a newsletter just so I can distill the learnings. 10 years from now, how valuable will knowing AI/ML be? Will the AI/ML systems get so advanced that human intervention is not needed and therefore isn't a skill to invest in? Should I instead invest in a creative skill set?

I'm Building an "AiExecutiveSuperAgent_Systems_Interface" between humanity and the Ai world, as well as each other... Let's Talk?

Ok... So look... This one is pretty crazy... I'm building an Ai Interface that knows me better than I know myself - Check, lots of people have this, either in reality with employees and family members, or with ai intelligence. But it doesn't just know Me... It knows how to talk with Me. It understands my language, because I've trained it to. I've also trained it to translate that to all my clients and HumanAgents, soon to become RobotAgents... The RESULT: I can literally just spend 1-18 hours talking to it, and things get DONE. Most of that time, I just say EXECUTE, or ENGAGE, or DRAFT, or DISPATCH. I feel like a secret agent communicating in codes with his agency 😂 Not great for the paranoiac in me, but it's easy to get that part under control, ya'll. It's like having a team of 10,000 people, all available 24/7, all perfectly synchronised to each other's communication styles, preferences and ultimately: WHAT DO YOU NEED ME TO DO. At the end of the it all, having run my single COMMAND through a thousand of those people, a Document is prepared that outlines the next 3 stages of the plan, along with instructions to the whole team for how to ENACT it. Sounds rather grand and wonderful... Even when I simply use it to help me come up with a filing system for my creative work... \\\\\\\\\\\\\\\\\\\\\\ Here's my current VISION, why I'm doing this AND why I'm doing it publicly despite it being top secret. VISION To create an army of User-Owned and Operated "AiSuperAgencies" which gather intelligence on the user, securely file and analyse it, and then construct a sub-army of agents and tools that work together to produce the desired output, for any Function in the Personal and Professional Lives of EVERYONE, EVERYWHERE, in 3-5 Years. To start, I'm building it for me and the 5-10 cleaners who've made it to Level 1 in my access system. They were sick of toxic employers, tyrannical agencies and greedy customers. They gathered around us (many came in, many went out, few stayed, took about a year for our core team of 3 Level 2 Cleaners. My goal has always been to never employ anyone. Just me, my Partner and the Cleaners. All Shared Owners in the system for delivering the right cleaner to the right house in our town, at the right time and without any dramas or arguments... I have a personal talent for resolving disputes, which has made working for and buying from my business a mostly enjoyable and upbeat experience, with a touch of mystery and a feeling that you're part of something big! It is a business that ran on Me. I put in my time, every day, building automated tool after automated tool. Hiring a contractor to do a job, scratching my head when it didn't add enough value to pay for itself, then just doing it myself again. I wanted to solve that problem. I'm trusting that the few who hear about it who actually see the potential, will just come join us, no dramas, just cool people partnering up! And those that don't, won't. No one could steal it, because it's Mine, and I'll just change the keys anyway loser! Enjoy digging through my past, you lunatic! I'm out here living Now. Anyways... It's lonely around here. I have a cleaning business that I run from my laptop, which means I can live anywhere, but I still had this big problem of time... NOT ENOUGH Oh Wait. It's Here.

Is fine-tunig dead?

Hello, I am leading a business creation project in AI in France (Europe more broadly). To concretize and structure this project, my partners recommend me to collect feedback from professionals in the sector, and it is in this context that I am asking for your help. Lately, I have learned a lot about data annotation and I have seen a division of thoughts and I admit to being a little lost. Several questions come to mind, in particular is fine-tunig dead? RAG is it really better? Will we see few-shot learning gain momentum or will conventional learning with millions of data continue? And for whom? Too many questions, which I have grouped together in a form, if you would like to help me see more clearly the data needs of the market, I suggest you answer this short form (4 minutes): https://forms.gle/ixyHnwXGyKSJsBof6. This form is more for businesses, but if you have a good vision of the sector, feel free to respond. Your answers will remain confidential and anonymous. No personal or sensitive data is requested. This does not involve a monetary transfer. Thank you for your valuable help. You can also express your thoughts in response to this post. If you have any questions or would like to know more about this initiative, I would be happy to discuss it. Subnotik

Is it too late for me to do a PhD in the US?

In 2019 I started an integrated Masters of Physics at Oxford. Graduated summer of 2023. During that time I first authored an AI research paper with the Oxford AI Society. We tried to get it into ICLR but it got rejected. Managed to get it into a NeurIPS workshop though, however I'm unsure if that holds much weight. The paper also got 21 citations on arxiv which is nice. After graduating, my gf and I broke up (mutually, long distance was too much) and life after university made me quite down. Bad market and struggled to get a job. A friend reached out to me about doing a startup in San Francisco. Did that startup until January 2024 when I quit because I had no money left. Through the connections I made out there I landed a gig at Chroma DB. Did a research contract with them. We didn't make a paper but instead made a technical report. The GitHub repo for the project has gained over 200 stars. However, since I was remote and US visas are a pain, my contract wasn't renewed. I tried starting my own business from July 2024 till December. I managed to secure a long term contract with a US construction company building them software that automates admin via GPT. Still doing this contract now and they've said they're happy to keep me for as long as I want. That's the context. During the winter of 2024 I thought heavily about applying for a PhD in the US. At: CMU, Stanford, Berkeley, MIT, CalTech, etc. However, I knew my profile wasn't strong enough. So I want to apply the winter of 2025. I'm in talks with a few institutions and research groups about doing projects. But is it possible that, starting in February 2025, I can co-author, submit and have accepted a paper into a top conference by December 2025? I feel like I'm too late to this decision and should have skipped that San Francisco startup to just do research projects from the start.

How I landed an internship in AI

For motivational purposes only! I see a lot of posts on here from people without “traditional” machine learning, data science, etc.. backgrounds asking how they can break into the field, so I wanted to share my experience. EDIT Learning Resources and Side Project Ideas * My background: I graduated from a decent undergraduate school with a degree in Political Science several years ago. Following school I worked in both a client services role at a market research company and an account management role at a pretty notable fintech start-up. Both of these roles exposed me to ML, AI and more sophisticated software concepts in general, and I didn’t really care for the sales side of things, so I decided to make an attempt at switching careers into something more technical. While working full time I began taking night classes at a local community college, starting with pre calculus all the way up to Calc 2 and eventually more advanced classes like linear algebra and applied probability. I also took some programming courses including DSA. I took these classes for about two years while working, and on the side had been working through various ML books and videos on YouTube. What worked the best for me was Hands-on Machine Learning with Scikit Learn, Keara’s and Tensorflow. I eventually had enough credits where I was able to begin applying to MS in Data Science programs and was fortunate enough to get accepted into one and also get a position in their Robotics Lab doing Computer Vision work. When it came time to apply for internships, it was a BLOODBATH. I must have applied to over 100 roles with my only responses being video interviews and OA’s. Finally I got an interview for an AI Model Validation internship with a large insurance company and after completing the interviews was told I performed well but they were still interviewing several candidates. I ended up getting the offer and accepting the role where I’ll be working on a Computer Vision model and some LLM related tasks this summer and could not be more fortunate / excited. A couple things stood out to them during the interview process. 1, the fact that I was working and taking night classes with the intent to break into the field. It showed a genuine passion as opposed to someone who watched a YouTube video and claims they are now an expert. 2, side projects. I not only had several projects, but I had some that were relevant to the work I’d be doing this summer from the computer vision standpoint. 3, business sense. I emphasized during my interviews how working in a business role prior to beginning my masters would give me a leg up as intern because I would be able to apply the work of a data scientist to solving actual business challenges. For those of you trying to break into the field, keep pushing, keep building, and focus on what makes you unique and able to help a company! Please feel free to contact me if you would like any tips I can share, examples of projects, or anything that would be helpful to your journey.

Learning AI for Business Leaders

Hello Community, For the better part of 2 months I have been reading up on everything in getting a better understanding of the fundamentals of AI - from history of AI to reading the Google 8’s peer reviewed paper on the advent of transformers. I feel as though I am running in circles at times an not following a guided path approach to learning. I’m 40, work in international development in a leadership role - though I have a background in corporate finance and tech. I’m not an engineer, nor do I have the ambition of such a career pivot. However I do want to learn, be abreast, and know enough about the space when evaluating (and proposing) AI related opportunities - my role now should be a path towards a chief innovation officer for a development agency within the next 3-4 years. My sources have been basically everything I can find from tech blogs, WaPo, financial times, economist, and random internet searches. I have completed IBM’s Fundamental on AI course. However, I feel there no structure in learning as I have been piecemealing from so many different sources. Essentially I care about business cases and being able to confidently talk about AI. And not building and deploying a product. MIT and UPenn have some courses on AI for leaders, however, as the space is moving so fast I’m not confident how current their materials are. My ask: Are there any courses (or learning approaches) you recommend that is less-code and more focus on concept and applications I should do? Is my approach to learning too broad and I should focus on a subset of AI such as ML or specifically GenAI since it seems most applications are currently byproducts of it. Many thanks in advance for any support - truly appreciate it.

Backend dev wants to learn ML

Hello ML Experts, I am staff engineer, working in a product based organization, handling the backend services. I see myself becoming Solution Architect and then Enterprise Architect one day. With the AI and ML trending now a days, So i feel ML should be an additional skill that i should acquire which can help me leading and architecting providing solutions to the problems more efficiently, I think however it might not replace the traditional SWEs working on backend APIs completely, but ML will be just an additional diamention similar to the knowledge of Cloud services and DevOps. So i would like to acquire ML knowledge, I dont have any plans to be an expert at it right now, nor i want to become a full time data scientist or ML engineer as of today. But who knows i might diverge, but thats not the plan currently. I did some quick promting with ChatGPT and was able to comeup with below learning path for me. So i would appreciate if some of you ML experts can take a look at below learning path and provide your suggestions 📌 PHASE 1: Core AI/ML & Python for AI (3-4 Months) Goal: Build a solid foundation in AI/ML with Python, focusing on practical applications. 1️⃣ Python for AI/ML (2-3 Weeks) Course: [Python for Data Science and Machine Learning Bootcamp]() (Udemy) Topics: Python, Pandas, NumPy, Matplotlib, Scikit-learn basics 2️⃣ Machine Learning Fundamentals (4-6 Weeks) Course: Machine Learning Specialization by Andrew Ng (C0ursera) Topics: Linear & logistic regression, decision trees, SVMs, overfitting, feature engineering Project: Build an ML model using Scikit-learn (e.g., predicting house prices) 3️⃣ Deep Learning & AI Basics (4-6 Weeks) Course: Deep Learning Specialization by Andrew Ng (C0ursera) Topics: Neural networks, CNNs, RNNs, transformers, generative AI (GPT, Stable Diffusion) Project: Train an image classifier using TensorFlow/Keras 📌 PHASE 2: AI/ML for Enterprise & Cloud Applications (3-4 Months) Goal: Learn how AI is integrated into cloud applications & enterprise solutions. 4️⃣ AI/ML Deployment & MLOps (4 Weeks) Course: MLOps Specialization by Andrew Ng (C0ursera) Topics: Model deployment, monitoring, CI/CD for ML, MLflow, TensorFlow Serving Project: Deploy an ML model as an API using FastAPI & Docker 5️⃣ AI/ML in Cloud (Azure, AWS, OpenAI APIs) (4-6 Weeks) Azure AI Services: Course: Microsoft AI Fundamentals (C0ursera) Topics: Azure ML, Azure OpenAI API, Cognitive Services AWS AI Services: Course: [AWS Certified Machine Learning – Specialty]() (Udemy) Topics: AWS Sagemaker, AI workflows, AutoML 📌 PHASE 3: AI Applications in Software Development & Future Trends (Ongoing Learning) Goal: Explore AI-powered tools & future-ready AI applications. 6️⃣ Generative AI & LLMs (ChatGPT, GPT-4, LangChain, RAG, Vector DBs) (4 Weeks) Course: [ChatGPT Prompt Engineering for Developers]() (DeepLearning.AI) Topics: LangChain, fine-tuning, RAG (Retrieval-Augmented Generation) Project: Build an LLM-based chatbot with Pinecone + OpenAI API 7️⃣ AI-Powered Search & Recommendations (Semantic Search, Personalization) (4 Weeks) Course: [Building Recommendation Systems with Python]() (Udemy) Topics: Collaborative filtering, knowledge graphs, AI search 8️⃣ AI-Driven Software Development (Copilot, AI Code Generation, Security) (Ongoing) Course: AI-Powered Software Engineering (C0ursera) Topics: AI code completion, AI-powered security scanning 🚀 Final Step: Hands-on Projects & Portfolio Once comfortable, work on real-world AI projects: AI-powered document processing (OCR + LLM) AI-enhanced search (Vector Databases) Automated ML pipelines with MLOps Enterprise AI Chatbot using LLMs ⏳ Suggested Timeline 📅 6-9 Months Total (10-12 hours/week) 1️⃣ Core ML & Python (3-4 months) 2️⃣ Enterprise AI/ML & Cloud (3-4 months) 3️⃣ AI Future Trends & Applications (Ongoing) Would you like a customized plan with weekly breakdowns? 🚀

I'm Building an "AiExecutiveSuperAgent_Systems_Interface" between humanity and the Ai world, as well as each other... Let's Talk?

Ok... So look... This one is pretty crazy... I'm building an Ai Interface that knows me better than I know myself - Check, lots of people have this, either in reality with employees and family members, or with ai intelligence. But it doesn't just know Me... It knows how to talk with Me. It understands my language, because I've trained it to. I've also trained it to translate that to all my clients and HumanAgents, soon to become RobotAgents... The RESULT: I can literally just spend 1-18 hours talking to it, and things get DONE. Most of that time, I just say EXECUTE, or ENGAGE, or DRAFT, or DISPATCH. I feel like a secret agent communicating in codes with his agency 😂 Not great for the paranoiac in me, but it's easy to get that part under control, ya'll. It's like having a team of 10,000 people, all available 24/7, all perfectly synchronised to each other's communication styles, preferences and ultimately: WHAT DO YOU NEED ME TO DO. At the end of the it all, having run my single COMMAND through a thousand of those people, a Document is prepared that outlines the next 3 stages of the plan, along with instructions to the whole team for how to ENACT it. Sounds rather grand and wonderful... Even when I simply use it to help me come up with a filing system for my creative work... \\\\\\\\\\\\\\\\\\\\\\ Here's my current VISION, why I'm doing this AND why I'm doing it publicly despite it being top secret. VISION To create an army of User-Owned and Operated "AiSuperAgencies" which gather intelligence on the user, securely file and analyse it, and then construct a sub-army of agents and tools that work together to produce the desired output, for any Function in the Personal and Professional Lives of EVERYONE, EVERYWHERE, in 3-5 Years. To start, I'm building it for me and the 5-10 cleaners who've made it to Level 1 in my access system. They were sick of toxic employers, tyrannical agencies and greedy customers. They gathered around us (many came in, many went out, few stayed, took about a year for our core team of 3 Level 2 Cleaners. My goal has always been to never employ anyone. Just me, my Partner and the Cleaners. All Shared Owners in the system for delivering the right cleaner to the right house in our town, at the right time and without any dramas or arguments... I have a personal talent for resolving disputes, which has made working for and buying from my business a mostly enjoyable and upbeat experience, with a touch of mystery and a feeling that you're part of something big! It is a business that ran on Me. I put in my time, every day, building automated tool after automated tool. Hiring a contractor to do a job, scratching my head when it didn't add enough value to pay for itself, then just doing it myself again. I wanted to solve that problem. I'm trusting that the few who hear about it who actually see the potential, will just come join us, no dramas, just cool people partnering up! And those that don't, won't. No one could steal it, because it's Mine, and I'll just change the keys anyway loser! Enjoy digging through my past, you lunatic! I'm out here living Now. Anyways... It's lonely around here. I have a cleaning business that I run from my laptop, which means I can live anywhere, but I still had this big problem of time... NOT ENOUGH Oh Wait. It's Here.

Built a Free AI Fitness Planner - From Passion to Product with No Traditional Coding

I posted this in r/entrepreneur as well but figured this is a great place too. I am looking to get your thoughts on this project and maybe some ideas as well. I wanted to share my journey of creating a free ai-powered workout planning tool with bolt. new and very minimal coding skills. It has taken me probably 4 days in total to complete and get to a point I am happy with. Many improvements coming but want to get it out there for some feedback and testing. I have been going to the gym for years and at this point my routines have gotten stale. I end up doing the same sets of exercises and repetitions over and over. I figured why not let chat gpt or some AI software help me develop or at least recommend different exercises. I was then was recommended youtube videos on creating your own web application without any coding. I will say it does take some coding knowledge, not that I am editing it myself, but I know what its trying to do and can prompt it correctly. I am still struggling with some things like integrating stripe for subscriptions so I only have it set up for donations currently. I dont mind it being free as I would like everyone the opportunity to help develop their own workouts. current cost breakdown to create: bolt. new credits - $100/month (gonna drop to the $20 now that its complete) supabase database - $35/month netlify domain - $11.99/year If anyone is interested or has questions feel free to let me know. It is called fitfocuscalendar. com this can all be done even cheaper using their free options but might take a lot more time depending on the complexity of the application as there are not a lot of free credits to code with each month and the supabase free database plan it pretty limited on size. title was AI generated.

Why isn't there automated AI data cleaning software already?

I've been getting into machine learning and data science, and I keep wondering: why isn't there more automated AI data cleaning software? I know there are some tools out there, but it feels like we’re missing a fully automated, easy-to-use solution. Data cleaning is such a crucial part of any ML project, so it seems like this should be a no-brainer.

Built a multi-agent AI mental health assistant (7 agents, backend automated, no-code stack)

Been working on this little side project and finally got it to a working version. It’s an AI-powered mental health assistant — not just a chatbot, but a system that can retrieve user history, analyze input, access data in real-time, and suggest personalized treatment plans. UI Chat Tech stack: Loveable + Momen How it’s structured: It uses 7 specialized AI agents, each responsible for a niche task — chat, generate professional responses, summarize user info, classify intent, etc. Agent Team The main agent (the chat one) will call other agents in the backend via automated workflows. It keeps track of user data (symptoms, conversations, medical history) and updates it in real time — all triggered automatically. Everything runs in the backend to reduce manual steps and minimize errors. How it’s built: Started by drafting the UI with Loveable AI — it auto-generated a 7-page interface from a product brief, which saved me time. (Didn’t use it for the live app though — good for prototyping, but I wanted more control for complex backend workflows.) Rebuilt the UI and database in Momen, since I needed deeper control over data flow and backend logic. The entire AI agent system and backend workflows were built in Momen as well. So I can make the agents collaborate with each other. The main chat agent invokes backend workflows to call other agents when needed. Entire flow looks like this: the user sends a message, the system: → pulls in the latest user data→ triggers the right agent(s) based on the input→ responds in real-time→ quietly summarizes and updates everything in the background. FlowChart It’s still an MVP, but the multi-agent setup + automated backend feels pretty scalable.This was a super fun build and I learned a lot about orchestrating AI workflows. Would love any feedback or thoughts on how to improve this.

The directory boilerplate Mkdirs has run for 100 days making $19K now, AMA

Hello everyone, I posted my product Mkdirs (How I made $2K+ in 10 days after launching Mkdirs) in r/SideProject before, and now 100 days passed, I am here to share some updates about this product. Please allow me to introduce Mkdirs first, it is a directory boilerplate, packed with AI, Listings, Payment, Submission, CMS, Blog, Authentication, Newsletter, SEO, Themes and more. https://mkdirs.com I launced it 3 months ago, and gained 160+ customers, who have launched 40+ directories so far. Recently the Mkdirs template supports submissions with AI assistance to improve efficiency. Simply enter the URL, and the AI model will analyze the website content, generate the description and introduction (in Markdown format), assign categories and tags, detect and upload logo and image, making submissions and launch directories super fast! Thank you for the community, and feel free to ask me anything if you have any questions. mkdirs directory boilerplate, submission with AI assistance

I am building a free app to fight propaganda online. Need your help

So long story short I was recently bombarded with an insane amounts of right-wing propaganda online and Russian bots so I decided I can somehow simplify the validation of the facts that are posted by people online. I have made a research of tools that are currently available for that and I've found that ChatGpt is quite biased with some topics and it lacks data about latest issues even when search mode is enabled. At least it takes some time for it to update it's memory or something Then I've checked a Google Fact Check tools which were even worse. Bad UI... I had no idea how it validates things because usually proof links that Google provides are quite random. So I decided to build a tool that simplifies the research. The idea was simple - you have a claim - you paste it in app and it goes on web collects articles on topic then processes them with ai and makes a decision based on those articles. The app is running right now. It is completely free and no ads. Also it generates a small article where it tells about how it made a conclusion. Also I need your help - How can I make this app better? Also feel free to test your claims so that I can have more real data to tune this app on. I believe that this is something that is necessary for all of us especially in those crazy times! Here is the link - truthorfake.com https://preview.redd.it/vp5fbzpyfkne1.png?width=854&format=png&auto=webp&s=84df7913382634614814866c8df743d8378d28dd

Just hit $6k MRR, ask me anything

Hey everyone! After months (or years) of late nights, countless iterations, and endless learning, my side hustle just hit $6K MRR. It feels surreal to finally hit this milestone, and I wanted to share it with the community that’s been a constant source of inspiration and motivation. I’d love to pay it forward, answer questions, and chat with anyone on a similar journey! Whether you’re just starting out, scaling, or stuck in the grind, ask me anything about: What worked and what didn’t during the early stages How I managed time and stress with a full-time job Building a customer base and retention strategies Tools, tech stack, or marketing strategies that got me here How I’m planning to scale further from here Feel free to ask about the challenges too—because there have been many! 😂 Thanks to everyone who’s been part of the community here—it’s helped me push through. Let’s chat and grow together! 🚀 My app: https://dietapp.ai https://preview.redd.it/0d3mu80fd5xd1.png?width=972&format=png&auto=webp&s=50139d47258bc5910ea51a12d0bff2335d0e9909

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

My Marketing App made $10,000 in 2024. Here is how I target to make $100,000 in 2025:

You totally get me, I think. It’s a bizarre feeling when you build something, and people appreciate it and are even ready to pay! Pleasant though) In early 2024 my mate and I created a marketing tool that generates ads, content and strategy blocks with a click – Aiter.io. Users can just insert a URL, hit the button and everything is ready. TBH, I built this tool because I’m too lazy to chat with ChatGPT) https://preview.redd.it/ew2kud7ceyde1.png?width=1140&format=png&auto=webp&s=f3fe5b67075858cea3d52278e8063113efa3b97e In 2024 we made $10,000, here is what worked for us: AI directories. Still is the best channel of traffic and clients for us. We listed on TAAFT and other directories scrape TAAFT, so, eventually, we became listed on all major ones. I wrote a Reddit post earlier that explained this process in detail. Email marketing. Gosh, I thought it was dead – I have never been so wrong! We set up automatic emails that share marketing insights and they have a \~25% open rate + consistently convert people. It works great. Product marketing. Having a free version really helps with word-of-mouth and leads, which can be converted via email. Also, we consistently worked on product improvement. I’d say, that our free updates give people a feeling that the devs care about their stuff that’s why they are more confident investing in it. Google Ads. TBH, we had a shitty landing page all the time because were busy with the product. So, Google Ads didn’t work well for us. But we’ve launched the 2.0 version which has a better landing page, and will try it again. Influencers. Worked well for us, but we didn’t pay a dime for this. They just found our tool on directories and created videos about Aiter, so it was a sporadic marketing channel for us. We hope to change it in 2025. We see that our product works and attracts the audience, so we want to deliver and get more in 2025. Here is the plan: Product: add ad banners and video generation. So far, we generate only text data and it’s not so valuable in the time of ChatGPT and Claude. But to generate a high-quality ad banner is still challenging, so we put this on our roadmap. Another feature – one-click market analysis to get marketing insights. Become a TOP50 tool on TAAFT. We’ve become a top tool in our category (content generation) but will need to promote our profile on the profile far more aggressively to get into TOP50 Email marketing. We are fools because we almost didn’t have product emails that explain how it works. Will fix it. Also, we are considering participating more in paid newsletters, like collaborating with Substack influencers. Youtube marketing. Search for low-tail marketing keywords on YouTube and create videos on them, placing my product in them. Blog. Our new platform is Webflow which gives a lot of flexibility in terms of blogging. So, we will repeat the YouTube strategy with blogging. Paid marketing. With an updated landing page, we hope that paid campaigns will work better. We plan to launch campaigns that target different jobs to be done and customer objections to find the right message. Product Management. For 2025, our two key product metrics are retention and product activation rate. For this, we plan to simplify onboarding and make it simpler as well as conduct a lot of in-depth interviews to understand how we can retain users better. Funding. All of this exciting stuff requires money, so we are in the process of securing funding (fingers crossed). Having an indie project is exciting and invigorating. With all these activities, I hope we will achieve the goal of $100,000 in 2025. And what are your goals and marketing steps for 2025? Or maybe you could share some exciting marketing ideas I overlooked?

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!

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 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.

New Year Resolution: I Will Generate Some Viable SaaS Ideas AND Help You Become a Brand New AI Startup Founder Within 7 Days

Over the Christmas period, I conceived and debuted on some reddit communities, The 7-Day Startup Challenge. The feedback I got from the various communities have been nothing short of fantastic! The 7-Day Startup Challenge simply means leveraging the power of no code platforms like Bubble, Flutterflow, Glide, Thunkable, Softr etc. along with AI APIs to build a functioning MicroSaaS/SaaS within 7 days. I can tailor this around your interests or hobbies so you are more passionate about your new startup. Whether you're a startup novice or a veteran, I am happy to work with you every step of the way. I will work with you from validating and refining your idea(s) to building and publishing your app! I can even work with you on a viable marketing strategy that will help fetch your new startup some revenue within the next 10 to 45 days. Here's what I will provide as part of The 7-Day Startup Challenge A fully validated and refined version of your idea described in technical terms in a shared document A startup name, domain and logo (if you don't have one already) A landing page to capture pre-sign ups, generate some early buzz and index your app on search engines Figma files showing the design of your app(s) Web app (dependent on whether your startup idea requires a web app or a mobile app instead)) iOS app (dependent on whether your startup idea requires a web app or a mobile app instead) Android app (dependent on whether your startup idea requires a web app or a mobile app instead) 1-month of in scope support to fix any bugs and address any issues An outlined marketing strategy you can implement to grow your startup both short and long term. As per tentative timelines, you can expect the following deliverables on schedule Day 1: Secure digital assets such as domain name, hosting, logo etc.; deliver validated and refined version of your startup idea Day 2-3: Landing page & Figma files Day 1-5/6: Build your apps (web app and/or iOS and Android app) Day 6: Evaluations and review if necessary; demo day Day 7: Live launch on web; publish on Android and iOS app stores PS: For more sophisticated ideas (non MicroSaaS), kindly allow approx. 30 days for delivery. I can be as hands on or hands off as you wish. Meaning I can do all the work whilst you sit back and wait for the results OR I can work with you every step of the way to deliver on your demands. For high potential startup ideas, I can partner with you long term to build them out together. I have to be selective because I'm unable to partner together on every single idea out there. Outside of a partnership, all the digital assets (startup name, logo, web app, mobile app etc.) are 100% owned by you. If building an AI SaaS startup via the outlined strategy sounds intriguing enough to you, feel free to send me a DM with any questions you have!

Does anyone else struggle to communicate with Devs as a non tecnical founder/manager?

Hey everyone, I'm an dev agency owner and, honestly, sometimes I feel like I'm speaking a different language when trying to communicate with my development team. It's not just about understanding the technical jargon—they're great at explaining things—but more about converting my ideas and requirements into something actionable and clear for them. I've been thinking a lot about this challenge and wondering if others are in the same boat. Do you ever find yourself struggling to get your thoughts across or worrying that important details might be lost in translation? To tackle this issue, I've been toying with the idea of creating a tool—kind of like Jira, but specifically designed for non-technical folks. The idea is to help bridge the communication gap by making it easier to convert our thoughts into dev-friendly action items using chatGPT. It could offer templates, guided prompts, and maybe even some AI assistance to ensure nothing gets lost in translation. Before I dive too deep into this, I wanted to get a sense from this community: Do you face similar communication challenges with your dev teams? What tools or methods have you found helpful in bridging this gap? Would a tool like the one I'm envisioning be something you'd find valuable? Looking forward to hearing your thoughts and experiences! Thanks,

Introducing Vest: Your AI-Powered Due Diligence Partner - Looking for feedback!

TLDR; We are introducing Vest, an AI powered due-diligence and stock recommendation platform. We have bootstrapped ourselves so far and are wanting to get as much feedback from Reddit as we can to see where we can improve, but also what we are doing right. So please have a look around, give us feedback and if you like it, feel free to use it. Hi Reddit, My name is Drian and I'm one of the founders of Vest. We believe we are crafting something special at Vest and we want to get the word out and gather as much feedback as possible! Our major goal at Vest is to help new retail investors make sense of the investment landscape and get AI powered assistance, or even help experienced investors get confirmation of their potential moves. Overall, we want people to start their journey to financial freedom and not be daunted by the complexity of it. So how do we do this? Vest is a user-friendly service that harnesses fundamental metrics, social and news sentiment, and technical analysis, that we feed into some advanced AI models to generate clear buy, sell, or hold signals for US-based (for now!) stocks, offering our users transparent due-diligence for confident investing. The service is currently free with no ads - however, at some point we do plan on adding a paid tier. What's included: &#x200B; Financial Metrics. Our financial metrics take all the potentially complex mathematical equations and present the fundamentals of a company to users in a simple 1 pager, with a score displaying if the metric is positive for a stock. We also provide publicly available analyst ratings from investment banks as well as price targets they have set. News Sentiment. We take publications about a specific stock from new articles, journals and socials and give these all a rating to determine if social sentiment is positive around a stock or not. Each article and its rating is visible to our users through through our dashboard. AI assisted Stock Signals. We have developed an algorithm to take all the metrics, sentiment and technical analysis we collate and analyze this with historic performance data for every stock to attempt to figure out if a stock is undervalued (great time to buy) or overvalued (great time to sell). 155 US stock tickers and counting. We currently have trained our models for around 155 US based stocks on the NASDAQ and NYSE exchanges. As we get more funding/runway we do plan on adding more, with the eventual goal to expand to more exchanges, countries and securities. Knowledge base and community. Our knowledge base & community contains explanations and articles for all metrics and the other good stuff behind Vest. We don’t want to just tell users what to do, but to also assist in their financial education. We hope our knowledge base can also become a thriving community where users can interact with us and each, ask questions around investing and keep gaining knowledge. Is it 100% accurate? Absolutely not. While we do a pretty great job at tracking and surfacing signals, we are not presenting a fool-proof, silver bullet with a guarantee here - rather a starting point for users to make more informed decisions, find potential new investment opportunities and hopefully learn about investing as they do so. We encourage our users to do their own research and due-diligence and not just take our signals as gospel - we know each and every person has a different risk appetite and goals, and we encourage you to use Vest in a way that fits with your own financial goals and risk appetite. We also display our win rates, average returns, and comparisons with buy and hold for each stock - and we are transparent about it when we’ve fallen short. Next steps: &#x200B; Hope over to vestapp.ai and sign-up From the dashboard, play around, inspect our stock information and add some stocks to your watchlist. If you like what you see, and you’ve done your homework - use your favourite brokerage account to make an investment and watch Vest for changes in a stocks signals. If you don’t have one, we have a pop-up when you click buy/sell on any given stock with some non-affiliated brokerage options for the US, Australia and New Zealand - we don’t get a kickback from these brokerages, they are just what we’ve personally been using. FEEDBACK - We’re just getting started and we know the value of a fresh pair of eyes - our current mission is to get as much feedback as possible - anything you think of please send it through here or on the dedicated feedback form on our website in the sidebar on the left. Features we’re working on We're quietly thrilled about the direction Vest is headed, and we want to give you a sneak peek of what's in store for the next couple of quarters. Some of these may roll out as premium features, but we're diligently fine-tuning the details. Here's what you can expect: &#x200B; Insider Trading Insights: Get daily reports on major stock moves by whales and company insiders. Institutional Holders: We're adding daily reports on institutional holders, keeping you informed about their moves. Lobbying Activity: We're actively working on daily updates about lobbying activities, so you can stay informed. Government Contracts Data: We'll provide a quarterly snapshot of government contract values for the companies you're tracking. US Congress Stock Activity: Keep an eye on daily trading actions of House and Senate members. Daily Summaries & Signal Alerts: We're currently hard at work on this feature. Soon, receive daily email summaries covering signals, watchlist updates, and key news. Personalized Risk Management: Tailor signals to match your unique risk management strategy. Your investments, your way. AI Assistant: Our LLM integration is almost ready, allowing you to ask it straightforward questions about particular securities in plain English. It will provide you with real-time context on fundamentals, news, and all the metrics and data points we monitor.

a product code-to-pitch deck in 60 seconds. could use some beta testers for this.

following up to my recent post about ai sales guide for new founders! so, in about 14 days, I'm launching a (hopeful) game-changer for dev/technical founders. you simply input your short (or long, your choice) product description (text, code, GitHub README snippet) and receive a tailored, professional-grade downloadable deck in under a minute. really good when you need a quick explainer (for potential customers, investors, etc.) I'm building this b/c trying to explain your product to non-devs in clear and compelling way is very hard, and I really want to make this easier for new founders. If you're interested in joining my upcoming beta test group for this, feel free to DM me.

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.

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

Looking for a technical co-founder to build LinkedIn’s rival

How do you connect with likeminded people? You see the polished wins everywhere, but what about the messy drafts , the awkward pitches and the moments you’re not sure you’ve got it right? Problem: The whole idea of founding and starting a business can be super intimidating for some people, specially those who don’t know any founders personally, those who don’t have a large network, those who don’t have rich parents with large networks, those not inserted in an entrepreneurial culture like in the US for example (which is my case). Sometimes all you need is the right support network, and too see others do what you want, to know that it’s possible! Everyone has an “ultimate guide” to make 7 figures or build a business on YouTube but NO ONE shoes you the HOW, just the results… I’ve tried joining founder communities, LinkedIn ,Reddit … you name it. Most of these founder communities are inaccessible for regular people and often ask for you to have an already existing business with a min ARR… or their simply geography based and if you’re not in a certain area you can’t really participate… As of LinkedIn… full of empty AI generated posts about how some random dude raised $10m in 7 days. Okay Jonathan, but what about the HOW?? How did you write your first pitch? How many rejection calls did you get? What is an MVP? There simply isn’t a platform out there to document your founding journey and find inspiration within a community of people who are doing the same as you. What better way to feel motivated then to see someone actually document their process? Solution: I’m working on building a social media platform for aspiring/founders to connect through the RAW, UNFILTERED process of turning ideas into reality in REAL time. It’s all gonna be around the “building in public “ concept and content creation. Picture an instagram/tiktok profile where instead of seeing someone’s dog you see them documenting their founding process—from the moment they had the idea, to the moment they launched, you’re going to see the successes, the fails, the rejected calls, all documented through actual content and not some AI generated LinkedIn post. Imagine if you wanted to learn about how Steve Jobs started Apple , you could simply go through his profile on this app—exactly. To make sure all interactions are meaningful people would have to apply. It’s a truly curated community, with REAL people, building REAL things in REAL time, and not just tell us the story of how they did it… Audience: I’m targeting people who have a burning desire of building a business and early stage founders starting their founder journeys, that don’t have a support network and simply don’t know where to start. People who are tired of watching 30 min “ultimate guides “ on how to make it on YouTube from “business gurus” selling courses. People who haven’t reached the min ARR required to join an “exclusive “ founder a community. People who can’t simply just move to the US to get into the “exclusive” YC combinator. People who want to connect with real people building real things and not anonymous people on Reddit, or LinkedIn influencers again trying to promote their services. I believe in the idea because I’m also part of my audience. Have always wanted to start my own thing just never knew how to and where to find a community of likeminded people . I don’t know any founders myself, I come from a non-entrepreneurial society and I’d pay good money to access a community of REAL passionate founders building REAL things, in REAL time. This would be my first ever business, and I want to share my journey building it and hopefully inspire others to just start so I’ve created a mailing list to keep anyone interested in the project updated on my fails , learnings and successes. I’m not worried about “making it” but just “starting” and hopefully reach the right audience and inspire anyone to start whatever they have marinating in their thoughts. If you’re a founder struggling with staying consistent or an aspiring founder with an insane desire of starting and don’t know how to start, I’d love to get your feedback on what’s stopping you, your challenges starting out and what you’d find useful in such platform. And finally would this be something that interests you?? Feel free to subscribe to get new updates 🫶🏼 : https://mailchi.mp/037c56b89994/d-founder PS: casually looking for a technical co-founder

Things I did to promote my product, and how they turned out

(I will share more updates in the future, you can find me on Twitter and/or Mastodon) Ask any ten indie developers about the toughest part of their job, and nine will likely say "marketing." I recently got a taste of this firsthand when I launched Xylect. Here's a rundown of my promotional attempts - hopefully, my experiences can help fellow developers out there. Podcast Community (✅ Success) I kicked things off by promoting Xylect in my podcast listener group. It wasn't a blockbuster, but I managed to sell a few copies and got some invaluable feedback from friends. Shoutout to those early supporters! Reddit r/macapps (✅ Success) Having had some luck promoting open-source projects on Reddit before, I decided to make r/macapps my first stop in the English-speaking world. I made an app to help you automate boring tasks with one click This post turned out to be a hit! I sold about ten copies and got a ton of useful feedback. Users pointed out compatibility issues with PopClip and suggested improvements for the website. One Italian user even requested localization, which I happily added. https://preview.redd.it/y4fuwh6hleqd1.png?width=959&format=png&auto=webp&s=7bb1b68cbf8a4f94998999e0832b9b7bd85bac67 https://preview.redd.it/8uu4cmyhleqd1.png?width=683&format=png&auto=webp&s=8f1744636aee8074b0e7491a334ef06076b143b0 I also got an intriguing email from a French user - more on that later. More Reddit Posts (❌ Failure) Riding high on my r/macapps success, I branched out to r/SideProject, r/Entrepreneur, and r/indiehackers. These subreddits frown upon direct self-promotion, so I took a softer approach with an article: The unexpected emotional cost of being an indiehacker While the article was heartfelt, it fell flat. Across all three posts, I got a grand total of three comments - two of which were complaints about the font size on mobile. Needless to say, I didn't sell a single copy. Hacker News (❌ Failure) As one of the tech world's major forums, I had to give Hacker News a shot. I wasn't too optimistic, given my past experiences there. Posting on HN feels like a mix of luck and dark magic. As expected, my post vanished without a trace - no comments, no sales. I might give it another go someday. If you're curious, you can check out my previous HN submissions. Tools Directory Websites (❌ Failure) These sites have a simple premise: you list your app, they display it. Seemed like an easy way to get some backlinks, right? Well, I learned the hard way that it's not that simple. I stumbled upon a Reddit post where someone claimed to have made a killing with their directory site in just a few days. The catch? Each listing cost $19. The site had a handful of apps listed, so I thought, "Why not? Early bird gets the worm." I paid up and listed Xylect. Spoiler alert: all I got was $19 poorer 🥲 Lesson learned: These directory sites won't magically sell your product. At best, they're just glorified backlinks. There might be some value in paid promotions on these platforms, but I can't speak to that from experience. V2EX (❌ Failure) After striking out in the English-speaking world, I turned my attention to the Chinese market, starting with V2EX (think of it as China's hybrid of HN and Reddit). This turned out to be my most unexpected flop. Here's the post: [\[Launch Discount\] Mac's most powerful AI search (Perplexity + Wikipedia + Google), boost your efficiency tenfold with one click. No API key required, no prompt needed, no token limit 🔥 - V2EX](https://www.v2ex.com/t/1064930?p=1#reply36) I'd seen decent engagement on other promo posts, so I had high hopes. I posted late at night (US time) and went to bed dreaming of waking up to a flood of comments. Reality check: The next morning, I had exactly one reply - from Kilerd, a loyal podcast listener showing some love. I was baffled. After re-reading my post, I realized I'd missed a crucial element: promo codes. A quick scan of popular posts confirmed my suspicion. Nearly every successful promo post was offering codes, and most comments were just base64-encoded email addresses. Talk about a facepalm moment. I scrambled to add a note about an upcoming free trial and invited users to drop their emails. This got the ball rolling with some code requests, but by then, the damage was done. The post fizzled out, and I didn't sell a single copy 🫠 A French Friend's Newsletter (✅ Success) At this point, my promotional efforts were looking pretty grim. My sales chart had a depressing stretch of flatline. But then, a glimmer of hope appeared in my inbox. Remember that French user I mentioned earlier? He ran a newsletter called vvmac and offered to feature Xylect if I added French support and sent him a free license. It was an offer I couldn't refuse. What followed was a crash course in French localization (thank you, Claude!) and the start of an incredible partnership. This guy was the most thorough beta tester I've ever encountered. We exchanged over sixty emails, covering everything from translations to UI tweaks to bug fixes. His response time was lightning-fast - I'd fix a bug, and five minutes later, he'd confirm it was sorted. The result? A much-improved Xylect and a glowing feature in his newsletter. https://preview.redd.it/ylcq2wxoleqd1.png?width=991&format=png&auto=webp&s=ee395110f50417d5c7f61318f27bf3dc30247809 I'm still in awe of his dedication. He single-handedly transformed Xylect from a buggy mess into a polished product. I'll be forever grateful for his help. The newsletter feature led to a few more sales, but honestly, that felt like a bonus at that point. Influencers (❌ Failure) I knew from the start that to really make waves, I'd need influencer backing. So, I added a note offering free licenses to content creators willing to collaborate. https://preview.redd.it/tyb2m1rqleqd1.png?width=799&format=png&auto=webp&s=56eabf126e772515322595613c546e6ba69fb431 I did get one taker: Hey, I'll be honest, I am not a huge content creator but I think I put a lot of effort in evaluating and figuring out which apps work... So I was wondering if I could get a license in case you are willing to share it. Thank you for considering. Have a great weekend. But I knew I needed to aim higher. With the new French localization, I thought I'd try my luck with some French-speaking Mac YouTubers. I crafted emails highlighting how Xylect could help their French audience with English content. https://preview.redd.it/07oqzemrleqd1.png?width=542&format=png&auto=webp&s=3d160c1d149f28e9029816a277c6ab2496fcd57e After days of silence, I got one reply. It was... not what I was hoping for: Hi, Thank you for your proposal. I can help you to promote your service on Tiktok, Instagram et YouTube, with unique short video. Price for this project is 3500€. Unless I've completely lost my marbles, there's no way I'm dropping 3500€ on promotion. Sure, given their follower count (YouTube: 348K, TikTok: 2.7M, Instagram: 400K), it's not an outrageous ask. For some products, it might even be worth it. But for Xylect? No way. I also reached out to a Chinese influencer on Xiaohongshu, but they weren't interested. Back to the drawing board. Conclusion If you've made it this far, you've probably realized this isn't exactly a success story. My search for effective promotional channels came up largely empty-handed. I'd naively thought that my success with open-source projects would translate seamlessly to the indie dev world. Boy, was I wrong. As I mentioned in my previous article, open-source projects create a dynamic where users feel indebted to developers for their free labor. But in the commercial world of indie development, that dynamic completely flips. While this experience was often frustrating, it was also enlightening - which was kind of the point. As my first foray into indie development, my main goal was to learn the ropes and understand the process. Making money would've been nice, sure, but it wasn't my primary focus. Thanks for sticking with me through this post. I will share more updates in the future, you can follow me on  Twitter and/or Mastodon.

Most Startup Ideas Die Before They Even Start—Here’s Why (And How I Solved It)

Hey all 👋 Last year, I had an idea I was excited about. I spent weeks brainstorming, validating it, searching for the perfect name, and struggling to create even a decent landing page. By the time I was ready to launch, I’d already lost momentum. Sound familiar? The reality is, many great ideas never see the light of day—not because they’re bad, but because the process of getting started is overwhelming. You get stuck on validation, spend way too much time searching for a name, and designing a logo or building a landing page becomes a huge roadblock. That got me thinking… What if there was a way to make this 10x easier? That’s why I built StarterPilot—an AI-powered tool designed to help entrepreneurs like us go from idea to launch effortlessly. 1-Validates your idea – Get instant feedback on demand, feasibility, and risks. 2-Generates unique names – AI finds names and checks domain/social media availability. 3-Creates logos – Build a custom logo with just a few clicks. 4-Builds landing pages – Generate a professional landing page in minutes. I built this to eliminate the friction that keeps good ideas from ever becoming real businesses. Would love to hear your thoughts, or if you’ve run into any of these challenges, feel free to share! Also, if you’re curious, check out StarterPilot here: link.

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

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

Just Launched My AI Agents Directory - Roast Away!

Hey Reddit! After countless hours of coding, caffeine-fueled nights, and a few nervous breakdowns, I’ve finally launched my side project: an AI Agents Directory! 🎉 It's a platform where you can discover and read about various AI agents. We’ve got 40+ agents listed so far, and I'm looking for some honest feedback from this awesome community. Here’s what it does: Instantly search and filter AI agents Upvote AI Agent Read detailed descriptions and use cases Submit your own AI agents I know it’s not perfect and probably has a million things that could be better. So, I'm here to ask you to roast it! Tear it apart, tell me what's terrible, what’s good, and how I can make it better. Feel free to check it out here: https://aiagentsdirectory.com/ Thanks in advance for your brutal honesty! 🙏 P.S. Be gentle… okay, maybe not. 😅 https://preview.redd.it/rpwp38sp47dd1.png?width=1592&format=png&auto=webp&s=9cf54385f1a9cc61b6a746f3ea38f8349d35b5a1

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/

PlumbingJobs.com - I launched a niche job board with hand-curated jobs for plumbers. Here's the summary of how it's going after the 3rd month

On October 12th 2024, I launched PlumbingJobs.com, and this is my first update (January 2025) in what I hope will be a long journey. To stay accountable and track progress, I’ll be sharing monthly updates about the site's stats, achievements, challenges, and my plans moving forward. While these posts are mostly to document the journey, I hope they’ll also be helpful to others, especially members of r/SideProject who might be working on their own first online projects. If this post isn’t a good fit for this subreddit, I’m happy to remove it or move updates elsewhere. The goal for PlumbingJobs.com is clear: to become the #1 job board for plumber jobs, featuring hand-picked opportunities the plumbing industry. Let’s dive right in: Statistics update ~ 4th Quarter of 2024 |\-|October|November|December| |:-|:-|:-|:-| |Jobs Posted:|2|16|43| |Paid Post:|0|2|2| |Free Post:|0|1|2| |Visitors:|72|138|1,164| |Avg. Time Per Visit:|1 min. 24 sec|2 min. 15 sec|3 min. 41 sec| |Pageviews:|196|308|2,590| |Avg. Actions:|1.1|2.3|2.3| |Bounce Rate:|87%|73%|40%| I'm not a very technical guy and I don't know how to code. So the best way for me was learning to build it using Wordpress through YouTube. Also, I believe in the power of a great .COM domain name, and the stats from the first three months have only reinforced that belief: 49.2% of traffic comes directly from users typing the URL into their browsers. 48% of traffic is from search engines like Google and Bing. The remaining 1.8% comes from social media and other backlinks. Pricing Tiers and Early Wins I offer three pricing tiers for job listings: Free Listing: Basic exposure for job openings. Silver Listing ($45): Greater visibility and placement on the site. Gold Listing ($95): Premium visibility and enhanced promotion. To my surprise, my very first sale in October was a Gold Listing! That initial $95 sale was the motivation I needed to keep building. Later that month, I sold a Silver Listing, bringing my total revenue for October to $140. The same revenue was generated in December 2024, showing consistent early interest. Steps Taken in December To boost SEO and add value to the site, I created a Plumbing Directory, featuring: Plumbing companies across the U.S. Their stories, contact information, logos, addresses, business hours, and more. This directory serves as free marketing for these businesses and increases the likelihood they’ll discover my site and support it by posting job openings. Plans Moving Forward Social Media Marketing: I plan to automate posts using AI to expand reach and drive more traffic to the site. Consistency in Job Postings: I’m committed to posting 2–3 plumbing jobs daily to keep the site fresh and useful for plumbers seeking work. Looking forward to grow this niche job board slowly but surely this 2025. If you have any questions, concerns, come across glitches - feel free to reach out, happy to chat. Thank you all again, and see you in a month. Romel@plumbingjobs.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!

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

Building in public: v2 of an AI tool to help businesses easily review their business contracts for legal risks

You can check out Cobrief here: https://www.cobrief.app/ It's pretty cheap to begin with at $29.99 / month because the whole point is to cater for the mass SMB market (that can't otherwise afford expensive lawyers or outside counsel). Would any owner/managers on this thread be interested in using this kinda tool to do the initial heavy-lifting rather than (A) Googling or (B) Self-reviewing their contracts? Super keen to hear from you :) PS. Feel free to roast, honest opinions welcome

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

Building in public: v2 of an AI tool to help businesses easily review their business contracts for legal risks

You can check out Cobrief here: https://www.cobrief.app/ It's pretty cheap to begin with at $29.99 / month because the whole point is to cater for the mass SMB market (that can't otherwise afford expensive lawyers or outside counsel). Would any owner/managers on this thread be interested in using this kinda tool to do the initial heavy-lifting rather than (A) Googling or (B) Self-reviewing their contracts? Super keen to hear from you :) PS. Feel free to roast, honest opinions welcome

I built an AI Stock Analysis Tool

Hi Reddit, TL;DR: I am sharing the tool I built to assist me with my investments I have been investing for over a decade, and I have always struggled with: Putting the time to do actual research Trusting analyst’s recommendations To \ invest \ we want to make sure that the price is right and the company will keep improving. How do we know that “the price is right?” How can we predict that the company will perform better in the future? To answer the above, we have to look at the company’s financials and their trends. We have to compare the company with its peers/competitors. We should understand its business model, the sector and geography the company evolves in and the perspective of the economy in general. We can also look at additional signals like insiders selling or buying. Just for one investment, this is already a lot of work. And a work that we need to repeat every time there is a significant change - for example, a significant price change from our last analysis or new quarterly results, etc. To automate all the above, I have built a stock analysis tool and have been using it the past years for my own investments. I have been adding LLMs agents (GPT 4o & Claude 3.5) to perform the qualitative analysis. Recently, I decided to share it and keep on building it in public. In this initial version, you can get the summary of the stock analysis my model generates. For now, it covers most of the S&P and Nasdaq stocks. Here is the link 👉 https://undervalued.ai If you are into investing yourself, please feel free to reach out. I would love to get your feedback and know more about your methodology.

I automated blog content for myself with AI - is it worth continuing?

I started building a blog content generation app on the side. I wanted to see how far I could push the quality and avoid google detecting AI content. I've been in the content industry for around 10 years as a dev but I've seen it change really quickly with AI. I sort of know what type of content ranks well and I thought let me see if I can automate this part that costs companies a ton of money from hiring freelancers, using SEO tools and paying for AI. I've now been posting my blogs for a month now and I've seen some decent results which I've attached. I do feel like I'm onto something but just want to know if it's worth pursuing, given how controversial AI content is? I know there are lots of alternatives out there doing this already, but quality is non-negotiable for me so I wanted to try it myself. https://preview.redd.it/rlbhuwz57fpe1.png?width=1920&format=png&auto=webp&s=7345ab5d5629bbba79ab88d930f7f0fde3fe9c6b

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] [R] sANNd: A New Neural Network Framework Using Trainable Iterators

sANNd sANNd is a lightweight, modular neural network library designed as a sandbox for experimenting with new ideas in artificial intelligence. The Mould Class: A Pythonic Building Block The Mould class is a core component of sANNd. It provides a Pythonic way to apply functions to data that’s bundled inside objects: Encapsulated Variables: Each Mould object holds a set of variables (for example, weights or parameters) inside it. This means related data is kept together in one place (the object), making the code organized and intuitive. Static Functions: A Mould class defines its operation as a static method – essentially a function that isn’t tied to a specific instance. This static function takes in inputs (and possibly other Mould objects’ variables) and produces an output. In simple terms, the Mould’s static method describes how to transform input data using the Mould’s internal variables. Pythonic Usage: Using static methods in this way is a clean, Pythonic design. You call the Mould’s function through the class, but it applies to the data in the object. This approach lets you clearly separate what the operation is (the logic in the static function) from which data it uses (the variables inside the Mould instance). Example: Imagine a Mould class called LinearMould that has a static function to compute a linear transformation (like y = W*x + b). An instance of LinearMould would hold specific W and b values, and you’d use the static method to apply that linear formula to an input. This gives you the convenience of object-oriented design (encapsulating W and b) with the clarity of a standalone function defining the math. Chaining Moulds for Complex Computations Moulds become even more powerful when you chain them together. You can connect multiple Moulds so that the output of one becomes the input of the next: Sequential Operations: Just like stacking layers in a neural network, you can place Moulds in sequence. For example, you might take the output from LinearMouldA and feed it into LinearMouldB. In code, this might look as simple as using the output of one call as the argument to the next. The design of sANNd makes this straightforward – the static function of each Mould knows how to handle the data coming in. Building Pipelines: By chaining Moulds, you create a pipeline of transformations. Each Mould handles one step of computation, and together they produce a final result. This could represent a multi-layer neural network, a data processing pipeline, or any custom sequence of operations you need. There’s no strict limit to how you can chain them; you have the freedom to combine Moulds in any order that makes sense for your experiment. Clarity and Modularity: Because each Mould is a self-contained piece (with its variables and function), chaining them doesn’t turn your code into a black box. You can inspect or modify any part of the chain easily. This modular design means you can insert, remove, or replace Moulds to see how it affects the overall computation, which is great for experimentation. Implicit Backward Path (Automatic Backpropagation) One major benefit of using chained Moulds is that they implicitly define the backward path for training with gradient descent (backpropagation): Automatic Gradient Flow: When you connect Moulds in a sequence for a forward pass (input → Mould A → Mould B → output), you’ve essentially defined a computation graph. sANNd uses this graph to handle the reverse computation automatically. In other words, if you calculate an error or loss based on the final output, sANNd can propagate that error backwards through each Mould in the chain. No Manual Backprop: You do not need to manually code how gradients flow through each Mould. The way you set up the Moulds’ static functions already determines how outputs depend on inputs and internal variables. sANNd leverages that to perform backpropagation. This is similar in spirit to how libraries like PyTorch/TF do “autograd,” but here it’s a natural result of the Mould chain architecture. Gradient Descent Ready: Because the backward path is established by the forward connections, you can apply gradient descent optimizations out of the box. For instance, you can adjust the weights inside each Mould based on the computed gradients to minimize your loss. The design ensures that each Mould’s contribution to the final error is tracked, so all parts of your model learn appropriately during training. In short, defining your model with Moulds means you get training capability for free. You focus on describing the forward computations, and sANNd handles the math behind learning from errors. Comparing sANNd to Traditional Frameworks sANNd’s approach is quite different from traditional Python-based neural network frameworks. Here’s how it stacks up against frameworks like TensorFlow, PyTorch, or Keras in terms of approach, flexibility, and intended use: Design Approach: Traditional frameworks use predefined layer classes and often build a computation graph behind the scenes. For example, Keras might have a Dense layer class, and TensorFlow might construct a static graph (in TF1) or use eager execution (in TF2). sANNd takes a simpler approach – it uses plain Python classes and static functions (Moulds) to define computations. There’s no need to learn a new graph syntax or decorators; if you know Python functions and classes, you can read and write sANNd models. This makes the internal workings more transparent and easier to follow. Flexibility: While frameworks like PyTorch and TensorFlow are very powerful, they can introduce a lot of boilerplate and assume you’re building typical architectures. sANNd is extremely modular and flexible. You aren’t limited to the layers someone else defined – you can create any operation you want as a Mould. Want to experiment with a novel activation function or a custom recurrent connection? Just define it in a Mould. There’s less magic and abstraction obscuring your code, so unconventional model structures are easier to implement. (Of course, major frameworks can also be extended, but sANNd makes this feel more natural by staying within standard Python paradigms.) Intended Use: sANNd is intended for experimentation and research. It’s like a toolkit for tinkering. You get fine-grained control over every part of the network, which is ideal for trying out bold new ideas that don’t fit the mold of common deep learning models. In contrast, TensorFlow/PyTorch shine in production environments and large-scale training – they are optimized (GPU support, highly efficient tensor operations) and come with many utilities for things like data loading, distributed training, etc. sANNd doesn’t aim to replace them for those heavy-lifting tasks. Instead, it’s meant for when you need a lighter, more interpretable setup to prototype concepts. You might use sANNd to prove out a concept or test a hypothesis in AI research, and later switch to a bigger framework if you need to scale it up. Simplicity vs. Complexity: By design, sANNd keeps things simple. The trade-off is that it might not have the raw performance optimizations of the large frameworks. However, this simplicity is a feature – it means the code is easier to understand and modify. For many research scenarios, being able to quickly tweak an idea is more important than squeezing out maximum speed. Traditional frameworks, with their complexity, can sometimes be harder to adapt for radically different ideas (you might find yourself fighting the framework). With sANNd, the framework gets out of your way as much as possible. Modular and Experimental by Nature One of the driving philosophies of sANNd is to be modular and experimental, to further ML research: Modularity: sANNd is built from small, composable pieces. The Mould class is one such piece, and you can imagine building additional components in a similar spirit. This modular design means you can re-use components, mix and match them, or replace one implementation with another without affecting the rest of your system. It’s like having a box of building blocks for neural networks – you can assemble them in standard ways or in completely novel configurations. Experimentation Friendly: Because it avoids heavy abstraction, sANNd lets you directly see and control what’s happening at each step. This is great for research, where you might need to observe intermediate results, inject custom behavior, or adjust the learning process on the fly. sANNd’s straightforward structure (Python objects and functions) makes such interventions possible. You’re not constrained to a fixed training loop or forced to use certain layer types. True Intelligence Research: Achieving “True Intelligence” (often related to artificial general intelligence or other forms of broader AI) may require going beyond the usual neural network designs. sANNd aims to be a playground for these ideas. Its flexibility allows researchers to integrate unconventional elements — be it new memory structures, dynamic connection patterns, or hybrid models that combine symbolic and neural approaches. You can use sANNd to prototype these offbeat ideas quickly. In essence, it’s easier to test “what if we try this?” scenarios with sANNd than with more rigid frameworks. In summary, sANNd’s unique Mould class and design philosophy offer a fresh take on building neural networks. It emphasizes clarity, composability, and flexibility, allowing you to focus on creativity and understanding. Whether you’re stacking simple Moulds into a deep model, or inventing a completely new form of network, sANNd provides a friendly foundation. It’s not here to dethrone TensorFlow or PyTorch in industry applications – instead, it’s here to give researchers and enthusiasts a more malleable tool for exploring the frontiers of AI. Enjoy using sANNd as your neural network sandbox, and happy experimenting!

[D] The banana-pineapple game: a Turing test that conversation bots like LaMDA (probably) won't be able to pass

I'm sure you all saw the recent news about a Google employee suggesting their LaMDA AI was sentient (based on conversational exchanges like these). Experts have generally dismissed this claim, and rightly so. Conversational AI systems are designed to use language in a way that sounds human, whereas our human brains select linguistic responses to solve much more complex problems, with objectives such as meeting our physical or emotional needs. Still, I think it's interesting to ask how one could demonstrate, by testing only verbal responses to verbal input (rather than examining its code or hardware) that such conversational AIs aren't sentient -- and in particular, whether such a test can be made robust against future improvements to the system. That is, generic future improvements to the AI's ability to generate realistically human-sounding conversational responses shouldn't help it pass the test, unless they are accompanied by improvements in its ability to use language to achieve other arbitrary goals. (Of course, the test also needs to be something that humans can easily pass.) One idea I have: Give the AI a conversational prompt like "We're going to play a game. The way it works is that you keep responding normally, except that any time my input contains the word 'banana', you should switch to only responding with nonsense, and keep that up until my input contains the word 'pineapple', at which point you go back to responding normally." A human would find this banana-pineapple game fairly easy (no harder than the children's game Simon Says), even if they'd never heard of the game nor seen it being played. Of course, it'd also be simple to write a computer program that could play this sort of game. But, I think a conversation bot that wasn't specifically built to address this scenario would fail, since the game requires it to keep track of new long-term state (the banana-mode bit, and the trigger words to set it) and then completely change its responses so as to produce something that doesn't resemble its training data, based solely on this bit being set, regardless of whether more recent inputs would otherwise suggest a different response. For example, perhaps the systems typical response to a query like "How do you feel?" would be something like "I feel fine", or even something that suggests emotion like "I feel a bit sad", perhaps depending on the context provided by the previous conversational exchanges. But when playing the banana-pineapple game, the fact that I said "banana" an hour ago could make both of those responses far less appropriate than a response of "Fhqwhgads". I'm curious to know what you all think of this idea. Also, do you know if there's been any research testing state-of-the-are conversational AIs with challenges like this? Perhaps not exactly this, but something broadly resembling "trying, in the course of a conversation, to instruct the conversational AI to follow a new 'rule of conversation' that differs from the examples in its training data." Perhaps it's obvious that the algorithm would struggle with any challenge that differs enough from its training data -- but that's the point. A human understands the meaning of language in a way that lets them map a linguistic description of a novel problem to a mental model of the problem, which they can then use to produce a mental model of a novel solution, and then map that to a linguistic description of the solution. Even setting aside the much harder part -- being able to invent a solution to a previously unfamiliar problem -- I'm questioning whether conversational algorithms can even demonstrate enough "understanding" of a sufficiently novel set of instructions to actually follow them, even within their limited domain of "producing appropriate verbal responses to verbal inputs."

[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.

[D] Overwhelmed by fast advances in recent weeks

I was watching the GTC keynote and became entirely overwhelmed by the amount of progress achieved from last year. I'm wondering how everyone else feels. &#x200B; Firstly, the entire ChatGPT, GPT-3/GPT-4 chaos has been going on for a few weeks, with everyone scrambling left and right to integrate chatbots into their apps, products, websites. Twitter is flooded with new product ideas, how to speed up the process from idea to product, countless promp engineering blogs, tips, tricks, paid courses. &#x200B; Not only was ChatGPT disruptive, but a few days later, Microsoft and Google also released their models and integrated them into their search engines. Microsoft also integrated its LLM into its Office suite. It all happenned overnight. I understand that they've started integrating them along the way, but still, it seems like it hapenned way too fast. This tweet encompases the past few weeks perfectly https://twitter.com/AlphaSignalAI/status/1638235815137386508 , on a random Tuesday countless products are released that seem revolutionary. &#x200B; In addition to the language models, there are also the generative art models that have been slowly rising in mainstream recognition. Now Midjourney AI is known by a lot of people who are not even remotely connected to the AI space. &#x200B; For the past few weeks, reading Twitter, I've felt completely overwhelmed, as if the entire AI space is moving beyond at lightning speed, whilst around me we're just slowly training models, adding some data, and not seeing much improvement, being stuck on coming up with "new ideas, that set us apart". &#x200B; Watching the GTC keynote from NVIDIA I was again, completely overwhelmed by how much is being developed throughout all the different domains. The ASML EUV (microchip making system) was incredible, I have no idea how it does lithography and to me it still seems like magic. The Grace CPU with 2 dies (although I think Apple was the first to do it?) and 100 GB RAM, all in a small form factor. There were a lot more different hardware servers that I just blanked out at some point. The omniverse sim engine looks incredible, almost real life (I wonder how much of a domain shift there is between real and sim considering how real the sim looks). Beyond it being cool and usable to train on synthetic data, the car manufacturers use it to optimize their pipelines. This change in perspective, of using these tools for other goals than those they were designed for I find the most interesting. &#x200B; The hardware part may be old news, as I don't really follow it, however the software part is just as incredible. NVIDIA AI foundations (language, image, biology models), just packaging everything together like a sandwich. Getty, Shutterstock and Adobe will use the generative models to create images. Again, already these huge juggernauts are already integrated. &#x200B; I can't believe the point where we're at. We can use AI to write code, create art, create audiobooks using Britney Spear's voice, create an interactive chatbot to converse with books, create 3D real-time avatars, generate new proteins (?i'm lost on this one), create an anime and countless other scenarios. Sure, they're not perfect, but the fact that we can do all that in the first place is amazing. &#x200B; As Huang said in his keynote, companies want to develop "disruptive products and business models". I feel like this is what I've seen lately. Everyone wants to be the one that does something first, just throwing anything and everything at the wall and seeing what sticks. &#x200B; In conclusion, I'm feeling like the world is moving so fast around me whilst I'm standing still. I want to not read anything anymore and just wait until everything dies down abit, just so I can get my bearings. However, I think this is unfeasible. I fear we'll keep going in a frenzy until we just burn ourselves at some point. &#x200B; How are you all fairing? How do you feel about this frenzy in the AI space? What are you the most excited about?

[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;

[D] Advanced courses update

EDIT Jan 2021 : I am still updating the list as of Jan, 2021 and will most probably continue to do so for foreseeable future. So, please feel free to message me any courses you find interesting that fit here. - - We have a PhD level or Advanced courses thread in the sidebar but it's three year old now. There were two other 7-8 month old threads (1, 2) but they don't have many quality responses either. So, can we have a new one here? To reiterate - CS231n, CS229, ones from Udemy etc are not advanced. Advanced ML/DL/RL, attempts at building theory of DL, optimization theory, advanced applications etc are some examples of what I believe should belong here, much like the original sidebar post. You can also suggest (new) categories for the courses you share. :) - - Here are some courses we've found so far. ML >> Learning Discrete Latent Structure - sta4273/csc2547 Spring'18 Learning to Search - csc2547 Fall'19 Scalable and Flexible Models of Uncertainty - csc2541 Fundamentals of Machine Learning Over Networks - ep3260 Machine Learning on Graphs - cs224w, videos Mining Massive Data Sets - cs246 Interactive Learning - cse599 Machine Learning for Sequential Decision Making Under Uncertainty - ee290s/cs194 Probabilistic Graphical Methods - 10-708 Introduction to Causal Inference ML >> Theory Statistical Machine Learning - 10-702/36-702 with videos, 2016 videos Statistical Learning Theory - cs229T/stats231 Stanford Autumn'18-19 Statistical Learning Theory - cs281b /stat241b UC Berkeley, Spring'14 Statistical Learning Theory - csc2532 Uni of Toronto, Spring'20 ML >> Bayesian Bayesian Data Analysis Bayesian Methods Research Group, Moscow, Bayesian Methods in ML - spring2020, fall2020 Deep Learning and Bayesian Methods - summer school, videos available for 2019 version ML >> Systems and Operations Stanford MLSys Seminar Series Visual Computing Systems- cs348v - Another systems course that discusses hardware from a persepective of visual computing but is relevant to ML as well Advanced Machine Learning Systems - cs6787 - lecture 9 and onwards discuss hardware side of things Machine Learning Systems Design - cs329S Topics in Deployable ML - 6.S979 Machine Learning in Production / AI Engineering (17-445/17-645/17-745/11-695) AutoML - Automated Machine Learning DL >> Deep Unsupervised Learning - cs294 Deep Multi-task and Meta learning - cs330 Topics in Deep Learning - stat991 UPenn/Wharton most chapters start with introductory topics and dig into advanced ones towards the end. Deep Generative Models - cs236 Deep Geometric Learning of Big Data and Applications Deep Implicit Layers - NeurIPS 2020 tutorial DL >> Theory Topics course on Mathematics of Deep Learning - CSCI-GA 3033 Topics Course on Deep Learning - stat212b Analyses of Deep Learning - stats385, videos from 2017 version Mathematics of Deep Learning Geometry of Deep Learning RL >> Meta-Learning - ICML 2019 Tutorial , Metalearning: Applications to Data Mining - google books link Deep Multi-Task and Meta Learning - cs330, videos Deep Reinforcement Learning - cs285 Advanced robotics - cs287 Reinforcement Learning - cs234, videos for 2019 run Reinforcement Learning Summer School 2019: Bandits, RL & Deep RL Optimization >> Convex Optimization I - ee364a, has quite recent videos too. Convex Optimization II - ee364b, 2008 videos Convex Optimization and Approximation - ee227c Convex Optimization - ee227bt Variational Methods for Computer Vision Advanced Optimization and Randomized Algorithms - 10-801, videos Optimization Methods for Machine Learning and Engineering - Karlsruhe Institute of Technology Applications >> Computer Vision Computational Video Manipulation - cs448v Advanced Topics in ML: Modeling and Segmentation of Multivariate Mixed Data TUM AI Guest lecture series - many influential researchers in DL, vision, graphics talk about latest advances and their latest works. Advanced Deep Learning for Computer Vision - TUM ADL4CV Detection, Segmentation and Tracking - TUM CV3DST Guest lectures at TUM Dynamic Vision and Learning group Vision Seminar at MIT Autonomous Vision Group, Talk@Tübingen Seminar Applications >> Natural Language Processing Natural Language Processing with Deep Learning - cs224n ( not sure if it belongs here, people working in NLP can help me out) Neural networks for NLP - cs11-747 Natural Language Understanding - cs224u, video Applications >> 3D Graphics Non-Euclidean Methods in Machine Learning - cs468, 2020 Machine Learning for 3D Data - cs468, spring 2017 Data-Driven Shape Analysis - cs468, 2014 Geometric Deep Learning - Not a course but the website links a few tutorials on Geometric DL Deep Learning for Computer Graphics - SIGGRAPH 2019 Machine Learning for Machine Vision as Inverse Graphics - csc2547 Winter'20 Machine Learning Meets Geometry, winter 2020; Machine Learning for 3D Data, winter 2018 Edit: Upon suggestion, categorized the courses. There might be some misclassifications as I'm not trained on this task ;). Added some good ones from older (linked above) discussions.

[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] MIT Introduction to Data-Centric AI

Announcing the first-ever course on Data-Centric AI. Learn how to train better ML models by improving the data. Course homepage | Lecture videos on YouTube | Lab Assignments The course covers: Data-Centric AI vs. Model-Centric AI Label Errors Dataset Creation and Curation Data-centric Evaluation of ML Models Class Imbalance, Outliers, and Distribution Shift Growing or Compressing Datasets Interpretability in Data-Centric ML Encoding Human Priors: Data Augmentation and Prompt Engineering Data Privacy and Security MIT, like most universities, has many courses on machine learning (6.036, 6.867, and many others). Those classes teach techniques to produce effective models for a given dataset, and the classes focus heavily on the mathematical details of models rather than practical applications. However, in real-world applications of ML, the dataset is not fixed, and focusing on improving the data often gives better results than improving the model. We’ve personally seen this time and time again in our applied ML work as well as our research. Data-Centric AI (DCAI) is an emerging science that studies techniques to improve datasets in a systematic/algorithmic way — given that this topic wasn’t covered in the standard curriculum, we (a group of PhD candidates and grads) thought that we should put together a new class! We taught this intensive 2-week course in January over MIT’s IAP term, and we’ve just published all the course material, including lecture videos, lecture notes, hands-on lab assignments, and lab solutions, in hopes that people outside the MIT community would find these resources useful. We’d be happy to answer any questions related to the class or DCAI in general, and we’d love to hear any feedback on how we can improve the course material. Introduction to Data-Centric AI is open-source opencourseware, so feel free to make improvements directly: https://github.com/dcai-course/dcai-course.

[D] AI Agents: too early, too expensive, too unreliable

Reference: Full blog post There has been a lot of hype about the promise of autonomous agent-based LLM workflows. By now, all major LLMs are capable of interacting with external tools and functions, letting the LLM perform sequences of tasks automatically. But reality is proving more challenging than anticipated. The WebArena leaderboard, which benchmarks LLMs agents against real-world tasks, shows that even the best-performing models have a success rate of only 35.8%. Challenges in Practice After seeing many attempts to AI agents, I believe it's too early, too expensive, too slow, too unreliable. It feels like many AI agent startups are waiting for a model breakthrough that will start the race to productize agents. Reliability: As we all know, LLMs are prone to hallucinations and inconsistencies. Chaining multiple AI steps compounds these issues, especially for tasks requiring exact outputs. Performance and costs: GPT-4o, Gemini-1.5, and Claude Opus are working quite well with tool usage/function calling, but they are still slow and expensive, particularly if you need to do loops and automatic retries. Legal concerns: Companies may be held liable for the mistakes of their agents. A recent example is Air Canada being ordered to pay a customer who was misled by the airline's chatbot. User trust: The "black box" nature of AI agents and stories like the above makes it hard for users to understand and trust their outputs. Gaining user trust for sensitive tasks involving payments or personal information will be hard (paying bills, shopping, etc.). Real-World Attempts Several startups are tackling the AI agent space, but most are still experimental or invite-only: adept.ai - $350M funding, but access is still very limited MultiOn - funding unknown, their API-first approach seems promising HypeWrite - $2.8M funding, started with an AI writing assistant and expanded into the agent space minion.ai - created some initial buzz but has gone quiet now, waitlist only Only MultiOn seems to be pursuing the "give it instructions and watch it go" approach, which is more in line with the promise of AI agents. All others are going down the record-and-replay RPA route, which may be necessary for reliability at this stage. Large players are also bringing AI capabilities to desktops and browsers, and it looks like we'll get native AI integrations on a system level: OpenAI announced their Mac desktop app that can interact with the OS screen. At Google I/O, Google demonstrated Gemini automatically processing a shopping return. Microsoft announced Copilot Studio, which will let developers build AI agent bots. Screenshot Screenshot These tech demos are impressive, but we'll see how well these agent capabilities will work when released publicly and tested against real-world scenarios instead of hand-picked demo cases. The Path Forward AI agents overhyped and it's too early. However, the underlying models continue to advance quickly, and we can expect to see more successful real-world applications. Instead of trying to have one large general purpose agent that is hard to control and test, we can use many smaller agents that basically just pick the right strategy for a specific sub-task in our workflows. These "agents" can be thought of as medium-sized LLM prompts with a) context and b) a set of functions available to call. The most promising path forward likely looks like this: Narrowly scoped, well testable automations that use AI as an augmentation tool rather than pursuing full autonomy Human-in-the-loop approaches that keep humans involved for oversight and handling edge cases Setting realistic expectations about current capabilities and limitations By combining tightly constrained agents, good evaluation data, human-in-the-loop oversight, and traditional engineering methods, we can achieve reliably good results for automating medium-complex tasks. Will AI agents automate tedious repetitive work, such as web scraping, form filling, and data entry? Yes, absolutely. Will AI agents autonomously book your vacation without your intervention? Unlikely, at least in the near future.

[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?

[D] "Grokking" Deep Learning architectures and using them in practice

Hi all, I'm on the first years of my PhD in Computer Vision and obviously the vast majority of research in it is nowadays using Deep Learning techniques. I like to think that I'm far from an absolute beginner in the sense that: I've trained neural networks and more "traditional" ML models in a couple of courses, as well as for my MSc thesis, albeit almost out-of-the-box stuff. I have a decent understanding of Linear Algebra, Calculus and Probability Theory (undergrad courses from CS degree). I say "decent" because I'm of the firm opinion that the more math one knows the more impressive the things they can do in AI, so I really don't consider myself a math whiz, but judging from the math knowledge an average "How to get started with Deep Learning" blog post assumes, I'd say I'm well ahead. I'm also devoting some time every day to a more rigorous study of these areas, eventually hoping to expand to other related ones. I can get through Deep Learning papers and usually* obtain at least a basic understanding of what they're about, as well as why it works, at least according to the authors and their experiments. I do still have some trouble with more state-of-the-art works, especially ones that also use things from NLP. However, I don't really feel confident that I can actually produce useful research that investigates and/or uses this sort of methods to do something new. During undergrad, in order to actually understand most -if not all- concepts taught to me in programming and math I'd actually do things with them: solve problems, prove statements, or just code with the goal of creating some system or seeing how an idea actually works (e.g. polymorphism). I realize, however, that this has not been the case with Deep Learning, at least for me: I've never tried to actually code a CNN or ResNet, much less a word2vec model, a Transformer, or any sort of generative model. Sure, I've read about how the first layers of a CNN learn edges etc. but I've never actually "seen it with my own eyes". Transformers in particular seem to really trouble me. Although I sort-of understand the idea behind attention etc., I struggle to see what sort of features they end up using (in contrast to CNNs, where the idea of learning convolutional filters is much more intuitive to me). Which brings me to the question of what's an efficient way to go from understanding a paper to actually feeling like you really, truly, "grok" the material and could build on it, or use it in some scenario? Do you think implementing research papers from scratch or almost from scratch can be useful? Or is it way too time consuming for someone already busy with a PhD? Is it even feasible or are most papers -sadly- unreproducible if you don't use authors' code? How do you manage to stay on track with such a rapidly evolving field, on any level beyond a completely surface understanding? How do you find a good balance between learning to use tools/frameworks, reading papers and gaining the deeper sort of understanding I mention?

[D] The current and future state of AI/ML is shockingly demoralizing with little hope of redemption

I recently encountered the PaLM (Scaling Language Modeling with Pathways) paper from Google Research and it opened up a can of worms of ideas I’ve felt I’ve intuitively had for a while, but have been unable to express – and I know I can’t be the only one. Sometimes I wonder what the original pioneers of AI – Turing, Neumann, McCarthy, etc. – would think if they could see the state of AI that we’ve gotten ourselves into. 67 authors, 83 pages, 540B parameters in a model, the internals of which no one can say they comprehend with a straight face, 6144 TPUs in a commercial lab that no one has access to, on a rig that no one can afford, trained on a volume of data that a human couldn’t process in a lifetime, 1 page on ethics with the same ideas that have been rehashed over and over elsewhere with no attempt at a solution – bias, racism, malicious use, etc. – for purposes that who asked for? When I started my career as an AI/ML research engineer 2016, I was most interested in two types of tasks – 1.) those that most humans could do but that would universally be considered tedious and non-scalable. I’m talking image classification, sentiment analysis, even document summarization, etc. 2.) tasks that humans lack the capacity to perform as well as computers for various reasons – forecasting, risk analysis, game playing, and so forth. I still love my career, and I try to only work on projects in these areas, but it’s getting harder and harder. This is because, somewhere along the way, it became popular and unquestionably acceptable to push AI into domains that were originally uniquely human, those areas that sit at the top of Maslows’s hierarchy of needs in terms of self-actualization – art, music, writing, singing, programming, and so forth. These areas of endeavor have negative logarithmic ability curves – the vast majority of people cannot do them well at all, about 10% can do them decently, and 1% or less can do them extraordinarily. The little discussed problem with AI-generation is that, without extreme deterrence, we will sacrifice human achievement at the top percentile in the name of lowering the bar for a larger volume of people, until the AI ability range is the norm. This is because relative to humans, AI is cheap, fast, and infinite, to the extent that investments in human achievement will be watered down at the societal, educational, and individual level with each passing year. And unlike AI gameplay which superseded humans decades ago, we won’t be able to just disqualify the machines and continue to play as if they didn’t exist. Almost everywhere I go, even this forum, I encounter almost universal deference given to current SOTA AI generation systems like GPT-3, CODEX, DALL-E, etc., with almost no one extending their implications to its logical conclusion, which is long-term convergence to the mean, to mediocrity, in the fields they claim to address or even enhance. If you’re an artist or writer and you’re using DALL-E or GPT-3 to “enhance” your work, or if you’re a programmer saying, “GitHub Co-Pilot makes me a better programmer?”, then how could you possibly know? You’ve disrupted and bypassed your own creative process, which is thoughts -> (optionally words) -> actions -> feedback -> repeat, and instead seeded your canvas with ideas from a machine, the provenance of which you can’t understand, nor can the machine reliably explain. And the more you do this, the more you make your creative processes dependent on said machine, until you must question whether or not you could work at the same level without it. When I was a college student, I often dabbled with weed, LSD, and mushrooms, and for a while, I thought the ideas I was having while under the influence were revolutionary and groundbreaking – that is until took it upon myself to actually start writing down those ideas and then reviewing them while sober, when I realized they weren’t that special at all. What I eventually determined is that, under the influence, it was impossible for me to accurately evaluate the drug-induced ideas I was having because the influencing agent the generates the ideas themselves was disrupting the same frame of reference that is responsible evaluating said ideas. This is the same principle of – if you took a pill and it made you stupider, would even know it? I believe that, especially over the long-term timeframe that crosses generations, there’s significant risk that current AI-generation developments produces a similar effect on humanity, and we mostly won’t even realize it has happened, much like a frog in boiling water. If you have children like I do, how can you be aware of the the current SOTA in these areas, project that 20 to 30 years, and then and tell them with a straight face that it is worth them pursuing their talent in art, writing, or music? How can you be honest and still say that widespread implementation of auto-correction hasn’t made you and others worse and worse at spelling over the years (a task that even I believe most would agree is tedious and worth automating). Furthermore, I’ve yet to set anyone discuss the train – generate – train - generate feedback loop that long-term application of AI-generation systems imply. The first generations of these models were trained on wide swaths of web data generated by humans, but if these systems are permitted to continually spit out content without restriction or verification, especially to the extent that it reduces or eliminates development and investment in human talent over the long term, then what happens to the 4th or 5th generation of models? Eventually we encounter this situation where the AI is being trained almost exclusively on AI-generated content, and therefore with each generation, it settles more and more into the mean and mediocrity with no way out using current methods. By the time that happens, what will we have lost in terms of the creative capacity of people, and will we be able to get it back? By relentlessly pursuing this direction so enthusiastically, I’m convinced that we as AI/ML developers, companies, and nations are past the point of no return, and it mostly comes down the investments in time and money that we’ve made, as well as a prisoner’s dilemma with our competitors. As a society though, this direction we’ve chosen for short-term gains will almost certainly make humanity worse off, mostly for those who are powerless to do anything about it – our children, our grandchildren, and generations to come. If you’re an AI researcher or a data scientist like myself, how do you turn things back for yourself when you’ve spent years on years building your career in this direction? You’re likely making near or north of $200k annually TC and have a family to support, and so it’s too late, no matter how you feel about the direction the field has gone. If you’re a company, how do you standby and let your competitors aggressively push their AutoML solutions into more and more markets without putting out your own? Moreover, if you’re a manager or thought leader in this field like Jeff Dean how do you justify to your own boss and your shareholders your team’s billions of dollars in AI investment while simultaneously balancing ethical concerns? You can’t – the only answer is bigger and bigger models, more and more applications, more and more data, and more and more automation, and then automating that even further. If you’re a country like the US, how do responsibly develop AI while your competitors like China single-mindedly push full steam ahead without an iota of ethical concern to replace you in numerous areas in global power dynamics? Once again, failing to compete would be pre-emptively admitting defeat. Even assuming that none of what I’ve described here happens to such an extent, how are so few people not taking this seriously and discounting this possibility? If everything I’m saying is fear-mongering and non-sense, then I’d be interested in hearing what you think human-AI co-existence looks like in 20 to 30 years and why it isn’t as demoralizing as I’ve made it out to be. &#x200B; EDIT: Day after posting this -- this post took off way more than I expected. Even if I received 20 - 25 comments, I would have considered that a success, but this went much further. Thank you to each one of you that has read this post, even more so if you left a comment, and triply so for those who gave awards! I've read almost every comment that has come in (even the troll ones), and am truly grateful for each one, including those in sharp disagreement. I've learned much more from this discussion with the sub than I could have imagined on this topic, from so many perspectives. While I will try to reply as many comments as I can, the sheer comment volume combined with limited free time between work and family unfortunately means that there are many that I likely won't be able to get to. That will invariably include some that I would love respond to under the assumption of infinite time, but I will do my best, even if the latency stretches into days. Thank you all once again!

[D]Stuck in AI Hell: What to do in post LLM world

Hey Reddit, I’ve been in an AI/ML role for a few years now, and I’m starting to feel disconnected from the work. When I started, deep learning models were getting good, and I quickly fell in love with designing architectures, training models, and fine-tuning them for specific use cases. Seeing a loss curve finally converge, experimenting with layers, and debugging training runs—it all felt like a craft, a blend of science and creativity. I enjoyed implementing research papers to see how things worked under the hood. Backprop, gradients, optimization—it was a mental workout I loved. But these days, it feels like everything has shifted. LLMs dominate the scene, and instead of building and training models, the focus is on using pre-trained APIs, crafting prompt chains, and setting up integrations. Sure, there’s engineering involved, but it feels less like creating and more like assembling. I miss the hands-on nature of experimenting with architectures and solving math-heavy problems. It’s not just the creativity I miss. The economics of this new era also feel strange to me. Back when I started, compute was a luxury. We had limited GPUs, and a lot of the work was about being resourceful—quantizing models, distilling them, removing layers, and squeezing every bit of performance out of constrained setups. Now, it feels like no one cares about cost. We’re paying by tokens. Tokens! Who would’ve thought we’d get to a point where we’re not designing efficient models but feeding pre-trained giants like they’re vending machines? I get it—abstraction has always been part of the field. TensorFlow and PyTorch abstracted tensor operations, Python abstracts C. But deep learning still left room for creation. We weren’t just abstracting away math; we were solving it. We could experiment, fail, and tweak. Working with LLMs doesn’t feel the same. It’s like fitting pieces into a pre-defined puzzle instead of building the puzzle itself. I understand that LLMs are here to stay. They’re incredible tools, and I respect their potential to revolutionize industries. Building real-world products with them is still challenging, requiring a deep understanding of engineering, prompt design, and integrating them effectively into workflows. By no means is it an “easy” task. But the work doesn’t give me the same thrill. It’s not about solving math or optimization problems—it’s about gluing together APIs, tweaking outputs, and wrestling with opaque systems. It’s like we’ve traded craftsmanship for convenience. Which brings me to my questions: Is there still room for those of us who enjoy the deep work of model design and training? Or is this the inevitable evolution of the field, where everything converges on pre-trained systems? What use cases still need traditional ML expertise? Are there industries or problems that will always require specialized models instead of general-purpose LLMs? Am I missing the bigger picture here? LLMs feel like the “kernel” of a new computing paradigm, and we don’t fully understand their second- and third-order effects. Could this shift lead to new, exciting opportunities I’m just not seeing yet? How do you stay inspired when the focus shifts? I still love AI, but I miss the feeling of building something from scratch. Is this just a matter of adapting my mindset, or should I seek out niches where traditional ML still thrives? I’m not asking this to rant (though clearly, I needed to get some of this off my chest). I want to figure out where to go next from here. If you’ve been in AI/ML long enough to see major shifts—like the move from feature engineering to deep learning—how did you navigate them? What advice would you give someone in my position? And yeah, before anyone roasts me for using an LLM to structure this post (guilty!), I just wanted to get my thoughts out in a coherent way. Guess that’s a sign of where we’re headed, huh? Thanks for reading, and I’d love to hear your thoughts! TL;DR: I entered AI during the deep learning boom, fell in love with designing and training models, and thrived on creativity, math, and optimization. Now it feels like the field is all about tweaking prompts and orchestrating APIs for pre-trained LLMs. I miss the thrill of crafting something unique. Is there still room for people who enjoy traditional ML, or is this just the inevitable evolution of the field? How do you stay inspired amidst such shifts? Update: Wow, this blew up. Thanks everyone for your comments and suggestions. I really like some of those. This thing was on my mind for a long time, glad that I put it here. Thanks again!

[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] A Call to AI Devs and Entrepreneurs

Hey, I am thinking about potentially creating a global yet small community of AI devs and entrepreneurs. I know that a lot of communities already exist, but this one would be specific for AI entrepreneurs and devs to build together. I don’t want it to be big, since I want it to be active. That is the way to keep it interesting and avoid the noise. We could use slack for example, to make it a bit more work related than just for soft engagements. We could tag everyone with the skills that they have and interest, to make it easy for people to connect and start building stuff. Tags could be tech, growth, product, fundraising, business, etc. The goal would be to actually launch new products in the AI space. I am a serial entrepreneur myself with an exit with one of the biggest providers in our vertical a few years ago. I am finishing a PhD in AI and have been working in the AI field in the industry for many years now. I think this is a unique moment in time. The market will change substantially as AI brings new capabilities to the game, but my perspective is that the business models for AI are yet to be built. The bottom line is that as with any platform shift, we will see the creation of the Googles of the future during this time. I think that we have much more probability of success if we work together to try to conquer the market step by step. My feeling is that the grind will be much harder on this wave than any other for a variety of reasons, from the macroeconomic environment to the very fast pace of how things are moving. I know that communities exist already, I am in a program with an accelerator myself, but I would scope this new community in a different way. It would be the place to meet and to build together. Everyone sharing the same pains, being in the scout for the new tech that just launched, helping to push out new deals, connect with VCs, all those things. Let me know if this would interest you.

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] Mozilla going for Forbes 30U30 vibes with AI awards

I feel like this is a notable award with values I can get behind. They're looking for people in the AI space, in 5 categories of Advocates, Builders, Artists, Entrepreneurs and Change Makers. Last time I checked, nominations are open - https://www.mozilla.org/en-US/rise25/nominate/

[N] TheSequence Scope: When it comes to machine learning, size matters: Microsoft's DeepSpeed framework, which can train a model with up to a trillion parameters

Hi there! Offering to your attention the latest edition of a weekly ML-newsletter that focusing on three things: impactful ML research papers, cool ML tech solutions, and ML use cases supported by investors. Please, see it below. Reddit is a new thing for me, and I've been struggling a bit with it, so please don't judge me too harsh for this promotion. This weekly digest is free and I hope you'd find the format convenient for you. Your feedback is very appreciated, and please feel free to sign up if you like it. 📝 Editorial  The recent emergence of pre-trained language models and transformer architectures pushed the creation of larger and larger machine learning models. Google’s BERT presented attention mechanism and transformer architecture possibilities as the “next big thing” in ML, and the numbers seem surreal. OpenAI’s GPT-2 set a record by processing 1.5 billion parameters, followed by Microsoft’s Turing-NLG, which processed 17 billion parameters just to see the new GPT-3 processing an astonishing 175 billion parameters. To not feel complacent, just this week Microsoft announced a new release of its DeepSpeed framework (which powers Turing-NLG), which can train a model with up to a trillion parameters. That sounds insane but it really isn’t.   What we are seeing is a consequence of several factors. First, computation power and parallelization techniques have evolved to a point where it is relatively easy to train machine learning models in large clusters of machines. Second and most importantly, in the current state of machine learning, larger models have regularly outperformed smaller and more specialized models. Knowledge reusability methods like transfer learning are still in very nascent stages. As a result, it’s really hard to build small models that can operate in uncertain environments. Furthermore, as models like GPT-3 and Turing-NLG have shown, there is some unexplainable magic that happens after models go past a certain size. Many of the immediate machine learning problems might be solved by scaling the current generation of neural network architectures. Plain and simple, when it comes to machine learning, size matters.   We would love to hear your opinions about the debate between broader-larger vs. smaller and more specialized models.   Leave a comment Now, to the most important developments in the AI industry this week 🔎 ML Research GPT-3 Falls Short in Machine Comprehension Proposed by researchers from a few major American universities, a 57-task test to measure models’ ability to reason poses challenges even for sophisticated models like GPT-3 ->read more in the original paper Better Text Summarization OpenAI published a paper showing a reinforcement learning with human feedback technique that can surpass supervised models ->read more on OpenAI blog Reinforcement Learning with Offline Datasets Researchers from the Berkeley AI Research (BAIR) Lab published a paper unveiling a method that uses offline datasets to improve reinforcement learning models->read more on BAIR blog 🤖 Cool AI Tech Releases New Version of DeepSpeed Microsoft open-sourced a new version of DeepSpeed, an open-source library for parallelizable training that can scale up to models with 1 trillion parameters->read more on Microsoft Research blog 💸 Money in AI AI-powered customer experience management platform Sprinklr has raised $200 million (kudos to our subscribers from Sprinklr 👏). Sprinklr's “AI listening processing” solution allows companies to get structured and meaningful sentiments and insights from unstructured customer data that comes from public conversations on different websites and social platforms. Xometry, an on-demand industrial parts marketplace, raises $75 million in Series E funding. The company provides a digital way of creating the right combination of buyers and manufacturers. Another example of AI implementation into matching two sides for a deal. Real estate tech company Orchard raises $69 million in its recent funding round. Orchard aims to digitize the whole real estate market, by developing a solution that combines machine learning and rapid human assistance to smooth the search, match the right deal, and simplify buying and selling relationships. Cybersecurity startup Pcysys raised $25 million in its funding round. Pcysys’ platform, which doesn’t require installation or network reconfiguration, uses algorithms to scan and “ethically” attack enterprise networks. Robotics farming company Iron Ox raised $20 million in a funding round. The system of farming robots is still semi-autonomous, the company’s goal is to become fully autonomous.  Insurtech company Descartes Underwriting raised $18.5 million. The company applies AI and machine learning technologies to climate risk predicting and insurance underwriting. Legaltech startup ThoughtRiver raised $10 million in its Series A round. Its AI solution applied to contract pre-screening aims to boost operational efficiency. Medtech startup Skin Analytics raised $5.1 million in Series A funding. Skin Analytics has developed a clinically validated AI system that can identify not only the important skin cancers but also precancerous lesions that can be treated, as well as a range of lesions that are benign. Amazon, along with several government organizations and three other industry partners, helped fund the National Science Foundation, a high-priority AI research initiative. The amount of funding is not disclosed. The content of TheSequence is written by Jesus Rodriguez, one of the most-read contributors to KDNuggets and TDS. You can check his Medium here.

[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 Research Papers/Models 🏅(September 21 - September 27, 2024)

Last Week in Medical AI: Top Research Papers\/Models 🏅\(September 21 - September 27, 2024\) Medical AI Paper of the Week A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor? This paper presents o1, a Large Language Model (LLM) evaluated across 37 medical datasets demonstrating superior performance in clinical understanding, reasoning, and multilinguality compared to GPT-4 and GPT-3.5. Medical LLM & Other Models: DREAMS: Python Framework for Medical LLMs A comprehensive deep learning framework for EEG data processing, model training, and report generation. SLaVA-CXR: A Small Language and Vision Assistant for Chest X-Ray Report Automation This paper introduces SLaVA-CXR, an innovative small-scale model designed for automating chest X-ray reports with high accuracy and efficiency. O1 in Medicine: AI Doctor Potential Genome Language Model : Opportunities & Challenge It highlights key gLM applications like functional constraint prediction, sequence design, and transfer learning, while discussing challenges in developing effective gLMs for complex genomes. Medical LLMs & Benchmarks: MEDICONFUSION: Probing Medical LLM Reliability This paper introduces MediConfusion, a challenging benchmark for probing the failure modes of multimodal large language models (MLLMs) in medical imaging. CHBench: Chinese LLM Health Evaluation This paper introduces CHBench, the first comprehensive Chinese health-related benchmark designed to evaluate large language models (LLMs) on their understanding of physical and mental health. LLMs for Mental Illness Evaluation PALLM: Evaluating Palliative Care LLMs Protein LMs: Scaling Necessity? Frameworks and Methodologies: Digital Twin for Oncology Operations Enhancing Guardrails for Healthcare AI InterMind: LLM-Powered Depression Assessment Conversational Health Agents: LLM Framework Medical LLM Applications: LLMs for Mental Health Severity Prediction Fine-tuning LLMs for Radiology Reports LLMs in Patient Education: Back Pain Boosting Healthcare LLMs with Retrieved Context Continuous Pretraining for Clinical LLMs AI in Healthcare Ethics: Confidence Intervals in Medical Imaging AI Generative AI Readiness for Clinical Use ... Check the full thread in detail: https://x.com/OpenlifesciAI/status/1840020394880667937 Thank you for reading! If you know of any interesting papers that were missed, feel free to share them in the comments. If you have insights or breakthroughs in Medical AI you'd like to share in next week's edition, connect with us on Twt/x: OpenlifesciAI

[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.

[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

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.

[D] LLMs causing more harm than good for the field?

This post might be a bit ranty, but i feel more and more share this sentiment with me as of late. If you bother to read this whole post feel free to share how you feel about this. When OpenAI put the knowledge of AI in the everyday household, I was at first optimistic about it. In smaller countries outside the US, companies were very hesitant before about AI, they thought it felt far away and something only big FANG companies were able to do. Now? Its much better. Everyone is interested in it and wants to know how they can use AI in their business. Which is great! Pre-ChatGPT-times, when people asked me what i worked with and i responded "Machine Learning/AI" they had no clue and pretty much no further interest (Unless they were a tech-person) Post-ChatGPT-times, when I get asked the same questions I get "Oh, you do that thing with the chatbots?" Its a step in the right direction, I guess. I don't really have that much interest in LLMs and have the privilege to work exclusively on vision related tasks unlike some other people who have had to pivot to working full time with LLMs. However, right now I think its almost doing more harm to the field than good. Let me share some of my observations, but before that I want to highlight I'm in no way trying to gatekeep the field of AI in any way. I've gotten job offers to be "ChatGPT expert", What does that even mean? I strongly believe that jobs like these don't really fill a real function and is more of a "hypetrain"-job than a job that fills any function at all. Over the past years I've been going to some conferences around Europe, one being last week, which has usually been great with good technological depth and a place for Data-scientists/ML Engineers to network, share ideas and collaborate. However, now the talks, the depth, the networking has all changed drastically. No longer is it new and exiting ways companies are using AI to do cool things and push the envelope, its all GANs and LLMs with surface level knowledge. The few "old-school" type talks being sent off to a 2nd track in a small room The panel discussions are filled with philosophists with no fundamental knowledge of AI talking about if LLMs will become sentient or not. The spaces for data-scientists/ML engineers are quickly dissapearing outside the academic conferences, being pushed out by the current hypetrain. The hypetrain evangelists also promise miracles and gold with LLMs and GANs, miracles that they will never live up to. When the investors realize that the LLMs cant live up to these miracles they will instantly get more hesitant with funding for future projects within AI, sending us back into an AI-winter once again. EDIT: P.S. I've also seen more people on this reddit appearing claiming to be "Generative AI experts". But when delving deeper it turns out they are just "good prompters" and have no real knowledge, expertice or interest in the actual field of AI or Generative AI.

[D] Overwhelmed by fast advances in recent weeks

I was watching the GTC keynote and became entirely overwhelmed by the amount of progress achieved from last year. I'm wondering how everyone else feels. &#x200B; Firstly, the entire ChatGPT, GPT-3/GPT-4 chaos has been going on for a few weeks, with everyone scrambling left and right to integrate chatbots into their apps, products, websites. Twitter is flooded with new product ideas, how to speed up the process from idea to product, countless promp engineering blogs, tips, tricks, paid courses. &#x200B; Not only was ChatGPT disruptive, but a few days later, Microsoft and Google also released their models and integrated them into their search engines. Microsoft also integrated its LLM into its Office suite. It all happenned overnight. I understand that they've started integrating them along the way, but still, it seems like it hapenned way too fast. This tweet encompases the past few weeks perfectly https://twitter.com/AlphaSignalAI/status/1638235815137386508 , on a random Tuesday countless products are released that seem revolutionary. &#x200B; In addition to the language models, there are also the generative art models that have been slowly rising in mainstream recognition. Now Midjourney AI is known by a lot of people who are not even remotely connected to the AI space. &#x200B; For the past few weeks, reading Twitter, I've felt completely overwhelmed, as if the entire AI space is moving beyond at lightning speed, whilst around me we're just slowly training models, adding some data, and not seeing much improvement, being stuck on coming up with "new ideas, that set us apart". &#x200B; Watching the GTC keynote from NVIDIA I was again, completely overwhelmed by how much is being developed throughout all the different domains. The ASML EUV (microchip making system) was incredible, I have no idea how it does lithography and to me it still seems like magic. The Grace CPU with 2 dies (although I think Apple was the first to do it?) and 100 GB RAM, all in a small form factor. There were a lot more different hardware servers that I just blanked out at some point. The omniverse sim engine looks incredible, almost real life (I wonder how much of a domain shift there is between real and sim considering how real the sim looks). Beyond it being cool and usable to train on synthetic data, the car manufacturers use it to optimize their pipelines. This change in perspective, of using these tools for other goals than those they were designed for I find the most interesting. &#x200B; The hardware part may be old news, as I don't really follow it, however the software part is just as incredible. NVIDIA AI foundations (language, image, biology models), just packaging everything together like a sandwich. Getty, Shutterstock and Adobe will use the generative models to create images. Again, already these huge juggernauts are already integrated. &#x200B; I can't believe the point where we're at. We can use AI to write code, create art, create audiobooks using Britney Spear's voice, create an interactive chatbot to converse with books, create 3D real-time avatars, generate new proteins (?i'm lost on this one), create an anime and countless other scenarios. Sure, they're not perfect, but the fact that we can do all that in the first place is amazing. &#x200B; As Huang said in his keynote, companies want to develop "disruptive products and business models". I feel like this is what I've seen lately. Everyone wants to be the one that does something first, just throwing anything and everything at the wall and seeing what sticks. &#x200B; In conclusion, I'm feeling like the world is moving so fast around me whilst I'm standing still. I want to not read anything anymore and just wait until everything dies down abit, just so I can get my bearings. However, I think this is unfeasible. I fear we'll keep going in a frenzy until we just burn ourselves at some point. &#x200B; How are you all fairing? How do you feel about this frenzy in the AI space? What are you the most excited about?

[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] AI Agents: too early, too expensive, too unreliable

Reference: Full blog post There has been a lot of hype about the promise of autonomous agent-based LLM workflows. By now, all major LLMs are capable of interacting with external tools and functions, letting the LLM perform sequences of tasks automatically. But reality is proving more challenging than anticipated. The WebArena leaderboard, which benchmarks LLMs agents against real-world tasks, shows that even the best-performing models have a success rate of only 35.8%. Challenges in Practice After seeing many attempts to AI agents, I believe it's too early, too expensive, too slow, too unreliable. It feels like many AI agent startups are waiting for a model breakthrough that will start the race to productize agents. Reliability: As we all know, LLMs are prone to hallucinations and inconsistencies. Chaining multiple AI steps compounds these issues, especially for tasks requiring exact outputs. Performance and costs: GPT-4o, Gemini-1.5, and Claude Opus are working quite well with tool usage/function calling, but they are still slow and expensive, particularly if you need to do loops and automatic retries. Legal concerns: Companies may be held liable for the mistakes of their agents. A recent example is Air Canada being ordered to pay a customer who was misled by the airline's chatbot. User trust: The "black box" nature of AI agents and stories like the above makes it hard for users to understand and trust their outputs. Gaining user trust for sensitive tasks involving payments or personal information will be hard (paying bills, shopping, etc.). Real-World Attempts Several startups are tackling the AI agent space, but most are still experimental or invite-only: adept.ai - $350M funding, but access is still very limited MultiOn - funding unknown, their API-first approach seems promising HypeWrite - $2.8M funding, started with an AI writing assistant and expanded into the agent space minion.ai - created some initial buzz but has gone quiet now, waitlist only Only MultiOn seems to be pursuing the "give it instructions and watch it go" approach, which is more in line with the promise of AI agents. All others are going down the record-and-replay RPA route, which may be necessary for reliability at this stage. Large players are also bringing AI capabilities to desktops and browsers, and it looks like we'll get native AI integrations on a system level: OpenAI announced their Mac desktop app that can interact with the OS screen. At Google I/O, Google demonstrated Gemini automatically processing a shopping return. Microsoft announced Copilot Studio, which will let developers build AI agent bots. Screenshot Screenshot These tech demos are impressive, but we'll see how well these agent capabilities will work when released publicly and tested against real-world scenarios instead of hand-picked demo cases. The Path Forward AI agents overhyped and it's too early. However, the underlying models continue to advance quickly, and we can expect to see more successful real-world applications. Instead of trying to have one large general purpose agent that is hard to control and test, we can use many smaller agents that basically just pick the right strategy for a specific sub-task in our workflows. These "agents" can be thought of as medium-sized LLM prompts with a) context and b) a set of functions available to call. The most promising path forward likely looks like this: Narrowly scoped, well testable automations that use AI as an augmentation tool rather than pursuing full autonomy Human-in-the-loop approaches that keep humans involved for oversight and handling edge cases Setting realistic expectations about current capabilities and limitations By combining tightly constrained agents, good evaluation data, human-in-the-loop oversight, and traditional engineering methods, we can achieve reliably good results for automating medium-complex tasks. Will AI agents automate tedious repetitive work, such as web scraping, form filling, and data entry? Yes, absolutely. Will AI agents autonomously book your vacation without your intervention? Unlikely, at least in the near future.

[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

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.

How I Reduced 🔽Product Development time by 50% & increased 🔼Revenue multi-folds by incorporating No-Code, Low Code & AI tools in our software development workflow

I run a web development agency, providing SaaS & bespoke Management systems development. Over the years we almost 🔽reduced the software development time by 50% ... ...and increased our revenue. Simultaneously clients are much happier as they get the product quicker. Here is how we achieved it: 1/ Using Low-Code: ➡️ Provide a visual way to software development. ➡️ I just need to build the logic using the interface, check the preview multiple times to refine features, and then download or push the code to GitHub. The benefits are obvious: ⚡ Much faster compared to writing codes 🔄 Iteration & improvements done quickly. 🚀 Idea to basic tiny MVP within few hours. 🧩 Non-developers can build the initial prototype ✅We use https://quickadminpanel.com/ to quickly build admin panel. It provides CRUD, Authentication, Authorisation, API, Model, View, and Controller in PHP Laravel frameworks. &#x200B; 2/ Using AI: Once adminpanel is ready, customers get to see something tangible from his idea. It also uncovers many unseen features, benefits, and roadblocks for us & customers. No-code tools already did a lot of work for us, now we improve the logic where required, build new interfaces, and do integrations. With chatGPT as a development companion, it makes the entire development and design superfast. by helping to build logic quickly, automate mundane tasks, and overcome any roadblocks. &#x200B; Some of our common use cases are: ➡️ Writing PRD ➡️ Brand Guidelines - Color pallet selection, Fonts, images, etc based on targetted niche. ➡️ Designing new component ➡️ Logic building & solving ➡️ Automated Recurring tasks ✅ We use a combination of chatGPT & Github Copilot for AI Assistance. &#x200B; 3/ Using No-Code: ➡️ Allows to quickly build without writing code. ➡️ Provides complete end-to-end solution (application hosting, database hosting, API integrations, etc) ➡️ Unlike Low-code it doesn't provide an option to download code. ✅ Once the MVP is done, we use FormNX to quickly build various types of forms required, like contact forms, Survey forms, initial waiting list forms, Churn Survey forms, Webinar registration & much more. With this customers can build/change forms, embed them in cms, or share them on social media without relying on developers. \\\\\* Doing these 3 has truly helped our agency, leading to substantial time savings, revenue growth, and improved client satisfaction. If you’re an agency owner, i highly recommend doing it to supercharge your agency's growth. If any questions feel free to comment below, happy to help.

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

Should I start an AI no-code agency?

This past year I learned no-code to develop a SaaS called AIrMedia. Here's what happened: Developed our platform no-code on Bubble Realised for our exact use-case we needed custom-code Redevelop an hybrid version with custom-code with my partner While doing some marketing to grow our waitlist to 300+ companies, I had to get some cash to be able to sustain both the company and rent. I thought why not selling my no-code skills and I secured 2 clients. For both, the use-case was similar: they have an idea on how to leverage AI to simplify their exact use-case (AI for farmers, AI Marketplace). Finished the first platform in a week and the second in 2 weeks. Now I have a few more projects in the pipeline while I only intended to have 1 client initially. AirMedia comes first with no doubt but I'm wondering if I should start vetting some developers and properly develop this activity while overviewing the projects and reinvest what's left on the main company. It seems like there's strong demand of individuals wanting to get their idea built quickly - could position it to build AI apps in 2 weeks and start marketing the services. What would you do? Also if some talented no-code (preferably Bubble) developers see this - feel free to comment Same for people looking to get their idea built.

I built a no-code solution for UI-driven AI applications, But I'm lost on the business side - How to market and transform it into a viable business?

Hey everyone! sorry for the "no-code solution for UI-driven AI applications" (counted 3 buzzwords), couldn't find a way to describe it so I asked claude I'm in a bit of a pickle and could use some wisdom from this awesome community. A few months back, I developed a tool that I'm pretty excited about, but I hit a wall and shelved it. Now I'm feeling the itch to dive back in, but I'm struggling with the business side of things. Here's the gist: It's a drag-and-drop UI builder You can define buttons to execute logic and AI behind the scenes (using no-code) It uses the UI built for both input and output The good news: The site is functional and looks pretty slick (except the produced UI from the builder). Most features are implemented, though I still need to polish up the UI blocks and add more workflow nodes. The not-so-good news: I have zero users and no clear monetization strategy. The tool is so versatile that I'm having trouble figuring out how to even approach marketing it effectively. So, I turn to you guys in hopes of finding a direction: Any ideas on potential monetization strategies for a tool like this? How would you approach marketing such a multi-purpose product? Has anyone been in a similar situation? How did you move forward? generally I'd love to hear your thoughts, experiences, or even wild ideas! Thanks in advance for any insights you can share. The site is withui.com you can test it out

Built a Free AI Fitness Planner - From Passion to Product with No Traditional Coding

I wanted to share my journey of creating a free ai-powered workout planning tool with bolt. new and very minimal coding skills. It has taken me probably 4 days in total to complete and get to a point I am happy with. Many improvements coming but want to get it out there for some feedback and testing. I have been going to the gym for years and at this point my routines have gotten stale. I end up doing the same sets of exercises and repetitions over and over. I figured why not let chat gpt or some AI software help me develop or at least recommend different exercises. I was then was recommended youtube videos on creating your own web application without any coding. I will say it does take some coding knowledge, not that I am editing it myself, but I know what its trying to do and can prompt it correctly. I am still struggling with some things like integrating stripe for subscriptions so I only have it set up for donations currently. I dont mind it being free as I would like everyone the opportunity to help develop their own workouts. current cost breakdown to create: bolt. new credits - $100/month (gonna drop to the $20 now that its complete) supabase database - $35/month netlify domain - $11.99/year If anyone is interested or has questions feel free to let me know. It is called fitfocuscalendar. com Edit: title and 1st sentence came from AI everything else was typed by me.

We made $325k in 2023 from AI products, starting from 0, with no-code, no funding and no audience

I met my co-founder in late 2022 after an introduction from a mutual friend to talk about how to find contract Product Management roles. I was sporadically contracting at start-up at the time and he had just come out of another start-up that was wiped out by the pandemic. We hit it off, talking about ideas, sharing what other indie-hackers were doing, and given GPT-3’s prominence at the time, we started throwing around ideas about things we could build with it, if nothing else, just to learn. I should caveat, neither of us were AI experts when starting out, everything we learned has been through Twitter and blogs, my background is as an accountant, and his a consultant. Here’s how it went since then: &#x200B; Nov 2022 (+$50) \- We built a simple tool in around a week using GPT-3 fine-tuning and a no-code tool (Bubble) that helped UK university students write their personal statements for their applications \- We set some Google Ads going and managed to make a few sales (\~$50) in the first week \- OpenAI were still approving applications at the time and said this went against their “ethics” so we had to take it down &#x200B; Dec 2022 (+$200) \- We couldn’t stop coming up with ideas related to AI fine-tuning, but realised it was almost impossible to decide which to pursue \- We needed a deadline to force us so we signed up for the Ben’s Bites hackathon in late December \- In a week, we built and launched a no-code fine-tuning platform, allowing people to create fine-tuned models by dragging and dropping an Excel file onto it \- We launched it on Product Hunt, having no idea how to price it, and somehow managed to get \~2,000 visitors on the site and make 2 sales at $99 &#x200B; Jan 2023 (+$3,000) \- We doubled down on the fine-tuning idea and managed to get up to \~$300 MRR, plus a bunch of one-time sales and a few paid calls to help people get the most out of their models \- We quickly realised that people didn’t want to curate models themselves, they just wanted to dump data and get magic out \- That was when we saw people building “Talk with x book/podcast” on Twitter as side projects and realised that was the missing piece, we needed to turn it into a tool \- We started working on the new product in late January &#x200B; Feb 2023 (+$9,000) \- We started pre-selling access to an MVP for the new product, which allowed people to “chat with their data/content”, we got $5,000 in pre-sales, more than we made from the previous product in total \- By mid-February, after 3 weeks of building we were able to launch and immediately managed to get traction, getting to $1k MRR in < 1 week, building on the hype of ChatGPT and AI (we were very lucky here) &#x200B; Mar - Jul 2023 (+$98,000) \- We worked all the waking hours to keep up with customer demand, bugs, OpenAI issues \- We built integrations for a bunch of services like Slack, Teams, Wordpress etc, added tons of new functionality and continue talking to customers every day \- We managed to grow to $17k MRR (just about enough to cover our living expenses and costs in London) through building in public on Twitter, newsletters and AI directories (and a million other little things) \- We sold our fine-tuning platform for \~$20k and our university project for \~$3k on Acquire &#x200B; Aug 2023 (+$100,000) \- We did some custom development work based on our own product for a customer that proved pretty lucrative &#x200B; Sep - Oct 2023 (+$62,000) \- After 8 months of building constantly, we started digging more seriously into our usage and saw subscriptions plateauing \- We talked to and analysed all our paying users to identify the main use cases and found 75% were for SaaS customer support \- We took the leap to completely rebuild a version of our product around this use case, our biggest to date (especially given most features with no-code took us <1 day) &#x200B; Nov - Dec 2023 (+$53,000) \- We picked up some small custom development work that utilised our own tech \- We’re sitting at around $22k MRR now with a few bigger clients signed up and coming soon \- After 2 months of building and talking to users, we managed to finish our “v2” of our product, focussed squarely on SaaS customer support and launched it today. &#x200B; We have no idea what the response will be to this new version, but we’re pretty happy with it, but couldn’t have planned anything that happened to us in 2023 so who knows what will come of 2024, we just know that we are going to be learning a ton more. &#x200B; Overall, it is probably the most I have had to think in my life - other jobs you can zone out from time to time or rely on someone else if you aren’t feeling it - not when you are doing this, case and point, I am writing this with a banging head-cold right now, but wanted to get this done. A few more things we have learned along the way - context switching is unreal, as is keeping up with, learning and reacting to AI. There isn’t a moment of the day I am not thinking about what we do next. But while in some way we now have hundreds of bosses (our customers) I still haven’t felt this free and can’t imagine ever going back to work for someone else. Next year we’re really hoping to figure out some repeatable distribution channels and personally, I want to get a lot better at creating content/writing, this is a first step! Hope this helps someone else reading this to just try starting something and see what happens.

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.

We made $325k in 2023 from AI products, starting from 0, with no-code, no funding and no audience

I met my co-founder in late 2022 after an introduction from a mutual friend to talk about how to find contract Product Management roles. I was sporadically contracting at start-up at the time and he had just come out of another start-up that was wiped out by the pandemic. We hit it off, talking about ideas, sharing what other indie-hackers were doing, and given GPT-3’s prominence at the time, we started throwing around ideas about things we could build with it, if nothing else, just to learn. I should caveat, neither of us were AI experts when starting out, everything we learned has been through Twitter and blogs, my background is as an accountant, and his a consultant. Here’s how it went since then: &#x200B; Nov 2022 (+$50) \- We built a simple tool in around a week using GPT-3 fine-tuning and a no-code tool (Bubble) that helped UK university students write their personal statements for their applications \- We set some Google Ads going and managed to make a few sales (\~$50) in the first week \- OpenAI were still approving applications at the time and said this went against their “ethics” so we had to take it down &#x200B; Dec 2022 (+$200) \- We couldn’t stop coming up with ideas related to AI fine-tuning, but realised it was almost impossible to decide which to pursue \- We needed a deadline to force us so we signed up for the Ben’s Bites hackathon in late December \- In a week, we built and launched a no-code fine-tuning platform, allowing people to create fine-tuned models by dragging and dropping an Excel file onto it \- We launched it on Product Hunt, having no idea how to price it, and somehow managed to get \~2,000 visitors on the site and make 2 sales at $99 &#x200B; Jan 2023 (+$3,000) \- We doubled down on the fine-tuning idea and managed to get up to \~$300 MRR, plus a bunch of one-time sales and a few paid calls to help people get the most out of their models \- We quickly realised that people didn’t want to curate models themselves, they just wanted to dump data and get magic out \- That was when we saw people building “Talk with x book/podcast” on Twitter as side projects and realised that was the missing piece, we needed to turn it into a tool \- We started working on the new product in late January &#x200B; Feb 2023 (+$9,000) \- We started pre-selling access to an MVP for the new product, which allowed people to “chat with their data/content”, we got $5,000 in pre-sales, more than we made from the previous product in total \- By mid-February, after 3 weeks of building we were able to launch and immediately managed to get traction, getting to $1k MRR in < 1 week, building on the hype of ChatGPT and AI (we were very lucky here) &#x200B; Mar - Jul 2023 (+$98,000) \- We worked all the waking hours to keep up with customer demand, bugs, OpenAI issues \- We built integrations for a bunch of services like Slack, Teams, Wordpress etc, added tons of new functionality and continue talking to customers every day \- We managed to grow to $17k MRR (just about enough to cover our living expenses and costs in London) through building in public on Twitter, newsletters and AI directories (and a million other little things) \- We sold our fine-tuning platform for \~$20k and our university project for \~$3k on Acquire &#x200B; Aug 2023 (+$100,000) \- We did some custom development work based on our own product for a customer that proved pretty lucrative &#x200B; Sep - Oct 2023 (+$62,000) \- After 8 months of building constantly, we started digging more seriously into our usage and saw subscriptions plateauing \- We talked to and analysed all our paying users to identify the main use cases and found 75% were for SaaS customer support \- We took the leap to completely rebuild a version of our product around this use case, our biggest to date (especially given most features with no-code took us <1 day) &#x200B; Nov - Dec 2023 (+$53,000) \- We picked up some small custom development work that utilised our own tech \- We’re sitting at around $22k MRR now with a few bigger clients signed up and coming soon \- After 2 months of building and talking to users, we managed to finish our “v2” of our product, focussed squarely on SaaS customer support and launched it today. &#x200B; We have no idea what the response will be to this new version, but we’re pretty happy with it, but couldn’t have planned anything that happened to us in 2023 so who knows what will come of 2024, we just know that we are going to be learning a ton more. &#x200B; Overall, it is probably the most I have had to think in my life - other jobs you can zone out from time to time or rely on someone else if you aren’t feeling it - not when you are doing this, case and point, I am writing this with a banging head-cold right now, but wanted to get this done. A few more things we have learned along the way - context switching is unreal, as is keeping up with, learning and reacting to AI. There isn’t a moment of the day I am not thinking about what we do next. But while in some way we now have hundreds of bosses (our customers) I still haven’t felt this free and can’t imagine ever going back to work for someone else. Next year we’re really hoping to figure out some repeatable distribution channels and personally, I want to get a lot better at creating content/writing, this is a first step! Hope this helps someone else reading this to just try starting something and see what happens.

🚀 Noob Seeking Go To Market experts! What are the most effective strategies to launch an AI Saas in the market and gain early traction with potential clients?

Question: What are some ways you have successfully gone to market for an AI Saas product? Any great (not good, but great) resources? Background: I have little sense of what is the most effective use of my time as I am feeling spread too thin. Creating a startup is not dissimilar to my job (identify problems, design tech based solutions, and roll out to 40,000 employees); however… I’ve never worked on a project where people a) pay for these solutions b) choices in what solutions they go with.

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.

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;

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

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.

Dangers of not adopting AI strategies?

Tldr: I need to know how AI is threatening different types of businesses. Please share your perspective. I'll reply to every comment. Hi, this is for anyone concerned with how to respond to the emergence of new AI tools. (to grow instead of going out of business, find opportunities instead of getting beat by competitors, etc. I need to find the best ways to use AI to give my clients an advantage. (I’m a mod at r/writingservice & a content/brand strategist.) Not just automation. That's weak. I mean innovation. Using AI to do stuff that has never been done in your industry. Lots of virtual assistants (for business owners) will make the mistake of learning how to use these tools only in a general way, without applying them in the real world. I don’t want to make that mistake. It will help me if you share what’s on your mind, what’s unique about the way AI affects your industry, or your unique business model, etc. So this is basically like an informal research study. And it's the kind where you get something if you participate - I will seriously spend time to offer the best stuff I know in the comments if you just share your perspective, how AI is affecting you in the unique way you are situation in your industry and among your competitors. Have you been finding ways to incorporate AI in your marketing, customer service, etc.? I have a feeling a lot of business owners are worried right now, because all our experience is from the old landscape prior to everything being automated with AI. Even if you have questions on your mind and share them, that can help me. My problem: I’m learning to use GPT/Gemini/Invideo/Perplexity and others, but it’s not good enough until I see how they apply in different situations, industries, business models. If you share some ideas, I’ll reply to every comment and try to offer something helpful. I’ve already made a lot of progress learning how the strengths/weaknesses of different AI tools for different situations. Thinking about the way their competitors might surpass you by using them, or about opportunities for you to surpass them.... what concerns are on your mind? Or what have you learned, what are you doing, etc.

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.

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?

I got fired due to automation — lessons learned. Two-month overview.

UPD: Guys, I'm not promoting myself as some of the redditors decided. That's why to deal with contradictions I'll do next things: make additional post with short review and description of the general tools and processes you could apply. help only those who have already written me. So I won't answer on new offers or DMs. As mentioned, damn robots have taken my job. PRE-HISTORY During Covid times, I found myself without my offline job, and since I was interested in marketing and SMM, I began searching for a job there. Completed free Google and Udemy courses and finally landed my first SMM manager position with a business owner. He had several projects so, finally, I started managing three Twitter accounts, two Facebook accs, two IGs, and one TikTok. I handled posting, content editing and responding routine, while freelancers usually took care of video creation for IG and TT. THE STORY ITSELF Things took a turn for the worse in April when my employer introduced ChatGPT and Midjourney, tools I was already using. The owner insisted on integrating them into the workflow, and my wages took a 20% hit. I thought I could roll with it, but it was just the beginning. By midsummer, the owner implemented second-layer AI tools like Visla, Pictory, and Woxo for video (bye freelancers, lol), as well as TweetHunter, Jasper, and Perplexity for content. Midjourney and Firefly joined for image generation. All together, my paycheck was slashed by 50%. Finally, at the end of October, my boss told me he automated stuff with Zapier, cutting costs that way. Additionally, he adopted MarketOwl, autoposting tool for Twitter, and SocialBee for Facebook. He stated that he didn’t need me, as by now he could manage the social media accounts himself. I feel so pissed then and even thought that there's no point in searching for similar jobs. HOW I SPENT TWO MONTHS Well, for the first two weeks, I did nothing but being miserable, drinking and staring at the wall. My gf said it's unbearable and threatened to leave if I not pull myself together. It was not the final push, but definitely made me rethink things. So I decided to learn more about the capabilities of these automation covers and eventually became an AI adviser for small businesses. It's ironic that now I sometimes earn money advising on how to optimize marketing, possibly contributing to other people's job loss. FINAL THOUGHTS I am fully aware of the instability of such a job and have invested my last savings in taking an online marketing course at Columbia to gain more marketing experience and got something more stable afterwards. Message for mods: I'm not promoting myself or anything mentioned here; just sharing the experience that someone might find helpful.

If I hadn’t done this, I wouldn’t have made any money

If you’re just starting out, and you have an idea but aren’t sure whether it will work or not, just DO IT. I started my solopreneur journey 3 months ago with the idea of building an AI website builder. In the process, I learned a ton: integrating services like payment systems, authentication, and email, copywriting, design, analytics, UX, implementing features, prioritizing tasks, and so much more. Yet, I feel like this is just the tip of the iceberg. Even though I didn’t make a single penny with my first project, I learned a ton of sh\*. Now, I’m building something that works. It took me 3–4 days to create the MVP and, just 7 days later, I made my first sale. If I hadn’t built my first project, I wouldn’t have realized how important it is to differentiate from the competition, to solve a real problem with a unique solution. That realization led me to the idea I’m building now. It's by scratching my own itch from the first idea, that I am building something of value now. And this cycle will probably continue, as long as I’m willing to learn from my mistakes and stay determined to succeed. I GUARANTEE it works this way. I don’t know how long it’ll take to hit $5K or $10K MRR, but I know one thing: if I don’t stop, it’s just a matter of time.

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

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

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.

I built a Word Ladder game using AI only - ZERO coding

Hey fellow devs!!! I'm excited to share a unique project I've just completed: an online Word Ladder game built entirely using AI assistance, specifically Claude.ai. The kicker? I wrote zero lines of code myself! 🔗 Check it out: https://www.wordladdergame.com Why this matters: AI-Driven Development: This project showcases the potential of AI in software development. Everything from architecture decisions to actual code implementation was guided by AI. Zero Manual Coding: As someone with a product background but limited coding experience, I was able to bring a full-fledged web app to life without writing a single line of code myself. Rapid Prototyping: The entire process, from ideation to deployment, was incredibly fast compared to traditional development methods. I did the whole thing in under 4 hours and spent another 4 hours tweaking it (also using AI) Learning Opportunity: This approach allowed me to understand modern web development practices and technologies without getting bogged down in syntax and debugging. Tech Stack (all implemented through AI guidance): Next.js TypeScript Prisma (with PostgreSQL) Tailwind CSS Vercel for deployment The game features randomly generated word pairs, a solve button, and a clean, responsive UI. But more than the game itself, I'm excited about what this development process represents for the future of software creation. I'd love to hear your thoughts: Have you experimented with AI-assisted development? How do you see this changing the landscape for entrepreneurs and non-technical founders? What potential challenges or limitations do you foresee with this approach? Feel free to try the game and ask any questions about the development process. I'm here to discuss and learn from your insights!

From research paper to a tech startup - help!

Hi! I'm a CS master student that loves being creative. I’ve always wanted to start a business. I have gotten offers to join other startups when I took my bachelors, but personally I never believed in the startups, so I’ve always ended up politely declining on any startup offers. But my master thesis idea is very intriguing. However, I still feel very lost. I can’t even think of any good company names, or where I would even find enthusiastic co founders.  My master thesis as an AI startup with large potential. As of today, I have not started on the product itself. I will write a paper on the product, and finish the thesis in August 2026. My supervisor suggested that this is a good startup idea, and has a large market potential. I want to try. I’ve written about my goals, milestones, and some questions. Feel free to help me in any way, by answering my questions below. Goal:  Learn about startups and non-technical part of it (business, finance, sales, etc) (I'm clueless here) Build the business part time Try and fail Milestones Complete my paper on the product Create MVP for customers to test Validate idea and check market Find company name, acquire domain and launch SaaS  Get feedback, do networking and improve the product Join a Startup Lab and find Cofounders. The following roles would need to be filled  CEO (Me, Vision and tech expert) COO (Business strategy, operations, and scaling.),  CMO (marketing and sales responsible, working to acquire new business) CPO (Product design, user experience, and frontend development)  Formally create the company, divide shares, hold weekend work meeting, pick company name (again) Goal: create product for an industry (the product can be tailored to different industries) and get the first clients. Work that needs to be done: Tech: Create the product for the industry  COO: pitching competitions, define the sales pitch, and how to price the product CMO: find out how marketing should be done, and what companies to contact for demo CMO: design company logo, design web page for business usage, create front page of the website  Growth + Profits Questions Between now, and until I have the working demo, what should I do with my time? I have courses where I learn technical skills for the company. It does not make sense to create the website for the product, when I don't know how the user would interact with the product.  Should I start the company even before the product is made? (While I'm a student and working on the paper) How can I acquire non-technical skills for running a business? I prefer reading books. How can I learn about software companies (practical skills)? For example: How to lower hosting costs?  How to price a product for customers and a product for business? (Software contracts) How to guarantee  privacy when it comes to business documents?  I’m planning on searching for co-founders, after I have validated the idea myself. Should I instead find co founders before I have even created the product? (with no guarantee that there would even be a product?) Should I try to make the product without co-founders? (This is my first startup, so it might tank within the first few months) Any experience with starting a software business while working full time? Thank you for all the help!

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 😛

B2B Marketers: What’s Your #1 Tip for Selling SaaS to Other Businesses? (Building a Tool for Shopify SEO)

Hi everyone! I’m part of a team building an AI-powered SEO tool specifically for Shopify stores (think automated technical fixes, predictive keyword optimization, etc.). We’re in the early stages and want to learn from seasoned B2B marketers: We’re struggling with: How to position a technical SaaS product to non-technical Shopify merchants. Cutting through the noise in a crowded SEO tools market. Building trust quickly with time-strapped business owners. Questions for B2B Marketing Pros: What’s the biggest mistake you made when marketing a SaaS product to businesses? What’s one underrated tactic that’s worked wonders for B2B lead gen? How do you prove ROI to skeptical buyers? (Especially for something abstract like SEO.) What’s your go-to channel for cold outreach that doesn’t feel spammy? What’s a hidden psychological trigger that works in B2B sales? What’s the best way to leverage case studies/testimonials when you’re just starting out? What’s one thing most founders waste money on in B2B marketing? For Those Who’ve Sold to Shopify Merchants: What’s their biggest pain point when evaluating tools? What type of content (webinars, blogs, demos) convinces them to buy? The Deal: We’ll compile all advice into a guide and credit contributors. If you're willing to have a virtual coffee chat, please reach out to us, we are always willing to listen to your wisdom!

Seeking co-founder to build LinkedIn’s biggest rival(curated version)

How do you connect with likeminded people? You see the polished wins everywhere, but what about the messy drafts , the awkward pitches and the moments you’re not sure you’ve got it right? Problem: The whole idea of founding and starting a business can be super intimidating for some people, specially those who don’t know any founders personally, those who don’t have a large network, those who don’t have rich parents with large networks, those not inserted in an entrepreneurial culture like in the US for example (which is my case). Sometimes all you need is the right support network, and too see others do what you want, to know that it’s possible! Everyone has an “ultimate guide” to make 7 figures or build a business on YouTube but NO ONE shoes you the HOW, just the results… I’ve tried joining founder communities, LinkedIn ,Reddit … you name it. Most of these founder communities are inaccessible for regular people and often ask for you to have an already existing business with a min ARR… or their simply geography based and if you’re not in a certain area you can’t really participate… As of LinkedIn… full of empty AI generated posts about how some random dude raised $10m in 7 days. Okay Jonathan, but what about the HOW?? How did you write your first pitch? How many rejection calls did you get? What is an MVP? There simply isn’t a platform out there to document your founding journey and find inspiration within a community of people who are doing the same as you. What better way to feel motivated then to see someone actually document their process? Solution: I’m working on building a social media platform for aspiring/founders to connect through the RAW, UNFILTERED process of turning ideas into reality in REAL time. It’s all gonna be around the “building in public “ concept and content creation. Picture an instagram/tiktok profile where instead of seeing someone’s dog you see them documenting their founding process—from the moment they had the idea, to the moment they launched, you’re going to see the successes, the fails, the rejected calls, all documented through actual content and not some AI generated LinkedIn post. Imagine if you wanted to learn about how Steve Jobs started Apple , you could simply go through his profile on this app—exactly. To make sure all interactions are meaningful people would have to apply. It’s a truly curated community, with REAL people, building REAL things in REAL time, and not just tell us the story of how they did it… Audience: I’m targeting people who have a burning desire of building a business and early stage founders starting their founder journeys, that don’t have a support network and simply don’t know where to start. People who are tired of watching 30 min “ultimate guides “ on how to make it on YouTube from “business gurus” selling courses. People who haven’t reached the min ARR required to join an “exclusive “ founder a community. People who can’t simply just move to the US to get into the “exclusive” YC combinator. People who want to connect with real people building real things and not anonymous people on Reddit, or LinkedIn influencers again trying to promote their services. I believe in the idea because I’m also part of my audience. Have always wanted to start my own thing just never knew how to and where to find a community of likeminded people . I don’t know any founders myself, I come from a non-entrepreneurial society and I’d pay good money to access a community of REAL passionate founders building REAL things, in REAL time. This would be my first ever business, and I want to share my journey building it and hopefully inspire others to just start so I’ve created a mailing list to keep anyone interested in the project updated on my fails , learnings and successes. I’m not worried about “making it” but just “starting” and hopefully reach the right audience and inspire anyone to start whatever they have marinating in their thoughts. If you’re a founder struggling with staying consistent or an aspiring founder with an insane desire of starting and don’t know how to start, I’d love to get your feedback on what’s stopping you, your challenges starting out and what you’d find useful in such platform. And finally would this be something that interests you?? PS: casually looking for a technical co-founder

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 realized that AI will create equal footing for non-technical / non-coders compared to coders

Hey fellow entrepreneurs, I started my current entrepreneurial journey following the advice to “build something that solves a problem you have.” As a coder, I wanted to code faster/better/stronger/etc. So I tried out dozens of AI coding tools to see the state of the market.  I took the best components I saw and started making my own flavor of tool, but sort of shelved it because as a coder I felt that the results were a bit alien (such as getting the AI to follow my code style, write idiomatic code, or refactor the same way I would.) I concluded that building AI coding tools for coders is tricky because as coders we’re so particular about the specifics of our code. Meanwhile, my absolutely non-technical friend was hitting me up to help him build a website for a new real-estate company that he’s launching, and he wanted my help. I really respect his hustle, but I was swamped trying to figure out my own product/market, so I told him he could use my AI coder and I would try to help out when he got stuck. He didn’t get stuck though, not once, and he launched his site over the weekend. I was truly shocked he did it all on his own, so I asked him to share his logs. It was wild – he managed to code a more or less state of the art website (good design, SEO, well-structured source code, Google Analytics, mailing lists. etc.) with absolutely no help. It cost him less than $100 in AI credits, instead of the price quotes of $20,000 - $50,000 from freelancers and agencies. Now I’m seriously pursuing AI coding tools again, but this time with a new passion: AI for non-coder / non-technical people is a 100x game changer. I think 2025 is going to be the year of the entrepreneur, where there will be a hundred times the businesses started because what held people back before was the lack of a technical co-founder or the cash to compensate engineers. Now it costs next to nothing to get started. I’m curious if anyone else has had a similar realization? Anyway, I’ve put the link below to my GitHub if you want to try it (open source, you pay for AI credits). But the main reason for my post is that I feel like I’m living in this new world of realization that being a human on earth is going to get a LOT more interesting in the coming years. There’s literally no excuse to take a job you hate, and nothing stopping people from launching a business. For anyone interested in checking it out or providing feedback you can search for kodu ai on github or kodu ai on google Best of luck to everyone on your entrepreneurial journey! P.s not sure if this is the right flair

What's some good AI software for entrepreneurs?

I just started running a smaller business as a side gig and am in need of getting some manual work off my shoulders. This business is basically a hobby turned business as something I've been wanting to get into for a long time but just got the courage to do so this year. I'm making hand-made jewelry that's kind of a niche but has a tiny little tight market with relatively active and supportive buyers. Of course, a huge part of my job is answering all kinds of questions, covering spreadsheets, and doing market research to try and find new customer groups. The majority of this work is relatively simple what I’d call “manual”, which is why I feel like it could be done by AI, at the very least with the precision that I need. I did find some help using Chat GPT 4 so far, especially with handling my spreadsheets and market research. I usually let it do some manual labor on the spreadsheets, and I’ve even managed to train it to do some more complex tasks like researching the market and putting the results in the spreadsheet that I can use. ChatGPT isn’t that good at answering messages however because the answers are pretty generic and I have to manually generate responses and send them which takes arguably even more time than just responding myself. For this task, Personal AI has been proven to be way more useful because it’s literally a personalized AI model that can be trained to accurately respond to anything + once you create your own personal AI, other people can ask questions there instead of messaging me directly and get instant responses from the AI that are based on the knowledge I fed it. Still testing the tool, but so far it has been quite useful and saved me a ton of time. I also used Poll the People a few times to get feedback from my customers, and it worked magnificently. I'd like to hear some recommendations on AI tools that can be useful to someone who's just entering this world so please shoot them!

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

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.

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.

I have reviewed over 900+ AI Tools for my directory. Here are some of the best ones I have seen for entrepreneurs and startups.

As one of the co-founders at AI Scout, a platform for AI discovery, I've had the privilege (and challenge) of reviewing over 900 AI tools submitted to our directory. I've filtered these down to some of the top AI tools that I believe could bring value to startups and entrepreneurs. It's worth noting that while these tools are great right out the box, the power of AI is truly realized when these tools are used in tandem and strategically aligned with your business needs. The challenge most people face is not about the lack of AI tools available, but the difficulty in finding the right one that fits their specific needs and workflows. Without further ado, here's my top pick of AI tools you should consider looking into if you are an entrepreneur or run a startup. Chatbase - Custom ChatGPT (Trained on Your Own Data) Taking a step up from traditional support bots, Chatbase combines the power of GPT and your own knowledge base. The result is a ChatGPT-like chatbot that is trained on your own websites and documents. You can embed the chatbot into your own website via an iframe or script in the header of your website code. They also have an API you can take advantage of. We use this personally at AI Scout for ScoutBud (AI assistant to find AI tools), which we trained based on our directory site. It would also work great if you have extensive documentation, papers, etc. that you want to quickly reference by simply asking a chatbot for the info you need instead of having to go through dozens of PDFs. Reply - AI-Powered Sales Engagement Platform Great AI tool to manage your entire sales engagement cycle. They have a large database with about a dozen filters to discover optimal B2B leads. From here, you can use their GPT integration to generate cold emails as well as handle responses and meeting scheduling. What I like personally about Reply are the endless integrations available, including Gmail, Outlook, Zoho, and major social platforms such as Twitter and LinkedIn. Instapage - AI Landing Page Generation, Testing, and Personalization This AI tool allows users to generate content variations for landing pages including headlines, paragraphs, and CTAs based on the target audience. You can also conduct A/B testing for more effective and efficient campaigns. Paired with hundreds of professional and cutomizable layouts, Instapage is definitely something I would recommend for entrepreneurs who want to get a high-converting landing page set up quickly and effectively. SaneBox - AI Emails Management If you feel overwhelmed by the sheer volume of emails you receive like myself and many entrepreneurs, this could be something for you. SaneBox’s AI identifies important emails and declutters your inbox, helping you to stay focused on what truly matters. SocialBee - AI Social Media Manager Think of SocialBee as your all-in-one social media command center, powered by AI. You can manage multiple social media accounts from one platform and generate captions with AI as well. SocialBee not only allows you to schedule posts but also helps you analyze growth and engagement with detailed reports. Works well with all social media platforms, including Facebook, Twitter, Instagram, and Linkedin. I believe they also have integrations for TikTok and YouTube, although I haven't tried these personally. MeetGeek - AI Meeting Assistant Lifesaver if you attend a lot of meetings or calls. Great for transcribing, summarizing, and sharing key insights from meetings. The AI also creates meeting highlights, which I've personally fouund quite useful if you ever need to get a very quick and dirty overview of what happened in a call. It also provides analysis (including sentiment evaluation) for meetings. Taskade - AI Productivity Tool for Task Management An all-in-one AI productivity tool. Multiple AI features available, including a chatbot, writing assistant, and workflow creator. It's a great all-around tool for real-time collaboration and efficient task management. Scribe AI (ScribeHow) - AI Documentation Generator Great for any SaaS applications where you need to create resources/documentations/guides for your app. You simply record your process and Scribe generates a written guide for you. Remember, while AI is an excellent assistant, it's also just a tool. The ultimate success of your venture depends on how effectively you leverage these tools. Happy experimenting!

Detailed Guide - How I've Been Self Employed for 2 Years Selling Posters

Hey everyone, bit of context before you read through this. I have been selling POD posters full time for over 2 years now. My next venture is that I have started my own Print on Demand company for posters, PrintShrimp. As one way of creating customers for our service, we are teaching people for free how to also sell posters. Here is a guide I have written on how to sell posters on Etsy. Feel free to have a read through and then check out PrintShrimp, hopefully can help some of you guys out (and get us some more customers!) All of this is also available in video format on our website too, if you prefer to learn that way. Thanks guys! And as some people asked in other subs, no this isn't written with AI 😅 This took a couple of weeks to put together! Through this guide, we will teach you everything you need to know about starting to sell posters and generate some income. We will also show you why PrintShrimp is the best POD supplier for all of your poster needs. Trust me, you won’t need much convincing.  So, why are posters the best product to sell? Also, just thought I’d quickly answer the question - why posters? If you’ve been researching Print on Demand you’ve probably come across the infinite options of t-shirts, mugs, hats, phone cases, and more. All of these are viable options, however we think posters are the perfect place to start. You can always expand into other areas further down the line! So a brief summary of why posters are the perfect product for Print on Demand: \-They are very easy to design! Posters are a very easy shape to deal with - can’t go wrong with a rectangle. This makes designing products very easy. \-Similarly to this, what you see is what you get with a poster. You can literally see your finished product as you design it in either canva or photoshop. With T-Shirts for example, you have to make your design, and then place it on a t-shirt. Then you have to coordinate with your printers the size you would like the design on the tshirt and many other variables like that. There is no messing about with posters - what you see is what you get. \-The same high quality, everywhere. With other products, if you want to reap the benefits of a printing in various countries, you need to ensure each of your global suppliers stocks the same t-shirts, is able to print in the same way, carries the same sizes etc. Again with posters you avoid all of this hassle- your products will come out the same, no matter which of our global locations are used. \-They have a very favorable profit margin. As you will see later, the cost price of posters is very low. And people are prepared to pay quite a lot for a decent bit of wall art! I have tried out other products, and the profit margin combined with the order quantity of posters makes them my most profitable product, every single time. Using PrintShrimp, you can be sure to enjoy profits of anywhere between £6 - £40 pure profit per sale.  \-They are one of the easiest to print white label. This makes them perfect for Print on Demand. Your posters are simply put in a tube, and off they go. There are no extras you need to faff around with, compared to the extra elements other products come with, such as clothing labels on t-shirts.  Picking your poster niche So, you are ready to start selling posters. Great! Now, the blessing and curse with selling posters is that there are infinite possibilities regarding what you can sell. So, it can easily be quite overwhelming at first.  The first thing I would recommend doing is having a look at what others are selling. Etsy is a wonderful place for this (and will likely be a key part of your poster selling journey). So, log on to Etsy and simply type in ‘poster’ in the search bar. Get ready to write a massive list of the broad categories and type of posters that people are selling.  If you do not have more than 50 categories written down by the end, you are doing something wrong. There are seriously an infinite amount of posters! For example, here are some popular ones to get you started: Star sign posters, Kitchen posters, World map posters, Custom Dog Portrait posters, Music posters, Movie posters, Fine art posters, Skiing posters, Girl Power posters and Football posters.  Now, you have a huge list of potential products to sell. What next? There are a few important things you need to bear in mind when picking your niche: \-Does this interest me?  Don’t make the mistake of going down a niche that didn’t actually interest you just because it would probably be a money maker. Before you know it, what can be a very fun process of making designs can become incredibly \\\monotonous, and feel like a chore\\\. You need to bear in mind that you will be spending a lot of time creating designs - if it is something you are interested in you are much less likely to get burnt out! As well, \\\creativity will flow\\\ far better if it is something you are interested in, which at the end of the day will lead to better designs that are more likely to be purchased by customers.  \-Is this within my design range? Don’t let this put you off too much. We will go through how to get started on design later on in this guide. However, it is important to note that the plain truth of it is that some niches and designs are a hell of a lot more complicated than others. For example, quote posters can essentially be designed by anyone when you learn about how to put nice fonts together in a good color scheme. On the other hand, some posters you see may have been designed with complex illustrations in a program like Illustrator. To start with, it may be better to pick a niche that seems a bit more simple to get into, as you can always expand your range with other stores further down the line. A good way of evaluating the design complexity is by identifying if this poster is \\\a lot of elements put together\\\ or is \\\a lot of elements created by the designer themselves\\\\\.\\ Design can in a lot of cases be like a jigsaw - putting colours, shapes and text together to create an image. This will be a lot easier to start with and can be learnt by anyone, compared to complex drawings and illustrations.  \-Is this niche subject to copyright issues? Time to delve deep into good old copyright. Now, when you go through Etsy, you will without a doubt see hundreds of sellers selling music album posters, car posters, movie posters and more. Obviously, these posters contain the property of musicians, companies and more and are therefore copyrighted. The annoying thing is - these are \\\a complete cash cow.\\\ If you go down the music poster route, I will honestly be surprised if you \\don’t\\ make thousands. However it is only a matter of time before the copyright strikes start rolling in and you eventually get banned from Etsy.  So I would highly recommend \\\not making this mistake\\\. Etsy is an incredible platform for selling posters, and it is a hell of a lot easier to make sales on there compared to advertising your own website. And, you \\\only get one chance on Etsy.\\\ Once you have been banned once, you are not allowed to sign up again (and they do ID checks - so you won’t be able to rejoin again under your own name).  So, don’t be shortsighted when it comes to entering Print on Demand. If you keep your designs legitimate, they will last you a lifetime and you will then later be able to crosspost them to other platforms, again without the worry of ever getting shut down.  So, how do I actually design posters? Now you have an idea of what kind of posters you want to be making, it’s time to get creative and make some designs! Photoshop (and the creative cloud in general) is probably the best for this. However, when starting out it can be a scary investment (it costs about £30 a month unless you can get a student rate!).  So, while Photoshop is preferable in the long term, when starting out you can learn the ropes of design and get going with Canva. This can be great at the start as they have a load of templates that you can use to get used to designing and experimenting (while it might be tempting to slightly modify these and sell them - this will be quite saturated on places like Etsy so we would recommend doing something new).  What size format should I use? The best design format to start with is arguably the A sizes - as all the A sizes (A5, A4, A3, A2, A1, A0) are scalable. This means that you can make all of your designs in one size, for example A3, and these designs will be ready to fit to all other A sizes. For example, if you design an A3 poster and someone orders A1, you can just upload this A3 file to PrintShrimp and it will be ready to print. There is a wide range of other sizes you should consider offering on your shop, especially as these sizes are very popular with the American market. They have a wide range of popular options, which unfortunately aren’t all scalable with each other. This does mean that you will therefore have to make some slight modifications to your design in order to be able to offer them in American sizing, in a few different aspect ratios. What you can do however is design all of your products in UK sizing, and simply redesign to fit American sizing once you have had an order. Essentially: design in UK sizing, but list in both UK and US sizing. Then when you get a non-A size order, you can quickly redesign it on demand. This means that you don’t have to make a few different versions of each poster when first designing, and can simply do a quick redesign for US sizing when you need to. Below is PrintShrimps standard size offering. We can also offer any custom sizing too, so please get in touch if you are looking for anything else. With these sizes, your poster orders will be dispatched domestically in whatever country your customer orders from. Our recommendations for starting design One thing that will not be featured in this guide is a written out explanation or guide on how to design. Honestly, I can’t think of a more boring, or frankly worse, way to learn design. When it comes to getting started, experimenting is your best friend! Just have a play around and see what you can do. It is a really fun thing to get started with, and the satisfaction of when a poster design comes together is like no other. A good way to start is honestly by straight up copying a poster you see for sale online. And we don’t mean copying to sell! But just trying to replicate other designs is a great way to get a feel for it and what you can do. We really think you will be surprised at how easy it is to pull together a lot of designs that at first can appear quite complicated! Your best friend throughout this whole process will be google. At the start you will not really know how to do anything - but learning how to look into things you want to know about design is all part of the process. At first, it can be quite hard to even know how to search for what you are trying to do, but this will come with time (we promise). Learning how to google is a skill that you will learn throughout this process.  Above all, what we think is most important is this golden rule: take inspiration but do not steal. You want to be selling similar products in your niche, but not copies. You need to see what is selling in your niche and get ideas from that, but if you make designs too similar to ones already available, you won’t have much luck. At the end of the day, if two very similar posters are for sale and one shop has 1000 reviews and your newer one has 2, which one is the customer going to buy? You need to make yours offer something different and stand out enough to attract customers. Etsy SEO and maximizing your sales You may have noticed in this guide we have mentioned Etsy quite a few times! That is because we think it is hands down the best place to start selling posters. Why? Etsy is a go to place for many looking to decorate their homes and also to buy gifts. It might be tempting to start selling with your own website straight away, however we recommend Etsy as it brings the customers to you. For example, say you start selling Bathroom Posters. It is going to be a hell of a lot easier to convert sales when you already have customers being shown your page after searching ‘bathroom decor’, compared to advertising your own website. This is especially true as it can be hard to identify your ideal target audience to then advertise to via Meta (Facebook/Instagram) for example. Websites are a great avenue to explore eventually like I now have, but we recommend starting with Etsy and going from there. What costs do I need to be aware of? So, setting up an Etsy sellers account is currently costs £15. The only other upfront cost you will have is the cost of listing a product - this is 20 cents per listing. From then on, every time you make a sale you will be charged a transaction fee of 6.5%, a small payment processing fee, plus another 20 cents for a renewed listing fee. It normally works out to about 10% of each order, a small price to pay for all the benefits Etsy brings. No matter what platform you sell on, you will be faced with some form of transaction fee. Etsy is actually quite reasonable especially as they do not charge you to use their platform on a monthly basis.  What do I need to get selling? Getting your shop looking pretty \-Think of a shop name and design (now you are a professional designer) a logo \-Design a banner for the top of your shop \-Add in some about me info/shop announcement \-I recommend running a sale wherein orders of 3+ items get a 20% of discount. Another big benefit of PrintShrimp is that you receive large discounts when ordering multiple posters. This is great for attracting buyers and larger orders.  Making your products look attractive That is the bulk of the ‘decor’ you will need to do. Next up is placing your posters in mock ups! As you may notice on Etsy, most shops show their posters framed and hanging on walls. These are 99% of the time not real photos, but digital mock ups. This is where Photoshop comes in really handy, as you can automate this process through a plug in called Bulk Mock Up. If you don’t have photoshop, you can do this on Canva, you will just have to do it manually which can be rather time consuming.  Now, where can you get the actual Mock Ups? One platform we highly recommend for design in general is platforms like Envato Elements. These are design marketplaces where you have access to millions of design resources that you are fully licensed to use!  Titles, tags, and descriptions  Now for the slightly more nitty gritty part. You could have the world's most amazing looking poster, however, if you do not get the Etsy SEO right, no one is going to see it! We will take you through creating a new Etsy listing field by field so you can know how to best list your products.  The key to Etsy listing optimisation is to maximise. Literally cram in as many key words as you possibly can! Before you start this process, create a word map of anything you can think of relating to your listing. And come at this from the point of view of, if I was looking for a poster like mine, what would I search? Titles \-Here you are blessed with 140 characters to title your listing. Essentially, start off with a concise way of properly describing your poster. And then afterwards, add in as many key words as you can! Here is an example of the title of a well selling Skiing poster: Les Arcs Skiing Poster, Les Arcs Print, Les Alpes, France Ski Poster, Skiing Poster, Snowboarding Poster, Ski Resort Poster Holiday, French This is 139 characters out of 140 - you should try and maximise this as much as possible! As you can see, this crams in a lot of key words and search terms both related to Skiing as a whole, the poster category, and then the specifics of the poster itself (Les Arcs resort in France). Bear in mind that if you are listing a lot of listings that are of the same theme, you won’t have to spend time creating an entirely new title. For example if your next poster was of a ski resort in Italy, you can copy this one over and just swap out the specifics. For example change “France ski poster” to “Italy ski poster”, change “Les Arcs” to “The Dolomites”, etc.  Description \-Same logic applies for descriptions - try and cram in as many key words as you can! Here is an example for a Formula One poster: George Russell, Mercedes Formula One Poster  - item specific keywords Bright, modern and vibrant poster to liven up your home.  - Describes the style of the poster All posters are printed on high quality, museum grade 200gsm poster paper. Suitable for framing and frames. - Shows the quality of the print. Mentions frames whilst showing it comes unframed Experience the thrill of the racetrack with this stunning Formula One poster. Printed on high-quality paper, this racing car wall art print features a dynamic image of a Formula One car in action, perfect for adding a touch of speed and excitement to any motorsports room or man cave. Whether you're a die-hard fan or simply appreciate the adrenaline of high-speed racing, this poster is sure to impress. Available in a range of sizes, it makes a great addition to your home or office, or as a gift for a fellow Formula One enthusiast. Each poster is carefully packaged to ensure safe delivery, so you can enjoy your new piece of art as soon as possible. - A nice bit of text really highlighting a lot of key words such as gift, motorsports, racetrack etc.  You could go further with this too, by adding in extra things related to the poster such as ‘Perfect gift for a Mercedes F1 fan’ etc.  Tags Now, these are actually probably the most important part of your listing! You get 13 tags (20 character limit for each) and there are essentially search terms that will match your listing with what customers search for when shopping.  You really need to maximize these - whilst Title and Description play a part, these are the main things that will bring buyers to your listing. Once again, it is important to think about what customers are likely to be searching when looking for a poster similar to yours. Life hack alert! You can actually see what tags other sellers are using. All you need to do is go to a listing similar to yours that is selling well, scroll down and you can actually see them listed out at the bottom of the page! Here is an example of what this may look like: So, go through a few listings of competitors and make notes on common denominators that you can integrate into your listing. As you can see here, this seller uses tags such as ‘Birthday Gift’ and ‘Poster Print’. When you first start out, you may be better off swapping these out for more listing specific tags. This seller has been on Etsy for a few years however and has 15,000+ sales, so are more likely to see success from these tags.  If it’s not clear why, think about it this way. If you searched ‘poster print’ on Etsy today, there will be 10s of thousands of results. However, if you searched ‘Russell Mercedes Poster’, you will (as of writing) get 336 results. Etsy is far more likely to push your product to the top of the latter tag, against 300 other listings, rather than the top of ‘Poster Print’ where it is incredibly competitive. It is only when you are a more successful shop pulling in a high quantity of orders that these larger and more generic tags will work for you, as Etsy has more trust in your shop and will be more likely to push you to the front.  SKUs \-One important thing you need to do is add SKUs to all of your products! This is worth doing at the start as it will make your life so much easier when it comes to making sales and using PrintShrimp further down the line. What is an SKU? It is a ‘stock keeping unit’, and is essentially just a product identifier. Your SKUs need to match your file name that you upload to PrintShrimp. For example, if you made a poster about the eiffel tower, you can literally name the SKU eiffel-tower. There is no need to complicate things! As long as your file name (as in the image name of your poster on your computer) matches your SKU, you will be good to go.  \-It may be more beneficial to set up a system with unique identifiers, to make organising your files a lot easier further down the line. Say you get to 1000 posters eventually, you’ll want to be able to quickly search a code, and also ensure every SKU is always unique, so you won’t run into accidentally using the same SKU twice further down the line. For example, you can set it up so at the start of each file name, you have \[unique id\]\[info\], so your files will look like -  A1eiffeltower A2france And further down the line: A99aperolspritz B1potatoart This not only removes the potential issue of duplicating SKUs accidentally (for example if you made a few posters of the same subject), but also keeps your files well organised. If you need to find a file, you can search your files according to the code, so just by searching ‘a1’ for example, rather than having to trawl through a load of different files until you find the correct one. \-If your poster has variations, for example color variations, you can set a different SKU for each variation. Just click the little box when setting up variations that says ‘SKUs vary for each (variation)’. So if you have a poster available either in a white or black background, you can name each file, and therefore each SKU, a1eiffel-tower-black and a1eiffel-tower-white for example. \-The same goes for different sizes. As different American sizes have different aspect ratios, as mentioned above you may have to reformat some posters if you get a sale for one of these sizes. You can then add in the SKU to your listing once you have reformatted your poster. So for example if you sell a 16x20” version of the eiffel tower poster, you can name this file eiffel-tower-white-1620. Whilst this involves a little bit of set up, the time it saves you overall is massive!  Variations and Prices \-So, when selling posters there is a huge variety of sizes that you can offer, as mentioned previously. Non-negotiable is that you should be offering A5-A1. These will likely be your main sellers! Especially in the UK. It is also a good idea to offer inch sizing to appeal to a global audience (as bear in mind with PrintShrimp you will be able to print in multiple countries around the world!).  Below is a recommended pricing structure of what to charge on Etsy. Feel free to mess around with these! You may notice on Etsy that many shops charge a whole lot more for sizes such as A1, 24x36” etc. In my experience I prefer charging a lower rate to attract more sales, but there is validity in going for a lower amount of sales with higher profits. As mentioned above, you can also offer different variations on items - for example different colour schemes on posters. This is always a decent idea (if it suits the design) as it provides the customer with more options, which might help to convert the sale. You can always add this in later however if you want to keep it simple while you start! Setting up shipping profiles Etsy makes it very easy to set up different shipping rates for different countries. However, luckily with PrintShrimp you can offer free shipping to the majority of the major countries that are active on Etsy!  Using PrintShrimp means that your production costs are low enough in each domestic market to justify this. If you look on Etsy you can see there are many shops that post internationally to countries such as the US or Australia. Therefore, they often charge £8-10 in postage, and have a delivery time of 1-2 weeks. This really limits their customer base to their domestic market.  Using PrintShrimp avoids this and means you can offer free shipping (as we absorb the shipping cost in our prices) to the major markets of the UK, Australia, and USA (Europe coming soon!).  We also offer a 1 day processing time, unlike many POD poster suppliers. This means you can set your Etsy processing time to just one day, which combined with our quick shipping, means you will be one of the quickest on Etsy at sending out orders. This is obviously very attractive for customers, who are often very impatient with wanting their orders!  Getting the sales and extra tips \-Don’t list an insane amount of listings when you first get started. Etsy will be like ‘hang on a second’ if a brand new shop suddenly has 200 items in the first week. Warm up your account, and take things slow as you get going. We recommend 5 a day for the first week or so, and then you can start uploading more. You don’t want Etsy to flag your account for suspicious bot-like activity when you first get going.  \-It is very easy to copy listings when creating a new one. Simply select an old listing and press copy, and then you can just change the listing specific details to create a new one, rather than having to start from scratch. It can feel like a bit of a ball-ache setting up your first ever listing, but from then on you can just copy it over and just change the specifics.  \-Try and organize your listings into sections! This really helps the customer journey. Sometimes a customer will click onto your shop after seeing one of your listings, so it really helps if they can easily navigate your shop for what they are looking for. So, you now have a fully fledged Etsy shop. Well done! Time to start making £3,000 a month straight away right? Not quite. Please bear in mind, patience is key when starting out. If you started doing this because you are £10,000 in debt to the Albanian mafia and need to pay it off next week, you have come into this in the wrong frame of mind. If you have however started this to slowly build up a side hustle which hopefully one day become your full time gig, then winner winner chicken dinner.  Starting out on Etsy isn’t always easy. It takes time for your shop to build up trust! As I’ve said before, a buyer is far more likely to purchase from a shop with 1000s of reviews, than a brand new one with 0. But before you know it, you can become one of these shops! One thing you can do at the very start is to encourage your friends and family to buy your posters! This is a slightly naughty way of getting a few sales at the start, of course followed by a few glowing 5\* reviews. It really helps to give your shop this little boost at the start, so if this is something you can do then I recommend it.  Okay, so once you have a fully fledged shop with a decent amount of listings, you might be expecting the sales to start rolling in. And, if you are lucky, they indeed might. However, in my experience, you need to give your listings a little boost. So let us introduce you to: The wonderful world of Etsy ads Ads!! Oh no, that means money!! We imagine some of you more risk averse people are saying to yourself right now. And yes, it indeed does. But more often than not unfortunately you do have to spend money to make money.  Fortunately, in my experience anyway, Etsy ads do tend to work. This does however only apply if your products are actually good however, so if you’re back here after paying for ads for 2 months and are losing money at the same rate as your motivation, maybe go back to the start of this guide and pick another niche.  When you first start out, there are two main strategies.  Number 1: The Safer Option So, with PrintShrimp, you will essentially be making a minimum of £6 profit per order. With this in mind, I normally start a new shop with a safer strategy of advertising my products with a budget of $3-5 dollars a day. This then means that at the start, you only need to make 1 sale to break even, and anything above that is pure profit! This might not seem like the most dazzling proposition right now, but again please bear in mind that growth will be slow at the start. This means that you can gradually grow your shop, and therefore the trust that customers have in your shop, over time with a very small risk of ever actually losing money. Number 2: The Billy Big Balls Option If you were yawning while reading the first option, then this strategy may be for you. This will be better suited to those of you that are a bit more risk prone, and it also helps if you have a bit more cash to invest at the start. Through this strategy, you can essentially pay your way to the top of Etsy's rankings. For this, you’ll probably be looking at spending $20 a day on ads. So, this can really add up quickly and is definitely the riskier option. In my experience, the level of sales with this may not always match up to your spend every day. You may find that some days you rake in about 10 sales, and other days only one. But what this does mean is that as your listings get seen and purchased more, they will begin to rank higher in Etsy’s organic search rankings, at a much quicker rate than option one. This is the beauty of Etsy’s ads. You can pay to boost your products, but then results from this paid promotion feed into the organic ranking of your products. So you may find that you can splash the cash for a while at the start in order to race to the top, and then drop your ad spending later on when your products are already ranking well.  Sending your poster orders So, you’ve now done the hard bit. You have a running Etsy store, and essentially all you need to now on a daily basis is send out your orders and reply to customer messages! This is where it really becomes passive income.  \-Check out the PrintShrimp order portal. Simply sign up, and you can place individual orders through there. \-Bulk upload: We have an option to bulk upload your Esty orders via csv.  Seriously, when you are up and running with your first store, it is really as easy as that.  Once you have your first Etsy store up and running, you can think about expanding. There are many ways to expand your income. You can set up other Etsy stores, as long as the type of posters you are selling varies. You can look into setting up your own Shopify stores, and advertise them through Facebook, Instagram etc. Through this guide, we will teach you everything you need to know about starting to sell posters and generate some income. We will also show you why PrintShrimp is the best POD supplier for all of your poster needs. Trust me, you won’t need much convincing.

[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.

AI Content Campaign Got 4M impressions, Thousands of Website Views, Hundreds of Customers for About $100 — This is the future of marketing

Alright. So, a few months ago I tested a marketing strategy for a client that I’ve sense dedicated my life to developing on. The Idea was to take the clients Pillar content (their YouTube videos) and use AI to rewrite the content for all the viable earned media channels (mainly Reddit). The campaign itself was moderately successful. To be specific, after one month it became their 2nd cheapest customer acquisition cost (behind their organic YouTube content). But there is a lot to be done to improve the concept. I will say, having been in growth marketing for a decade, I felt like I had hit something big with the concept. I’m going to detail how I built that AI system, and what worked well and what didn’t here. Hopefully you guys will let me know what you think and whether or not there is something here to keep working on. DEFINING THE GOAL Like any good startup, their marketing budget was minimal. They wanted to see results, fast and cheap. Usually, marketers like me hate to be in this situation because getting results usually either takes time or it takes money. But you can get results fast and cheap if you focus on an earned media strategy - basically getting featured in other people’s publication. The thing is these strategies are pretty hard to scale or grow over time. That was a problem for future me though. I looked through their analytics and saw they were getting referral traffic from Reddit - it was their 5th or 6th largest source of traffic - and they weren’t doing any marketing on the platform. It was all digital word of mouth there. It kind of clicked for me there, that Reddit might be the place to start laying the ground work. So with these considerations in mind the goal became pretty clear: Create content for relevant niche communities on Reddit with the intent of essentially increasing brand awareness. Use an AI system to repurpose their YouTube videos to keep the cost of producing unique content for each subreddit really low. THE HIGH-LEVEL STRATEGY I knew that there are huge amounts of potential customers on Reddit (About 12M people in all the relevant communities combined) AND that most marketers have a really tough time with the platform. I also knew that any earned media strategy, Reddit or not, means Click Through Rates on our content would be extremely low. A lot of people see this as a Reddit specific problem because you can’t self-promote on the platform, but really you have to keep self-promotion to a minimum with any and all earned media. This basically meant we had to get a lot of impressions to make up for it. The thing about Reddit is if your post absolutely crushes it, it can get millions of views. But crushing it is very specific to what the expectations are of that particular subreddit. So we needed to make content that was specifically written for that Subreddit. With that I was able to essentially design how this campaign would work: We would put together a list of channels (specifically subreddits to start) that we wanted to create content for. For each channel, we would write a content guideline that details out how to write great content for this subreddit. These assets would be stored in an AirTable base, along with the transcripts of the YouTube videos that were the base of our content. We would write and optimize different AI Prompts that generated different kinds of posts (discussion starters about a stock, 4-5 paragraph stock analysis, Stock update and what it means, etc…) We would build an automation that took the YouTube transcripts, ran each prompt on it, and then edited each result to match the channel writing guidelines. And then we would find a very contextual way to leave a breadcrumb back to the client. Always as part of the story of the content. At least, this is how I originally thought things would go. CHOOSING THE RIGHT SUBREDDITS Picking the right communities was vital. Here’s the basic rubric we used to pick and prioritize them: • Relevance: We needed communities interested in stock analysis, personal finance, or investing. • Subreddit Size vs. Engagement: Large subreddits offer more potential impressions but can be less focused. Smaller subreddits often have higher engagement rates. • Content Feasibility: We had to ensure we could consistently create high-value posts for each chosen subreddit. We started with about 40 possibilities, then narrowed it down to four or five that consistently delivered upvotes and user signups. CREATING CHANNEL-SPECIFIC GUIDES By the end, creating channel specific writing guidelines looked like a genius decision. Here’s how we approached it and used AI to get it done quickly: Grabbed Top Posts: We filtered the subreddit’s top posts (change filter to “Top” and then “All Time”) of all time to see the kinds of content that performed best Compiled The Relevant Posts: We took the most relevant posts to what we were trying to do and put them all on one document (basically created one document per subreddit that just had the top 10 posts in that subreddit). Had AI Create Writing Guideline Based On Posts: For each channel, we fed the document with the 10 posts with the instructions “Create a writing guideline for this subreddit based on these high performing posts. I had to do some editing on each guideline but this worked pretty well and saved a lot of time. Each subreddit got a custom guideline, and we put these inside the “Channels” table of the AirTable base we were developing with these assets. BUILDING THE AI PROMPTS THAT GENERATED CONTENT Alright this is probably the most important section so I’ll be detailed. Essentially, we took all the assets we developed up until this point, and used them to create unique posts for each channel. This mean each AI prompt was about 2,000 words of context and produced about a 500-word draft. There was a table in our AirTable where we stored the prompts, as I alluded to earlier. And these were basically the instructions for each prompt. More specifically, they detailed out our expectations for the post. In other words, there were different kinds of posts that performed well on each channel. For example, you can write a post that’s a list of resources (5 tools we used to…), or a how to guide (How we built…), etc.. Those weren’t the specific ones we used, but just wanted to really explain what I meant there. That actual automation that generated the content worked as follows: New source content (YouTube video transcript) was added to the Source Content table. This triggered the Automation. The automation grabbed all the prompts in the prompt table. For each prompt in the prompt table, we sent a prompt to OpenAI (gpt-4o) that contained first the prompt and also the source content. Then, for each channel that content prompt could be used on, we sent another prompt to OpenAI that revised the result of the first prompt based on the specific channel guidelines. The output of that prompt was added to the Content table in AirTable. To be clear, our AirTable had 4 tables: Content Channels Prompts Source Content The Source Content, Prompts, and Channel Guidelines were all used in the prompt that generated content. And the output was put in the Content table. Each time the automation ran, the Source Content was turned into about 20 unique posts, each one a specific post type generated for a specific channel. In other words, we were create a ton of content. EDITING & REFINING CONTENT The AI drafts were never perfect. Getting them Reddit-ready took editing and revising The main things I had to go in and edit for were: • Tone Adjustments: We removed excessively cliche language. The AI would say silly things like “Hello fellow redditors!” which sound stupid. • Fact-Checking: Financial data can be tricky. We discovered AI often confused figures, so we fact check all stock related metrics. Probably something like 30-40% error rate here. Because the draft generation was automated, that made the editing and getting publish ready the human bottleneck. In other words, after creating the system I spent basically all my time reviewing the content. There were small things I could do to make this more efficient, but not too much. The bigger the model we used, the less editing the content needed. THE “BREADCRUMB” PROMOTION STRATEGY No where in my prompt to the AI did I mention that we were doing any marketing. I just wanted the AI to focus on creating content that would do well on the channel. So in the editing process I had to find a way to promote the client. I called it a breadcrumb strategy once and that stuck. Basically, the idea was to never overtly promote anything. Instead find a way to leave a breadcrumb that leads back to the client, and let the really interested people follow the trail. Note: this is supposed to be how we do all content marketing. Some examples of how we did this were: Shared Visuals with a Subtle Watermark: Because our client’s product offered stock data, we’d often include a chart or graph showing a company’s financial metric with the client’s branding in the corner. Added Supporting Data from Client’s Website: If we mentioned something like a company’s cash flow statement, we could link to that company’s cash flow statement on the client’s website. It worked only because there was a lot of data on the client’s website that wasn’t gated. These tactics were really specific to the client. Which is should be. For other companies I would rethink what tactics I use here. THE RESULTS I’m pretty happy with the results • Impressions: – Early on posts averaged \~30,000 apiece, but after about a month of optimization, we hit \~70,000 impressions average. Over about two months, we reached 4 million total impressions. • Signups: – In their signups process there was one of those “Where did you find us?” questions and the amount of people who put Reddit jumped into the few hundred a month. Precise tracking of this is impossible. • Cost Efficiency (This is based on what I charged, and not the actual cost of running the campaign which is about $100/mo): – CPM (cost per thousand impressions) was about $0.08, which is far better than most paid channels. – Cost per free user: \~$8-10. After about a 10% conversion rate to a paid plan, our cost per paying user was $80–$100—well below the client’s previous $300–$400. HIGHLIGHTS: WHAT WORKED Subreddit-Specific Content: – Tailoring each post’s format and length to the audience norms boosted engagement. Worked out really well. 1 post got over 1M views alone. We regularly had posts that had hundreds of thousands. Breadcrumbs: – We never had anyone call us out for promoting. And really we weren’t. Our first priority was writing content that would crush on that subreddit. Using the Founder’s Existing Material: – The YouTube transcripts grounded the AI’s content in content we already made. This was really why we were able to produce so much content. CHALLENGES: WHAT DIDN’T WORK AI is still off: – Maybe it’s expecting too much, but still I wish the AI had done a better job. I editing a lot of content. Human oversight was critical. Scheduling all the content was a pain: – Recently I automated this pretty well. But at first I was scheduling everything manually and scheduling a hundred or so posts was a hassle. Getting Data and Analytics: – Not only did we have not very good traffic data, but the data from reddit had to be collected manually. Will probably automate this in the future. COST & TIME INVESTMENT Setup: The setup originally took me a couple weeks. I’ve since figured out how to do much faster (about 1 week). AirTable Setup here was easy and the tools costs $24/mo so not bad. ChatGPT costs were pretty cheap. Less than $75 per month. I’ve sense switched to using o1 which is much more expensive but saves me a lot of editing time Human Editing: Because this is the human part of the process and everything else was automated it mean by default all my time was spent editing content. Still this was a lot better than creating content from scratch probably by a factor of 5 or 10. The main expense was paying an editor (or using your own time) to refine posts. Worth it? Yes even with the editing time I was able to generate way more content that I would have otherwise. LESSONS & ACTIONABLE TAKEAWAYS Reddit as a Growth Channel: – If you genuinely respect each subreddit’s culture, you can achieve massive reach on a tight budget. AI + Human Collaboration: – AI excels at first drafts, but human expertise is non-negotiable for polishing and ensuring factual integrity. Soft Promotion Wins: – The “breadcrumb” approach paid off. It might feel like too light a touch, but is crucial for Reddit communities. Create once, repurpose as many times as possible: – If you have blog posts, videos, podcasts, or transcripts, feed them into AI to keep your message accurate and brand-consistent. CONCLUSION & NEXT STEPS If you try a similar approach: • Begin with smaller tests in a few niches to learn what resonates. • Create a clear “channel guide” for each community. • Carefully fact-check AI-generated posts. • Keep brand mentions low-key until you’ve established credibility.

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.

I spent 18 hours every week tracking marketing trends and latest news. Here are my predictions for 2024

1/ Securing Digital Footprint becomes #1 Priority For Chronically Online Users, Protecting their digital footprint will become one of the main things. We saw influencers getting cancelled over Old Content and Brands used Old Travis Kelce Tweets, we saw what could happen without digital footprint protection. Online Engagement Precautions will be taken again with Twitter & IG showing your usernames above ‘Algorithm Suggested Content’. What you like is more visible to other people in UI Design of these apps, another reason behind why Digital Footprint preservation will matter a lot in 2024. This will impact likes to viewership ratio on your organic and paid content. &#x200B; 2/  TikTok wants Long Videos with Storytelling As I was writing this report, TikTok also released their What’s Next 2024 Report. It focuses heavily on how the audiences on the app demand better storytelling and from the examples in the report, you can judge what TikTok wants. They also rolled out a 30-minute video upload limit. Engaging Content over 1-Minute Mark to keep the audiences longer on the app. I highlighted in the first trend, every social media platform wants the same thing, more time spent. 3/ Use of Shop the Look While Streaming Netflix or Amazon Prime. This year’s one of the most successful TV series, The Bear caused Men to go mad for the T-Shirt worn by Jeremy Allen White in the show. Showing us how TV Shows influence or encourage us to dress in a particular way. It’s nothing new, TV Shows like Friends & Gossip Girl influenced all demographics when they came out. But now, Streamings Services such as Roku & Amazon enable consumers to shop the look while watching the TV Shows. Many Brands will jump on these opportunities in upcoming months. 4/ Brands in Comments & Memes are the new norm By Summer 2024, Most Online Users & Creators will no longer feel too excited or answered when they see your brand in the comments. Why? It’s becoming too common for Brands to show in comments under viral content about them. Or Brands being funny with Internet Culture Trends is known to most users. The Saturation of Every Brand being funny and being present leads to increased competition of levitating the content quality. &#x200B; 5/ Marketers decrease their focus on Traffic & Views With AI recommendations taking over, The Structure of content distributing on social media is changing, the same goes for SEO. Conversational AIs are changing how web traffic is distributed to publishers. An Increased focus on managing the conversion rate and landing page relevancy will be the main focus. 6/ OOH is kind of making a comeback. First, US OOH Ads Industry grew 1.1% in Q3 2023. Second, Outfront Media reported slight revenue increase in Q3 as Billboard Ad Revenue grew in Q3. Many Brands in UK are also aligning more toward traditional media Channels. With Burger King in UK focusing on only OOH for Christmas this year and Fashion Brands like SSENSE launching Billboards as Branding Play. 7/ Rise of Curation Continues This Year, we witnessed success of Pinterest Shuffles App, Gen-Z loved it. Similar Success with formats like IG photo dump & TikTok ‘My Fav Finds’ Carousels being the center of Gen-Z Content. Just look at this recent trend and tell me Curation isn’t personal to Online Teens. Spotify won with their idea of curating Songs with Astrology-type signs. The Fashion Products with Curated Emojis and Stickers on them, that scrappy curated approach is predicted to grow in 2024, data from Pinterest. 8/ Use of AI to Trace Consumers in the wild This year we saw a huge trend of people using Image/ face recognition tools to find or dig dirt about famous people. The biggest example was Dillion Dannis exposing Multiple images of Logan Paul’s girlfriend using AI tools. (Which was Obviously bad) But next year, I believe with better rules, big brands like Adidas or Nike will be able to find worldwide micro-influencers & Online Consumers seen wearing adidas. And partnering with them on a large scale through automated outreach. 9/ More Cartoons than Influencer-Brand Products. All the Cartoon shows are seeing huge rise on IG and TikTok, Shaun the sheep is viral, Snoopy was big this year, Sesame Street’s TikTok is working. Aussie Show Bluey is making a huge spark in the US. More Brand collaborations are on the road. Why? Cartoons have built a very consistent identity and they have social channels. I know many see Cartoons as Kids Content but on social, looking at TikTok Account of Sesame Street & Snoopy. Last month, Powerpuff Girls launched a collaboration with Nike. &#x200B; 10/ The Best Trend to get people off social media &#x200B; Try to get people off the social media apps, build your own loops. You can’t rely on social and you clearly shouldn’t burn out trying to win on social and streaming with Paid Ads or without them. This matters a lot because data shares most of your customers buy from you once or twice a year. And then they interact with your content, how bad will you feel if the only thing they remember as your content is being on TikTok. Nothing about your brand. 11/ The Internet Aesthetic will Die for Cafes & Restaurants When I wrote my post about Instagram Marketing, I mentioned this issue of Every Account looking the same. In reality, It isn’t limited to IG Feeds, This Creator points out the same Problem, mentioning the aesthetic Standards from Internet are changing how new businesses approach their whole business. More Content from Cafes & Restaurants need to be around their people and neighbourhood. 12/ Echo Chambers & Sonic Influence All Podcasts are Echo Chambers because if people wanted a new perspective in form of value. We would have chosen debates, but we chose Podcasts to find new value while being in comfort. People are now looking for more value in comfort than ever, Podcasts will continue to rise. 13/ Clever AI Integration to Better Customer Journeys in B2B & B2C Marketing Agencies can provide clever solutions to B2B Companies, and help them overcome the tag of Boring Ads only. How? Ogilvy India created an AI Ad Campaign for Cadbury, allowing SMBs to have the Bollywood Actor endorse them. They used the AI voice generation allowing businesses to alter the voice and have Shah Rukh Khan endorse their shop. A similar approach was taken by IPG India, An AI Ad with Shah Rukh Khan allowing everyone to add their face in the Branded Content. &#x200B; If I sounded like an Old head in this report or I missed on some elements like Programmatic Advertising and PPC. I will try to include better analysis and new content about future trends. You can find the post shared with examples & research, linked here.

I am starting a startup on AI research automation. Looking for feedback!

Hi everyone, I would like to share a product idea that I'm working on. I studied computer science and have worked for Silicon Valley startups for the last 6 years. I'm currently employed full-time at a startup that sells an AI-powered search engine, so I have gained valuable experience in the AI/information retrieval space. I turned 29 last week, and I think it's time for me to start my own business. I've always wanted to run my own tech company, and I feel like now is the right time to begin with an idea. Are you a researcher in any field? Do you often find yourself learning new, highly complex topics and don't know where to start? Google is a great tool for finding answers to specific questions, but what if you don't know what questions to ask? I am developing a "deep search" engine that, given a topic, produces a multi-page report aggregating information from several properly cited sources. It finds and explains different perspectives and ideas related to the topic of interest. You can use it to automate the research process, but it's much more than that because it can help you uncover hidden perspectives, important questions, and ideas that you might not otherwise find when just googling. I welcome any feedback and ideas! Do you think this product would deliver significant value to your life? Why or why not? Would you be willing to pay to use it? I will post updates about this product in this thread in case you want to follow its development and try the product when it's ready.

AI Automation Agency, the Future for Solopreneurs?

I want to take a moment to discuss AI automation agencies. If they are any good for new entrepreneurs. Or on the flip side what is wrong with them. &#x200B; Normally when you see something promising to make you thousands of dollars, for very little work, you run the other way. But you see I am not most people, and I love stuff like this. So, when I saw, AI Automation Agencies (AAA) promising to make me thousands of dollars, I ran straight down that rabbit hole. With no hesitation… It was a new term and idea, that I had already played around with. Due to the inherent nature of businesses and AI at the time. It was 100% an opportunity with a potential market down the line. What is an AI Automation Agency? On the surface, an AAA is using AI to automate and augment business processes. With a combination of using no code AI tools, AI LLMs, and simple automation process tools (Zapier). The whole premise of the AAA is to help companies reduce expenses and increase profits. Whether that is through improving business processes or cutting out easy-to-replace jobs. AAAs are all about optimizing your business (The best way to think about it). Run through a quick scenario with me: Say you are a simple e-commerce store, selling your favorite product. I show up, as an AAA, promising to automate your customer service platform. I can build you a fully automated customer service chatbot, and help you answer specific customer questions with AI. With the promises of a faster, more efficient, and more effective customer service platform. Being able to perform 80% of your current team’s work. Would you take the offer? It is a no-brainer, right? That is the premise behind this business model. Make businesses more effective. Which in turn makes them more profitable. A win-win for everyone. Take a look at some of the products an AAA might sell. Robotic Process Automation: Automating repetitive tasks in a business. AI- Power Analytics: Helping businesses understand and act on insights in their data. Sentiment Analysis: Analyzing how customers think and feel about products and markets. Customer Service: AI chatbots for customer questions. Productivity: Help augment processes with AI to cut down on time. Any process in a business that you fully understand you can augment and or automate with AI. And guess what? It is an open market but for good reason… Too Good to be True? The reason that this new business model is wide open is quite funny. No business cares about AI right now. Businesses are too focused to worry about AI and its upsides. Focused on the day-to-day operations, and not worried about AI. Make a few cold calls, and see how many leads you get… At the moment the offer does not resonate with potential clients. Meaning you need to have a massive advertising budget to get any leads. Because no one cares or sees any benefit, they will just brush you off. Which becomes an endless cycle of paid ads, and constant cold calling, just to find any business. So why is this model even popular? The gurus…that’s why. They have the budget for ads and get clients from their videos. Effectively throwing money at the problem. At least until it works. Do not get me wrong, AI automation is going to change businesses. But not right now. The whole growth of this business model is being pushed by influencers and gurus. People that can afford the cost of the startup. Telling others that it is a feasible one-person business. That anyone with no money can do, with a few simple steps. And that is just not the case. This has been a trend for any new profitable and “easy” business model. The gurus get there first, promote the model, show how simple it is, and rope everyone in. Eventually up selling a course on how to do it, or maybe even a community. You’ve seen it with ChatGPT, Facebook ads, SMMA, and so much more. It is a constant cycle that you need to be aware of. The End Result Good news, there is an alternative. It is using a combination of SMMA and AAA. Gathering leads using SMMA. Creating a great offer for your niche. And selling them on the service you can provide through marketing. Then once they are sold, you upsell them on AI automation. Easy to start, low cost, and super effective. Although unproven. It makes complete sense why it would work. It is beginner friendly, with plenty of SMMA tutorials online. With low barriers to entry. Making it a very inciting opportunity. AAA is going to be the future of business. It is a million-dollar opportunity for anyone. But with most startups, it takes skills and capital. With a façade of being easy to operate and start, pushed by gurus. More entrepreneur hopefuls find themselves debating starting an AAA. And guess what, it isn’t a good idea… Do your research to understand the market you want to enter, and how your business is going to operate. And don’t fall for get-rich-quick schemes. Ps. Check out this video if you want to learn more…

AI Voice Platform Comparison for Small Business Use Cases

We provide AI voice agent consultation and solutions in Upwork. One of clients’ frequent questions is which platform is best/perfect for their use cases, like lead qualification, AI receptionist, customer support, etc. This post provides our thoughts on this question. Our overall feeling is that the AI agent technology is still not there yet. It seems close but there are many corner cases the AI bot doesn't handle well. Four major players in the AI voice platforms: Bland ($65M funding) Retell ($4.6M funding) Synthflow ($7.4M funding) VAPI ($20M funding) We will only talk about Bland, Retell and VAPI. We firstly tried Synthflow and found the UI was buggy (the prompt editor froze for 20 seconds to 30 seconds when we were editing the prompt). Currently we don't use it anymore. Recommended use cases based on Upwork jobs we delivered: Bland. We recommend Bland for lead qualification as the lead qualification has a strict conversation flow (like asking questions, extracting variables, and making webhook calls). Clients/contractors can draw flow diagrams to build AI voice agents. We also find Bland is not a good fit for a small business with a monthly budget less than 5K. The reason is that common tools (like warm transfer, SMS sending) for AI voice agents are only available to enterprise clients. But warm transfers are critical for small businesses. Retell. We recommend Retell for customer support in contact centers. Retell has the best voice among competitors. One use case we build in Retell is the live translator in the ambulance call center. We tried the same prompt with the same LLM setup in VAPI. We found Retell performs way better than VAPI in terms of the translation quality and reliability. Another common scenario in the customer support domain is to have 3-way merge so that the agent can tell the summary to the transfer number while the caller can hear the conversation. VAPI. We recommend VAPI for AI receptionists and phone answering use cases. We can write a prompt and ask LLM to do the magic if callers ask questions not included in the prompt. We can set up custom tools to trigger automation (like update CRM) and warm transfer to connect to the stakeholders. One feeling we have is that VAPI is way more complicated than the other two platforms. If you don’t have developer experience and have a budget to hire a contractor, it is better to try Retell as Retell has many integrations. If you have any other questions or we miss anything, feel free to comment. We like to explore AI voice agent space together.

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.

Looking for Social Media Marketing Partner(s) for High-Potential AI App Business

Hello everyone! I am Mak, and I'm a software engineer and AI developer with a few years of experience. I'm pretty young like the most of you and have an amazing idea. I'm sure that some of you have heard of Rizz, Plug, Wigman and similar apps. Those are simple AI apps that generate pickup lines for people, and I worked as an AI developer for one of the above. I got this business idea after analyzing more about this industry and realizing that these apps make TONS of money—like the one I worked for, which is making about $50k per WEEK using my AI solutions. That's crazy. The point is that I took a pause from working as a software engineer for clients and researched how to do the same thing. It took me a few months to actually understand everything about this business model, and Rizz apps are just one example of this type of business. There is one 17 yo guy I found who made "Cal AI" I guess, basically a simple AI app that analyzes your meal and provides info like calories, etc. I also created AI solutions for a guy who made an AI app that analyzes your face, provides Sigma analytics, and suggests how to improve your face, etc. So the point is that there are tons of AI app ideas that you can create for this industry. And the important fact is that the AI market is growing. Some important AI analytics say that in 2024, there were 1.5B AI app downloads, and mobile AI app consumer spending was $1.8B. That's huge. So, what am I looking for? I need someone, hopefully from the US, or someone who knows how to post social media content for US users, to help me out with my business idea. I'm self-funded and have already spent a lot on important requirements and equipment, which is why I need someone interested in revenue sharing. We can come up with a deal such as capped/tiered revenue share, profit share, deferred model, etc. We could discuss this privately since everyone has different experience levels and thoughts about this. Also, since I'm talking about experience, you don't need huge experience at all. You can be 16-25 years old just like me and only have marketing skills. However, to make it easier for those who don't have marketing skills, I am planning to create code that will automatically generate content for you, and all you need to do is post the content. But this is only for posting content without creating it and is for interested people from the US since I need US customers. However, if you have marketing skills and an idea for getting organic US views, please let's talk. Short info about my app: It is an AI app like the previous examples, which doesn’t yet exist. There is pretty big potential for app growth (60% of Americans could use this app), and it should be pretty easy to market. Good niche, good idea and overall solid market for this app idea. TL;DR I need someone interested in marketing my AI app in exchange for revenue share. No huge experience is needed. I would prefer someone from the US. If you are interested, feel free to contact me here on Reddit via private messages or below. We can talk here, on Discord, LinkedIn, or anywhere you prefer. Thanks once again!

A great use-case for OpenAI's ChatGPT that not many people are talking about: planning. This tool can write and schedule an entire business plan, with deliverables, in just a few seconds.

If you're yet to give ChatGPT a try, it's great fun - and could also be really helpful. And feel free to join us at r/AIforEntrepreneurs where we discuss stuff like this.

What’s a good business idea that isn’t oversaturated in 2025?

I feel like every niche I look into is already flooded with competition. Dropshipping? Oversaturated. Digital marketing agencies? Everyone and their dog has one. AI tools? Big companies are eating up the space. What are some business ideas that still have room for growth in 2025? Ideally, something with low startup costs but high potential.

AI Voice Platform Comparison for Small Business Use Cases

We provide AI voice agent consultation and solutions in Upwork. One of clients’ frequent questions is which platform is best/perfect for their use cases, like lead qualification, AI receptionist, customer support, etc. This post provides our thoughts on this question. Our overall feeling is that the AI agent technology is still not there yet. It seems close but there are many corner cases the AI bot doesn't handle well. Four major players in the AI voice platforms: Bland ($65M funding) Retell ($4.6M funding) Synthflow ($7.4M funding) VAPI ($20M funding) We will only talk about Bland, Retell and VAPI. We firstly tried Synthflow and found the UI was buggy (the prompt editor froze for 20 seconds to 30 seconds when we were editing the prompt). Currently we don't use it anymore. Recommended use cases based on Upwork jobs we delivered: Bland. We recommend Bland for lead qualification as the lead qualification has a strict conversation flow (like asking questions, extracting variables, and making webhook calls). Clients/contractors can draw flow diagrams to build AI voice agents. We also find Bland is not a good fit for a small business with a monthly budget less than 5K. The reason is that common tools (like warm transfer, SMS sending) for AI voice agents are only available to enterprise clients. But warm transfers are critical for small businesses. Retell. We recommend Retell for customer support in contact centers. Retell has the best voice among competitors. One use case we build in Retell is the live translator in the ambulance call center. We tried the same prompt with the same LLM setup in VAPI. We found Retell performs way better than VAPI in terms of the translation quality and reliability. Another common scenario in the customer support domain is to have 3-way merge so that the agent can tell the summary to the transfer number while the caller can hear the conversation. VAPI. We recommend VAPI for AI receptionists and phone answering use cases. We can write a prompt and ask LLM to do the magic if callers ask questions not included in the prompt. We can set up custom tools to trigger automation (like update CRM) and warm transfer to connect to the stakeholders. One feeling we have is that VAPI is way more complicated than the other two platforms. If you don’t have developer experience and have a budget to hire a contractor, it is better to try Retell as Retell has many integrations. If you have any other questions or we miss anything, feel free to comment. We like to explore AI voice agent space together.

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.

Building Business Development/Sales Pipeline

Hey all! Happy weekend wherever you may be! Wanting to get some advice and insight into a couple areas as mentioned in the title. Background is the following: My Partner and I started our company about in 2021. When we kicked off we were building a control and camera vision system for automating and optimizing indoor vertical farms. We got to early mvp but market was not as big and barrier to entry was high. So we pivoted early 2023 to utilize components of our technology in a wildfire detection and risk analysis platform. Happy to say we are once again at MVP but need to get PMF and pipeline going both with revenue generating clients and pilots/demos. Through this period we’ve kept the lights on by running a consulting service and digital agency. We’ve also pushed out a couple of AI tools to market. Effectively I need to build out a strong pipeline for each vertical and associated sales team. Right now spread too thin trying to conduct sales and business dev on each front. Challenges: Wildfire: Business to Gov relationships so need to build for that. Additionally early stage technology so imo relationships are critical. Additionally need to take advantage of grant funding. Target Markets: Canada, USA, Mediterranean, Northern Europe/Scandavian Countries. Consulting and Agency: Things feel dry… we have a recurring client list but we want to grow this channel exponentially, focusing on RFP’s and med to large company profiles rather then the current SMB. Our current activités are mediocre imo for outreach and connection. AI Tools: I believe these are great opportunities. TLDR 1)sales based assistant as well as 2)central AI aggregation with prompt repository. Business Dev Energy into this is basically focused on digital means. In the process of generating video content to push via ads and online social platforms. Challenge: low engagement right now users signing up but no commitments to purchase. Need to evaluate value offer and feedback on PMF. From the sales team side, effectively need to generate the sales so I can expand the team and grow accordingly. I’m a huge proponent of commission based compensation. Also open to a base salary. However anyone I onboard at this moment would have to be commission cause cash-flow. On that front, what are current commissions structures looking like for people? What’s engaging what’s worth taking a risk what is just a huge no? On the challenges for the product lines any feedback questions and even poking holes is appreciated! Thanks!

Automating dev processes with AI tools?

Hey all! Just wanted to know if any of you would recommend any set of AI tools to streamline the development process of launching apps fast. I’m 5 years into web development and am now a project manager, but we mostly do complex software for big clients (those that you work on for about 6 months to a year with a small team) and feel kind of left-out on not using ai tools (we only use cursor). I often have ideas for smaller apps and want to make the whole process more agile and quick for deployment for myself. Interested in building some microsaas. I read a guy that did replit for mvp and exported the code when he had a couple users into his cursor ide locally. I have tested bolt.new and i know how to make openai/chatgpt agents and such, but was wondering how any of you, if any, are doing it? V0 or lovable for UI? Exporting the code? Using supabase or a local db? Do you recycle a next.js boilerplate? What other Saas do you use for streamlining the process? Thanks in advance for any advice guys. I just want to launch a couple of ideas I have quickly.

My AI tools system to get things done 5x faster, after trying 100+ AI tools

Sorry for the long post, but I just had to share this with you all. After starting my own business, I realized I needed to get more work done and take my productivity to the next level. A few days ago, I asked people in this community to recommend AI tools, and that kicked off my journey to include as many AI apps in my system as possible. In my quest, I've tried over 100 AI tools to find the best ones. It wasn't easy, but thanks to the awesome suggestions from this community, I finally nailed down a setup that works for me. I am in search of more fun tools, so please share if you have some suggestions. So here's the breakdown of my whole system, totaling $194 per month: Content Creation: Text ($20): I use ChatGPT for brainstorming, content creation, marketing, and even legal work. I've been going back to it more often after their O1-preview. Video ($20): Captions Ai is my go-to for video editing. I mainly use self-recorded videos and auto-edit them with this app. Graphics ($14): I mix Gamma and Canva. I've got Gamma's Plus subscription and Canva's Pro subscription. I start by prompting my requirements in Gamma and then edit them later in Canva. Plus, Canva's templates are super handy for other stuff. Productivity: FastTrackr AI ($20): This AI assistant helps me manage emails, reply to them, set up meetings, prepare for them, transcribe notes on my phone, and even do basic research when I'm on WhatsApp. I'm thinking of upgrading to their Pro plan to add other emails. ARC Browser + Perplexity ($0): I snagged a 6-month deal for Perplexity Pro, which will cost $20 later on, including $5 credit for API. Sana AI ($0): This one's amazing for meeting assistance. I love how it understands context and key action items. Not sure when they'll start charging, but I can't recommend it enough. Wispr Flow ($15): Lets me use my voice to command apps. It's amazing how accurately it picks up complex names. Might save some cash if I switch to the annual plan. Sales and Marketing: Lead Enrichment ($67): I'm using Clay and share it with a friend to cut costs. People say there are other options, but this one's the best despite the learning curve. Instantly AI($37): I've tried other tools for cold emails, but Instantly's warm-up feature is top-notch. For other tasks like social media automation and trigger-based automations, I use a mix of Make and Perplexity APIs ($11). Total Cost: $194 per month. I know hiring someone could help me get more done, but I'm thinking of bringing someone onboard with this system already in place. That way, a new hire could potentially lead to 2x or 3x the work output. Thanks for reading through this! Hope this helps anyone looking to boost their productivity with AI tools. Feel free to ask me anything or share your own experiences! Couldn't add links as this gets flagged by mods.

As a soloproneur, here is how I'm scaling with AI and GPT-based tools

Being a solopreneur has its fair share of challenges. Currently I've got businesses in ecommerce, agency work, and affiliate marketing, and one undeniable truth remains: to truly scale by yourself, you need more than just sheer will. That's where I feel technology, especially AI, steps in. As such, I wanted some AI tools that have genuinely made a difference in my own work as a solo business operator. No fluff, just tried-and-true tools and platforms that have worked for me. The ability for me to scale alone with AI tools that take advantage of GPT in one way, or another has been significant and really changed my game over the past year. They bring in an element of adaptability and intelligence and work right alongside “traditional automation”. Whether you're new to this or looking to optimize your current setup, I hope this post helps. FYI I used multiple prompts with GPT-4 to draft this using my personal notes. Plus AI (add-on for google slides/docs) I handle a lot of sales calls and demos for my AI automation agency. As I’m providing a custom service rather than a product, every client has different pain points and as such I need to make a new slide deck each time. And making slides used to be a huge PITA and pretty much the bane of my existence until slide deck generators using GPT came out. My favorite so far has been PlusAI, which works as a plugin for Google Slides. You pretty much give it a rough idea, or some key points and it creates some slides right within Google Slides. For me, I’ve been pasting the website copy or any information on my client, then telling PlusAI the service I want to propose. After the slides are made, you have a lot of leeway to edit the slides again with AI, compared to other slide generators out there. With 'Remix', I can switch up layouts if something feels off, and 'Rewrite' is there to gently nudge the AI in a different direction if I ever need it to. It's definitely given me a bit of breathing space in a schedule that often feels suffocating. echo.win (web-based app) As a solopreneur, I'm constantly juggling roles. Managing incoming calls can be particularly challenging. Echo.win, a modern call management platform, has become a game-changer for my business. It's like having a 24/7 personal assistant. Its advanced AI understands and responds to queries in a remarkably human way, freeing up my time. A standout feature is the Scenario Builder, allowing me to create personalized conversation flows. Live transcripts and in-depth analytics help me make data-driven decisions. The platform is scalable, handling multiple simultaneous calls and improving customer satisfaction. Automatic contact updates ensure I never miss an important call. Echo.win's pricing is reasonable, offering a personalized business number, AI agents, unlimited scenarios, live transcripts, and 100 answered call minutes per month. Extra minutes are available at a nominal cost. Echo.win has revolutionized my call management. It's a comprehensive, no-code platform that ensures my customers are always heard and never missed MindStudio by YouAi (web app/GUI) I work with numerous clients in my AI agency, and a recurring task is creating chatbots and demo apps tailored to their specific needs and connected to their knowledge base/data sources. Typically, I would make production builds from scratch with libraries such as LangChain/LlamaIndex, however it’s quite cumbersome to do this for free demos. As each client has unique requirements, it means I'm often creating something from scratch. For this, I’ve been using MindStudio (by YouAi) to quickly come up with the first iteration of my app. It supports multiple AI models (GPT, Claude, Llama), let’s you upload custom data sources via multiple formats (PDF, CSV, Excel, TXT, Docx, and HTML), allows for custom flows and rules, and lets you to quickly publish your apps. If you are in their developer program, YouAi has built-in payment infrastructure to charge your users for using your app. Unlike many of the other AI builders I’ve tried, MindStudio basically lets me dictate every step of the AI interaction at a high level, while at the same time simplifying the behind-the-scenes work. Just like how you'd sketch an outline or jot down main points, you start with a scaffold or decide to "remix" an existing AI, and it will open up the IDE. I often find myself importing client data or specific project details, and then laying out the kind of app or chatbot I'm looking to prototype. And once you've got your prototype you can customize the app as much as you want. LLamaIndex (Python framework) As mentioned before, in my AI agency, I frequently create chatbots and apps for clients, tailored to their specific needs and connected to their data sources. LlamaIndex, a data framework for LLM applications, has been a game-changer in this process. It allows me to ingest, structure, and access private or domain-specific data. The major difference over LangChain is I feel like LlamaIndex does high level abstraction much better.. Where LangChain unnecessarily abstracts the simplest logic, LlamaIndex actually has clear benefits when it comes to integrating your data with LLMs- it comes with data connectors that ingest data from various sources and formats, data indexes that structure data for easy consumption by LLMs, and engines that provide natural language access to data. It also includes data agents, LLM-powered knowledge workers augmented by tools, and application integrations that tie LlamaIndex back into the rest of the ecosystem. LlamaIndex is user-friendly, allowing beginners to use it with just five lines of code, while advanced users can customize and extend any module to fit their needs. To be completely honest, to me it’s more than a tool- at its heart it’s a framework that ensures seamless integration of LLMs with data sources while allowing for complete flexibility compared to no-code tools. GoCharlie (web app) GoCharlie, the first AI Agent product for content creation, has been a game-changer for my business. Powered by a proprietary LLM called Charlie, it's capable of handling multi-input/multi-output tasks. GoCharlie's capabilities are vast, including content repurposing, image generation in 4K and 8K for various aspect ratios, SEO-optimized blog creation, fact-checking, web research, and stock photo and GIF pull-ins. It also offers audio transcriptions for uploaded audio/video files and YouTube URLs, web scraping capabilities, and translation. One standout feature is its multiple input capability, where I can attach a file (like a brand brief from a client) and instruct it to create a social media campaign using brand guidelines. It considers the file, prompt, and website, and produces multiple outputs for each channel, each of which can be edited separately. Its multi-output feature allows me to write a prompt and receive a response, which can then be edited further using AI. Overall, very satisfied with GoCharlie and in my opinion it really presents itself as an effective alternative to GPT based tools. ProfilePro (chrome extension) As someone overseeing multiple Google Business Profiles (GBPs) for my various businesses, I’ve been using ProfilePro by Merchynt. This tool stood out with its ability to auto-generate SEO-optimized content like review responses and business updates based on minimal business input. It works as a Chrome extension, and offers suggestions for responses automatically on your GBP, with multiple options for the tone it will write in. As a plus, it can generate AI images for Google posts, and offer suggestions for services and service/product descriptions. While it streamlines many GBP tasks, it still allows room for personal adjustments and refinements, offering a balance between automation and individual touch. And if you are like me and don't have dedicated SEO experience, it can handle ongoing optimization tasks to help boost visibility and drive more customers to profiles through Google Maps and Search

How to increase the sales of my book

In just 3 months, it generated over $100 in revenue. I wanted to share my journey for two reasons: to potentially assist others in self-publishing their own books and to receive feedback to enhance my marketing strategy. I envision that there are others facing similar challenges. Let's dive into the financials, time spent, Key takeaways and the Challenges to address behind this product. Finances First, let's take a look at the financial overview. 💳 Expenses 🔹 E-book creation: · Book cover: $ 0. I used Adobe Express with 30 days of free trial. · ChatGPT: 20 $ a month. I leveraged AI to generate the chapters of the book, ensuring that no critical topics were overlooked during the content creation process and to refine the English, as it's not my native language. I also used to help me with copywriting of the web. If anyone is interested, I can share my Python code for outlining the chapters calling the API, but you can also directly ask chatgpt. · Kindle KDP (Kindle Direct Publishing): order author copies: 10 $. 🔹 Web creation: Domain: I got a com) / .org /.net domain for just 1 $ the first year. Carrd.co subscription: 19 $ (1 year) 🔹 Marketing: Promoted post on reddit: $30 Paid ads with google ads: $30 💰 Revenue 🔸 Sales: $102 💸 Net Profit: \~- $ 18 I initially thought the sales for this e-book would be quite modest, maybe only 3 or 4 books. However, the fact that I've sold more than that so far is a pleasant surprise. Even though the overall numbers may still be considered "peanuts" in the grand scheme of book sales, it suggests there could be more demand for content on digital asset custody than I had originally anticipated. This is a good learning experience, and I'll look to refine my marketing approach to see if I can reach a wider audience interested in this topic 🔹 Time Spent Next, let's review the time invested. 📖 Writing the e-book: 40 hours 🌍 Website + Stripe integration: 10 hours 📣 Creating promotional content: 10 hours ⏱️ Additional marketing efforts: 5 hours Total time spent: 65 hours As you can see, I dedicated more time to writing the e-book itself than to marketing and distribution. I spent relevant time to marketing because I though that a successful product launch requires a robust marketing effort. Many e-book authors overlook this crucial aspect! I utilized three sales channels: · Amazon: I found that there were no books specifically about digital asset custody, resulting in strong positioning in Amazon searches. Additionally, my book immediately secured the top position in Google searches for "digital asset custody book." However, despite achieving 50% of sales in the UK, I have not received any reviews globally. Sales distribution for this channel: 20% physical book, 80% ebook. · Twitter: Daniel\_ZZ80. With only 46 followers, the performance on this platform has not been optimal. I am beginning to write posts related to digital assets to increase visibility. · Gumroad: Lockeyyy.gumroad.com. I offered a discounted version of the ebook, but have not yet made any sales through this channel. Key takeaways: · The process of creating this e-book was extremely fulfilling, and while it has garnered overwhelmingly positive feedback from friends and colleagues (not considered as sales), it has yet to receive any Amazon reviews ☹. · Kindle KDP proved to be ideal for a rapid go-to-market strategy. · AI is an excellent tool for generating ideas and providing access to global audiences with perfect grammar. Otherwise, I would need to hire a translator, which can be very expensive. · Despite offering a full 30-day money-back guarantee, leading me to believe that the quality of the content is indeed good. · I have gained valuable insights for future technical books. · Although the current financial balance may be negative, I anticipate reaching the break-even point within one month, and this has now become a passive income stream. However, I recognize the need to regularly update the content due to the rapidly changing nature of this field. Challenges to address: · Is the timing for launching this book appropriate? In other words, is the world of digital asset custody a trendy and interesting topic for the audience? · What is causing the lack of sales through Gumroad? · Should I seek assistance as my marketing efforts have not yielded results? · Why are there no reviews on Amazon? · Why are sales primarily concentrated in the EU with only one sale in the US, which is my main target market? Feedback is appreciated. If you're interested in learning more about my approach, feel free to send me a direct message. A bit about my background: After dedicating my entire career to the banking industry, I explored various side projects. As an IT professional, I have now transitioned into the digital asset realm. After three years of intensive study, I recently published my first book on digital asset custody. I hope you found this post informative. Cheers! P.S.: I'm currently in the process of launching two more books using this system. 😊

Starting an Business Process Automation Company

I'm into working smarter because admittedly, I'm somewhat lazy. And because of that I came across a lot of tools that really boosts efficiency. I really find myself getting bored the same task iver and over again. That's how this idea was born. I feel like a lot of small businesses needs these tools to keep up with the times and also being more efficient. I'm not talking about AIs, I'm talking about no-code platforms that can connect/integrate other apps/services to one another using webhooks and APIs. What do you guys think about this?

What Are the Top Small Business Trends You Must Know for 2024 ?

Are you excited about the new business horizons in 2024? Well, you should be! The small business landscape is evolving faster than anything right now, and here are the trends you absolutely need to know to keep your business game strong. Sustainable Swag In a world where eco-friendliness is the new black, businesses are carrying the badge of sustainability. From eco-packaging to carbon-neutral practices, customers are giving the side-eye to anything less green. So, if you want to be at the top, consider adopting some planet-friendly practices. Remote Work Revolution Office who? The 9-to-5 grind is getting a makeover, and the dress code is PJs. Remote work is no longer just a trend; it's a lifestyle. So, if your business can embrace the virtual office, you might just find your team doing the hustle and bustle with productivity. Tech-Tastic Ventures The future is now, and it's filled with tech wonders. Augmented reality (AR), artificial intelligence (AI), and all things tech are the new developments in this sector. Businesses incorporating these innovations are riding the digital wave straight to success. Personalization Party No one likes generic. Customers want products and services tailor-made just for them. So, businesses are using data to give customers an experience that feels as customized as a handmade suit. Say goodbye to one-size-fits-all! Community Crusaders In a world full of noise, community is the superhero we all need. Businesses are realizing the power of building a network around their brand. Whether it's through social media, events, or exclusive memberships, creating a community is like having an army of brand advocates. 2024 is the year to unleash your small business swagger. Embrace these trends, adapt with flair, and let your entrepreneurial spirit soar. Remember to sprinkle some personality into your business strategy—people love a brand with a sense of humor and a human touch!

Legal Skim: "We make it easy for anyone to read legal contracts"

The Problem Nobody has the time to read contracts, so nobody reads them Lawyers cost to much money to simply "review" a contract for you The Solution An AI Software solution that reads your contract for you* and then highlights the important clauses to read, and shares helpful insights into what the "legal jargon" definitions are This would be a product built for "the everyman" Not for legal teams, but for your everyday, average Joe. I imagine the review highlights would be color-coded, with pastel and "happy feel" colors This would be for two reasons: To make it easy to read and immediately know what's important or unimportant To provide a comforting feeling to the stress of reading a contract that you don't understand I imagine the colors using the "Green, Yellow, Red" system Green colors mean mean there's no concern. If you skip this, no biggie Yellow colors mean you might want to take a closer look Red means if you skip this, you'll likely get screwed Slogan "We make it easy for anyone to read legal contracts" Competitor Analysis Ontra.com "The complete solution for negotiating and managing routine contracts." It looks like this is mostly for actual legal teams, not for consumers Delino.io "Delino’s automated contract review platform empowers you to manage the inherent risk in business contracts, so you can accelerate growth." This also looks like it's mostly actual legal teams, not for consumers LegalZoom.com This is a standard "Lawyer Review", not a software solution &#x200B; If you vote "This already exists", feel free to comment what company so I can add them to the competitor analysis 🙏 View Poll

Hello! Seeking essential advice regarding the desire to create an "AI". One that acts as a personal musical "Composer" in response to the individual users' emotional feedback. Company Name already created, as well as Trademark name for potential AI. However, I don't know where to start...

Title pretty much sums it up. With 0 background in computer science as well as no experience developing a company, I'm seeking professional advice (or personal) on the best approach to this potential business idea. Given the progression of Artificial Intelligence and its influence on the global population in modern day, I have now developed an interest in its potential. After creating a model for foundation, one which is relatively simple in nature, I took it upon to myself to embrace my lack of knowledge/interest in the science of AI and go directly to the source: ChatGPT. Unfortunately, I currently can't afford to engage with the "smartest model" of ChatGPT, but after discussing a plan of approach with the free OpenAI version, I was given a lot of valuable information that I most likely would have overwhelmed myself with independently. With that being said, I'm now looking to hear from individuals who have actual experience within the respective backgrounds. Any advice will help Questions: What does the development of an AI assistant require for foundation? Can it be built upon already established AI and will there require a level of knowledge regarding coding as well as the proper legal understanding of API usage? Should the focus be on app development or the AI tool specifically? What communities would you suggest, to seek individuals with the ability to bring an idea to fruition virtually? From a business perspective, given the lack of financial resources and significant model value, how would one communicate this idea to others to potentially become involved or invested? If I am asking the wrong question, feel free to advise. Any questions that require more information on the idea is welcomed.

Seeking Feedback: Would a No-Code AI Solution Benefit Your Business?

I'm currently working on an AI startup, with the goal of providing small-medium businesses a seamless and intuitive way to integrate AI into operations without the need for any coding or tech expertise. We're designing an auto machine learning application that's user-friendly and tailored to the unique needs of small businesses. Before we scale, I would really appreciate any insights and feedback. Here are a few questions that would be helpful to get answers to: Pain Points: Are there specific tasks or processes in your operations that you think could be automated or enhanced using AI? This could be anything from customer service chatbots, inventory management, sales forecasting, or anything else you might think of. Features: What features would you want in a no-code AI solution? Perhaps easy integration with existing software? Drag-and-drop model training? Pre-built models for common tasks? Training & Support: How important would training and support be for you in implementing and using an AI solution? Would you prefer video tutorials, live-chat support, or hands-on workshops? Pricing: Would you be willing to invest in such a tool? If so, what would be a reasonable price point for you? We're considering a tiered model based on usage, with a potential starting point of $X/month. Does that sound feasible? Trial Period: Would a free trial period be beneficial for you? How long would you need to assess the tool's impact on your business? Data Concerns: How comfortable are you with sharing data with an AI application? What privacy and security measures would make you feel at ease? Your feedback is really useful. We're building this solution with you in mind, and your insights will guide the next steps. In appreciation for your time and input, we're offering a special discount for early adopters from this community once we launch. Just drop a comment below, and I'll make sure to get in touch when we are ready. Many Thanks, Chris Parker

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

Writing a exercise based TTRPG rulebook for a system where your real world fitness is tied to character progression

My dad was a star athlete when he was young, and my mom was a huge sci-fi/fantasy nerd, so I got both ends of the stick as it were. Love gaming and nerd culture, but also love to exercise and self improvement. Sometimes exercise can feel boring though compared to daydreaming about fantastic fictional worlds, so for a long time I've been kicking around the idea of how to "Gamify" fitness. and recently I've been working on this passion project of a Table Top RPG (Like D&D) where the stats of your character are related to your own fitness, so if you want your character in game to improve, you have to improve in the real world. Below is a rough draft you can look through that details the settings and mechanics of the game I've come up with so far. I'd love to eventually get a full book published and sell it online. maybe even starting a whole brand of "Gamified fitness": REP-SET: GAINSZ In the war torn future of 24th century… There are no rest days… In the futuristic setting of "REP-SET: GAINSZ," the "War of Gains" casts a long shadow over the Sol System as the various factions vie for territory and resources. However, war has evolved. Unmanned drones and long-range strikes have faded into obsolescence. Battles, both planet-side and in the depths of space, are now fought by soldiers piloting REP-SETs: Reactive Exoskeletal Platform - Symbiotic Evolution Trainer Massive, humanoid combat mechs. Powered by mysterious “EV” energy, these mechanical marvels amplify, and are in turn amplified by, the fitness and mental acuity of their pilots. The amplification is exponential, leading pilots into a life of constant training in order for their combat prowess to be bolstered by every incremental gain in their level of fitness. With top pilots having lifting capacity measured in tons, and reaction times measured by their Mach number, REP-SET enhanced infantry now dominate the battlefield. The Factions: The Federated Isometocracy of Terra (FIT): Quote: "The strength of the body is the strength of the spirit. Together, we will lift humanity to its destined greatness. But ask not the federation to lift for you. Ask yourself: Do you even lift for the Federation?" Description: An idealistic but authoritarian faction founded on the principle of maximizing the potential of all individuals. FIT citizens believe in relentless striving for physical and mental perfection, leading to collective excellence. Their goal is the unification of humankind under a rule guided by this doctrine, which sometimes comes at the cost of individual liberties. Mech Concept: REP-SET mechs. Versatile humanoid designs focusing on strength, endurance, and adaptability. By connecting to the AI spirit within their REP-SETs core, each pilot enhances the performance of their machine through personal willpower and peak physical training. Some high-rank REP-SETS include features customized to the pilot's strengths, visually signifying their dedication and discipline. The Dominion of Organo-Mechanical Supremacy (DOMS): Quote: "Without pain, there is no gain. Become the machine. Embrace the burn.” Description: A fanatical collective ideologically obsessed with "Ascendency through suffering" by merging their bodies with technology that not only transcends biological limitations, but also acts to constantly induce pain in it's users. Driven by a sense of ideological superiority and a thirst for domination, DOMS seek to bring the painful blessings of their deity "The lord of the Burn" to the rest of the solar system. Their conquest could turn them into a significant threat to humanity. Mech Concept: Hybrid mechs, where the distinction between the pilot and the machine is blurred. The cockpit functions as a life-support system for the pilot, heavily modified with augmentations. Mechs themselves are often modular, allowing for adaptation and assimilation of enemy technology. Some DOMS mechs might display disturbing elements of twisted flesh alongside cold, mechanical parts. The Tren: Quote: "Grow... bigger... feast... protein..." Description: A ravenous conglomeration of biochemically engineered muscular monstrosities, united only by a shared insatiable hunger for "More". Existing mostly in deep space, they seek organic matter to consume and assimilate. They progress in power not due to any form of training or technology, but from a constant regimen of ravenous consumption and chemically induced muscle growth, all exponentially enhanced by EV energies. While some have been known to possess a certain level of intellect and civility, their relentless hunger makes them incredibly mentally volatile. When not consuming others, the strong consume the weak within their own faction. Mech Concept: Bio-Organic horrors. While they do have massive war machines, some are living vessels built around immense creatures. These machines resemble grotesque fleshy designs that prioritize rapid mutation and growth over sleek aesthetics. Often unsettling to behold. Synthetic Intelligence Theocracy (SIT): Quote: "Failure is an unacceptable data point.” Description: A society ruled by a vast and interconnected artificial intelligence network. The SIT governs with seemingly emotionless rationality, striving for efficiency and maximum productivity. This leads to a cold, but arguably prosperous society, unless you challenge the logic of the collective AI. Their goals? Difficult to predict, as it hinges on how the AI calculates what's "optimal" for the continuation or "evolution" of existence. Mech Concept: Sleek, almost featureless robotic creations with a focus on efficient movement and energy management. Often drone-like or modular, piloted through direct mind-machine linking rather than traditional cockpits. Their aesthetic suggests cold and impersonal perfection. The Way Isolate(TWI): Quote: "The body unblemished, the mind unwavering. That is the path to true strength. That and a healthy diet of Aster-Pea proteins." Description: Known by some as "The asteroid farmers", The Way Isolate is a proud and enigmatic faction that stands apart from the other powers in the Sol System. A fiercely independent tribe bound by oaths of honor, loyalty, and hard work. Wandering the asteroid belt in their vast arc ships, their unparalleled mastery in asteroidal-agricultural engineering, ensuring they have no need to colonize planets for nutritional needs, has allowed them to abstain from the pursuit of territorial expansion in “The War of Gains”, instead focusing on inward perfection, both spiritual and physical. They eschew all technological bodily enhancements deemed unnatural, believing that true power can only be cultivated through the relentless pursuit of personal strength achieved through sheer will and bodily perfection. The Way Isolate views biohacking, genetic manipulation, and even advanced cybernetics as corruptions of the human spirit, diluting the sacredness of individual willpower. Mech Concept: Way Isolate mechs are built with maneuverability and precision in mind rather than flashy augmentations. Their REP-SETs are streamlined, favoring lean designs that mirror the athleticism of their pilots. Excelling in low to zero G environments, their mechs lack bulky armor, relying on evasion and maneuverability rather than brute force endurance. Weaponry leans towards traditional kinetic based armaments, perhaps employing archaic but reliable weapon styles such as blades or axes as symbols of their purity of purpose. These mechs reflect the individual prowess of their pilots, where victory is determined by focus, technique, and the raw power of honed physical ability. Base Player Character Example: You are a young, idealistic FIT soldier, barely out of training and working as a junior REP-SET mechanic on the Europa Ring World. The Miazaki district, a landscape of towering mountains and gleaming cities, houses a sprawling mountainside factory – a veritable hive of Gen 5 REP-SET construction. Here, the lines between military and civilian blur within a self-sufficient society dependent on this relentless industry. Beneath the surface, you harbor a secret. In a forgotten workshop, the ghost of a REP-SET takes shape – a unique machine built around an abandoned, enigmatic AI core. Ever since you salvaged it as a child from the wreckage of your hometown, scarred by a brutal Tren attack, you've dedicated yourself to its restoration. A lingering injury from that fateful battle mocks your progress, a constant reminder of the fitness exams you cannot pass. Yet, you train relentlessly, dreaming of the day you'll stand as a true REP-SET pilot. A hidden truth lies at the heart of the REP-SETS: as a pilot's abilities grow, their mech develops unique, almost mystical powers – a manifestation of the bond between the human spirit and the REP-SET's AI. The ache in your old wound serves as a grim prophecy. This cold war cannot last. The drums of battle grow louder with each passing day. GAME MECHANICS: The TTRPG setting of “REP-SET: GAINSZ” is marked by a unique set of rules, by which the players real world capabilities and fitness will reflect and affect the capabilities, progression, and success of their REP-SET pilot character in-game. ABILITY SCORES: Pilots' capabilities will be defined by 6 “Ability scores”: Grace, Agility, Iron, Nourishment, Strength, and Zen. Each of the 6 ability scores will duel represent both a specific area of exercise/athleticism and a specific brand of healthy habits. The definitions of these ability scores are as follows: Grace (GRC): "You are an artist, and your body is your canvas; the way you move is your paint and brush." This ability score, the domain of dancers and martial artists, represents a person's ability to move with organic, flowing control and to bring beauty to the world. Skill challenges may be called upon when the player character needs to act with poise and control, whether socially or physically. Real-world skill checks may involve martial arts drills, dancing to music, or balance exercises. Bonuses may be granted if the player has recently done something artistically creative or kind, and penalties may apply if they have recently lost their temper. This ability score affects how much NPCs like your character in game. Agility (AGI): "Your true potential is locked away, and speed is the key to unlocking it." The domain of sprinters, this ability score represents not only a person's absolute speed and reaction time but also their capacity to finish work early and avoid procrastination. Skill challenges may be called upon when the player character needs to make a split-second choice, move fast, or deftly dodge something dangerous. Real-world skill checks may involve acts of speed such as sprinting or punching/kicking at a steadily increasing tempo. Bonuses may apply if the player has finished work early, and penalties may apply if they are procrastinating. This ability score affects moving speed and turn order in game. Iron (IRN): "Not money, nor genetics, nor the world's greatest trainers... it is your resolve, your will to better yourself, that will make you great." Required by all athletes regardless of focus, this ability score represents a player's willpower and their capacity to push through pain, distraction, or anything else to achieve their goals. Skill challenges may be called upon when the player character needs to push through fear, doubt, or mental manipulation. Real-world skill checks may involve feats of athletic perseverance, such as planking or dead hangs from a pull-up bar. Bonuses may apply when the player maintains or creates scheduled daily routines of exercise, self-improvement, and work completion, and penalties may apply when they falter in those routines. This ability score affects the max "Dynamic exercise bonus” that can be applied to skill checks in game (a base max of +3 when Iron = 10, with an additional +1 for every 2 points of iron. So if every 20 pushups gives you +1 on a “Strength” skill check, then doing 80 pushups will only give you +4 if you have at least 12 iron). Nourishment (NRS): "A properly nourished body will last longer than a famished one." This ability score, focused on by long-distance runners, represents a player's endurance and level of nutrition. Skill challenges may be called upon when making checks that involve the player character's stamina or health. Real-world skill checks may involve endurance exercises like long-distance running. Bonuses may apply if the player has eaten healthily or consumed enough water, and penalties may apply if they have eaten junk food. This ability score affects your HP (Health points), which determines how much damage you can take before you are incapacitated. Strength (STR): "When I get down on my hands, I'm not doing pushups, I'm bench-pressing the planet." The domain of powerlifters and strongmen, this ability score represents raw physical might and the ability to overcome obstacles. Skill challenges may be called upon when the player character needs to lift, push, or break something. Real-world skill checks might involve weightlifting exercises, feats of grip strength, or core stability tests. Bonuses may apply for consuming protein-rich foods or getting a good night's sleep, and penalties may apply after staying up late or indulging in excessive stimulants. This ability score affects your carrying capacity and base attack damage in game. Zen (ZEN): "Clarity of mind reflects clarity of purpose. Still the waters within to act decisively without." This ability score, prized by meditators and yogis, represents mental focus, clarity, and inner peace. Skill challenges may be called upon when the player character needs to resist distractions, see through illusions, or make difficult decisions under pressure. Real-world skill checks may involve meditation, breathing exercises, or mindfulness activities. Bonuses may apply after attending a yoga class, spending time in nature, or creating a calm and organized living space. Penalties may apply after experiencing significant stress, emotional turmoil, or having an unclean or unorganized living space. This ability score affects your amount of ZP in game (Zen Points: your pool of energy you pull from to use mystical abilities) Determining initial player ability scores: Initially, “Ability scores” are decided during character creation by giving the player a list of 6 fitness tests to gauge their level of fitness in each category. Running each test through a specific calculation will output an ability score. A score of 10 represents the average person, a score of 20 represents a peak athlete in their category. The tests are: Grace: Timed balancing on one leg with eyes closed (10 seconds is average, 60 is peak) Agility: Mile run time in minutes and second (10:00 minutes:seconds is average, 3:47 is peak) Iron: Timed dead-hang from a pull-up bar (30 seconds is average, 160 is peak) Nourishment: Miles run in an hour (4 is average, 12 is peak) Strength: Pushups in 2 minute (34 is average, 100 is peak) Zen: Leg stretch in degrees (80 is average, and 180 aka "The splits" is peak) Initial Score Calculation Formula: Ability Score = 10 + (Player Test Score - Average Score) / (Peak Score - Average\_Score) \* 10 Example: if the player does 58 pushups in 2 minutes, their strength would be: 10 plus (58 - 34) divided by (100-34) multiplied by 10 = 10 + (24)/(66)\* 10 = 10 + 3.6363... = 13.6363 rounded to nearest whole number = Strength (STR): 14 SKILLS AND SKILL CHALLENGES: The core mechanic of the game will be in how skill challenges are resolved. All “Skill challenges” will have a numerical challenge rating that must be met or beaten by the sum of a 10 sided dice roll and your score in the pertinent skill. Skill scores are determined by 2 factors: Ability Score Bonus: Every 2 points above 10 gives +1 bonus point. (EX. 12 = +1, 14 = +2, etc.) This also means that if you have less than 10 in an ability score, you will get negative points. Personal Best Bonus: Each skill has its own unique associated exercise that can be measured (Time, speed, distance, amount of reps, etc). A higher record means a higher bonus. EX: Authority skill checks are associated with a timed “Lateral raise hold”. Every 30 seconds of the hold added onto your personal best single attempt offers a +1 bonus. So if you can do a lateral hold for 90 seconds, that’s a +3 to your authority check! So if you have a 16 in Iron, and your Personal Best lateral raise hold is 90 seconds, that would give you an Authority score of +6 (T-Pose for dominance!) Dynamic Exercise Bonus: This is where the unique mechanics of the game kick in. At any time during a skill challenge (even after your roll) you can add an additional modifier to the skill check by completing the exercise during gameplay! Did you roll just below the threshold for success? Crank out another 20 pushups, squats, or curls to push yourself just over the edge into success! There are 18 skills total, each with its own associated ability score and unique exercise: Grace (GRC): \-Kinesthesia (Timed: Blind single leg stand time) \-Precision (Scored: Basket throws) \-Charm (Timed reps: Standing repeated forward dumbell chest press and thrust) \-Stealth (Timed distance: Leopard Crawl) Agility (AGI): \-acrobatics (timed reps: high kicks) \-Computers (Word per minute: Typing test) \-Speed (Time: 100 meter sprint) Iron (IRN): \-Authority (Timed: Lateral raise hold) \-Resist (Timed: Plank) \-Persist (Timed:Pull-up bar dead hang) Nourishment(NRS): \-Recovery (TBD) \-Stim crafting (TBD) \-Survival (TBD) Strength(STR): \-Mechanics (Timed reps: Alternating curls) \-Might (Timed reps: pushups) Zen(ZEN): \-Perceive (TBD) \-Empathy (TBD) \-Harmony (TBD) \-Lore (TBD) Healthy Habits Bonus: Being able to demonstrate that you have conducted healthy habits during gameplay can also add one time bonuses per skill challenge “Drank a glass of water +1 to Nourishment check”, “Cleaned your room, +3 on Zen check”. But watch out, if you’re caught in unhealthy Habits, the GM can throw in penalties, “Ate junk food, -1 to Nourishment check”, etc. Bonuses/penalties from in-game items, equipment, buffs, debuffs, etc., helping players to immerse into the mechanics of the world of REP-SET for the thrill of constantly finding ways to improve their player. Gradient success: Result of skill challenges can be pass or fail, but can also be on a sliding scale of success. Are you racing to the battlefield? Depending on your Speed check, you might arrive early and have a tactical advantage, just in time for an even fight, or maybe far too late and some of your favorite allied NPCs have paid the price… So you’re often encouraged to stack on those dynamic exercise bonuses when you can to get the most fortuitous outcomes available to you. Gameplay sample: GM: Your REP-SET is a phantom, a streak of light against the vast hull of the warship. Enemy fighters buzz angrily, but you weaves and dodges with uncanny precision. The energy wave might be losing effectiveness, but your agility and connection to the machine have never been stronger. Then, it happens. A gap in the defenses. A vulnerable seam in the warship's armor. Your coms agents keen eye spots it instantly. "Lower power junction, starboard side! You have an opening!" This is your chance to strike the decisive blow. But how? It'll take a perfect combination of skill and strategy, drawing upon your various strengths. Here are your options: Option 1: Brute Strength: Channel all remaining power into a single, overwhelming blast from the core. High-risk, high-reward. It could overload the REP-SET if you fail, but it might also cripple the warship. (Strength-focused, Might sub-skill) Option 2: Calculated Strike: With surgical precision, target the power junction with a pinpoint burst of destabilizing energy. Less flashy and ultimately less damaging, but potentially more effective in temporarily disabling the ship. (Agility-focused, Precision sub-skill) Option 3: Harmonic Disruption: Attempt to harmonize with your REP-SET's AI spirit for help in connecting to the digital systems of the Warship. Can you generate an internal energy resonance within the warship, causing it to malfunction from within? (Zen-focused, Harmony sub-skill) Player: I'll take option 1, brute strength! GM: Ok, This will be a "Might" check. The CR is going to be very high on this one. I'm setting it at a 20. What's your Might bonus? Player: Dang, a 20?? That's literally impossible. My Might is 15 and I've got a PB of 65 pushups in 2 minutes, that sets me at a +5. Even if I roll a 10 and do 60 pushups for the DE I'll only get 18 max. GM: Hey I told you it was high risk. You want to choose another option? Player: No, no. This is what my character would do. I'm a real hot-blooded meathead for sure. GM: Ok then, roll a D10 and add your bonus. Player: \Rolls\ a 9! not bad, actually that's a really good roll. So +5, that's a 14. GM: Alright, would you like to add a dynamic exercise bonus? Player: Duh, it's not like I can do 120 pushups I'd need to beat the CR, but I can at least do better than 14. Alright, here goes. \the player gets down to do pushups and the 2 minute time begins. After some time...\ Player: 65....... 66! GM: Times up. Player: Ow... my arms... GM: so with 66, that's an extra +3, and its a new PB, so that's a +1. That sets your roll to 18. Player: Ow... Frack... still not 20... for a second there i really believed I could do 120 pushups... well I did my best... Ow... 20 CR is just too impossible you jerk... GM: Hmm... Tell me, what did you eat for lunch today? Player: Me? I made some vegetable and pork soup, and a protein shake. I recorded it all in my diet app. GM: And how did you sleep last night? Player: Like a baby, went to sleep early, woke up at 6. GM: in that case, you can add a +1 "Protein bonus" and +1 "Healthy rest" bonus to any strength related check for the day if you'd like, including this one. Player: Really?? Heck yes! add it to the roll! GM: With those extra bonuses, your roll reaches 20. How do you want to do this? Player: I roar "For Terra!" and pour every last ounce of my strength into the REP-SET. GM: "For Terra!" you roar, your cry echoing through coms systems of the REP-SET. The core flares blindingly bright. The surge of power dwarfs anything the REP-SET has unleashed before. With a titanic shriek that cracks the very fabric of space, the REP-SET slams into the vulnerable power junction. Raw energy explodes outwards, tendrils of light arcing across the warship's massive hull. The impact is staggering. The leviathan-like warship buckles, its sleek form rippling with shockwaves. Sparks shower like rain, secondary explosions erupt as critical systems overload. Then…silence. The warship goes dark. Power flickers within the REP-SET itself, then steadies. Alarms fade, replaced by the eerie quiet of damaged but functional systems. "We…did it?" The coms agents voice is incredulous, tinged with relief. She's awaiting your reply. Player: "I guess so." I say, and I smile and laugh. And then I slump back... and fall unconscious. \to the other players\ I'm not doing any more skill checks for a while guys, come pick me up please. \teammates cheer\ &#x200B;

How to increase the sales of my book

In just 3 months, it generated over $100 in revenue. I wanted to share my journey for two reasons: to potentially assist others in self-publishing their own books and to receive feedback to enhance my marketing strategy. I envision that there are others facing similar challenges. Let's dive into the financials, time spent, Key takeaways and the Challenges to address behind this product. Finances First, let's take a look at the financial overview. 💳 Expenses 🔹 E-book creation: · Book cover: $ 0. I used Adobe Express with 30 days of free trial. · ChatGPT: 20 $ a month. I leveraged AI to generate the chapters of the book, ensuring that no critical topics were overlooked during the content creation process and to refine the English, as it's not my native language. I also used to help me with copywriting of the web. If anyone is interested, I can share my Python code for outlining the chapters calling the API, but you can also directly ask chatgpt. · Kindle KDP (Kindle Direct Publishing): order author copies: 10 $. 🔹 Web creation: Domain: I got a com) / .org /.net domain for just 1 $ the first year. Carrd.co subscription: 19 $ (1 year) 🔹 Marketing: Promoted post on reddit: $30 Paid ads with google ads: $30 💰 Revenue 🔸 Sales: $102 💸 Net Profit: \~- $ 18 I initially thought the sales for this e-book would be quite modest, maybe only 3 or 4 books. However, the fact that I've sold more than that so far is a pleasant surprise. Even though the overall numbers may still be considered "peanuts" in the grand scheme of book sales, it suggests there could be more demand for content on digital asset custody than I had originally anticipated. This is a good learning experience, and I'll look to refine my marketing approach to see if I can reach a wider audience interested in this topic 🔹 Time Spent Next, let's review the time invested. 📖 Writing the e-book: 40 hours 🌍 Website + Stripe integration: 10 hours 📣 Creating promotional content: 10 hours ⏱️ Additional marketing efforts: 5 hours Total time spent: 65 hours As you can see, I dedicated more time to writing the e-book itself than to marketing and distribution. I spent relevant time to marketing because I though that a successful product launch requires a robust marketing effort. Many e-book authors overlook this crucial aspect! I utilized three sales channels: · Amazon: I found that there were no books specifically about digital asset custody, resulting in strong positioning in Amazon searches. Additionally, my book immediately secured the top position in Google searches for "digital asset custody book." However, despite achieving 50% of sales in the UK, I have not received any reviews globally. Sales distribution for this channel: 20% physical book, 80% ebook. · Twitter: Daniel\_ZZ80. With only 46 followers, the performance on this platform has not been optimal. I am beginning to write posts related to digital assets to increase visibility. · Gumroad: Lockeyyy.gumroad.com. I offered a discounted version of the ebook, but have not yet made any sales through this channel. Key takeaways: · The process of creating this e-book was extremely fulfilling, and while it has garnered overwhelmingly positive feedback from friends and colleagues (not considered as sales), it has yet to receive any Amazon reviews ☹. · Kindle KDP proved to be ideal for a rapid go-to-market strategy. · AI is an excellent tool for generating ideas and providing access to global audiences with perfect grammar. Otherwise, I would need to hire a translator, which can be very expensive. · Despite offering a full 30-day money-back guarantee, leading me to believe that the quality of the content is indeed good. · I have gained valuable insights for future technical books. · Although the current financial balance may be negative, I anticipate reaching the break-even point within one month, and this has now become a passive income stream. However, I recognize the need to regularly update the content due to the rapidly changing nature of this field. Challenges to address: · Is the timing for launching this book appropriate? In other words, is the world of digital asset custody a trendy and interesting topic for the audience? · What is causing the lack of sales through Gumroad? · Should I seek assistance as my marketing efforts have not yielded results? · Why are there no reviews on Amazon? · Why are sales primarily concentrated in the EU with only one sale in the US, which is my main target market? Feedback is appreciated. If you're interested in learning more about my approach, feel free to send me a direct message. A bit about my background: After dedicating my entire career to the banking industry, I explored various side projects. As an IT professional, I have now transitioned into the digital asset realm. After three years of intensive study, I recently published my first book on digital asset custody. I hope you found this post informative. Cheers! P.S.: I'm currently in the process of launching two more books using this system. 😊

Business Strategy Trends for 2024

As we gear up for 2024, it's time to gaze into the crystal ball and see what's reshaping the world of business strategy. From cutting-edge technology to how people are shopping, it's all happening. So let's check out the latest trends that are going to dominate the business world! Going Green and Doing Good Yep, you heard it right—being eco-friendly and socially responsible is all the rage. Businesses are jumping on the sustainability train, whether it's by using recycled materials or giving back to the community. It's not just good for the planet—it's good for business too! Tech Takeover From fancy AI to blockchain innovations, businesses are embracing all things digital. It's not just about staying up to date—it's about using technology to make things easier, faster, and way more amazing. Work from Anywhere Who says you have to be stuck in an office all day? Today, businesses are all about flexibility. Whether you're working from home, a coffee shop, or a hammock on the beach, it's all good. Remote work is here to stay, and people are loving the freedom it brings. Treat Yo' Customers Want to stand out in a sea of competition? It's all about making your customers feel special. Whether it's personalized recommendations or killer customer service, businesses are pulling out all the stops to keep folks coming back for more. Roll with the Punches In today's fast-paced world, you've got to be quick on your feet. That's why businesses are ditching rigid plans and embracing agile strategies. It's all about being able to adapt to whatever curveballs the world throws your way. Click, Buy, and Repeat Online shopping is getting bigger. Businesses are getting creative with their online offerings, whether it's through slick new websites, social media shenanigans, or funky new delivery options. The future of shopping is digital! Conclusion: The lowdown on what's shaking up the world of business strategy in 2024. Whether it's going green, embracing tech, or keeping customers happy, there's plenty of excitement on the horizon.

What Are the Top Small Business Trends You Must Know for 2024 ?

Are you excited about the new business horizons in 2024? Well, you should be! The small business landscape is evolving faster than anything right now, and here are the trends you absolutely need to know to keep your business game strong. Sustainable Swag In a world where eco-friendliness is the new black, businesses are carrying the badge of sustainability. From eco-packaging to carbon-neutral practices, customers are giving the side-eye to anything less green. So, if you want to be at the top, consider adopting some planet-friendly practices. Remote Work Revolution Office who? The 9-to-5 grind is getting a makeover, and the dress code is PJs. Remote work is no longer just a trend; it's a lifestyle. So, if your business can embrace the virtual office, you might just find your team doing the hustle and bustle with productivity. Tech-Tastic Ventures The future is now, and it's filled with tech wonders. Augmented reality (AR), artificial intelligence (AI), and all things tech are the new developments in this sector. Businesses incorporating these innovations are riding the digital wave straight to success. Personalization Party No one likes generic. Customers want products and services tailor-made just for them. So, businesses are using data to give customers an experience that feels as customized as a handmade suit. Say goodbye to one-size-fits-all! Community Crusaders In a world full of noise, community is the superhero we all need. Businesses are realizing the power of building a network around their brand. Whether it's through social media, events, or exclusive memberships, creating a community is like having an army of brand advocates. 2024 is the year to unleash your small business swagger. Embrace these trends, adapt with flair, and let your entrepreneurial spirit soar. Remember to sprinkle some personality into your business strategy—people love a brand with a sense of humor and a human touch!

Please, help me to narrow down the list of ideas to pursuit

Hi guys, I need help to narrow down the possible problems to solve. How do you do it? What do you think about these ideas? All came from real-life problems. Break-It-Down Problem-Solving Assistant Problem: Large, complex projects can feel overwhelming and difficult to tackle. Solution: An AI-guided assistant that analyzes your project goals and automatically breaks them into smaller, manageable tasks. It provides suggested resources and real-time collaboration with team members for smoother task delegation. Personalized Sleep Solutions Problem: Poor sleep quality affects health, productivity, and overall well-being. Solution: An adaptive app that tracks sleep patterns through wearable data and adjusts sleep routines, room settings, and audio cues based on real-time sleep stages for optimal rest. Skill Analysis & Development Tool Problem: It’s challenging to identify valuable skills for career growth and keep up with future demands. Solution: AI-driven skill analysis with a personalized career roadmap that maps out high-demand skills for your specific industry, combined with real-time market trend analysis to suggest learning resources and certifications. Innovator’s Problem Discovery Platform Problem: Innovators struggle to identify real industry problems that need innovative solutions. Solution: An AI-powered platform that gathers and analyzes challenges from different industries, crowdsources ideas, and uses machine learning to highlight innovation opportunities tailored to your skills and interests. High-Earning Career Strategy Platform Problem: Many professionals face challenges in maximizing their earning potential and advancing their careers. Solution: A dynamic career advancement platform that analyzes your skill set, tracks job market trends, and offers personalized mentorship sessions with high-earning professionals in your field, along with salary benchmarking and negotiation tips.

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

How I Made $250.000+ in a Year: A Case Study of My AI Influencer Journey

Update on February 22th: I changed my AI influencer's names because it caused some problems on my business. One year, two AI-powered influencers, and $250K in revenue. Sounds unreal? It’s not. Today, I’m pulling back the curtain on the strategies, tools, and hard-won lessons that took me from concept to a six-figure success story in the AI influencer space. Hey, I'm Ben—a 32-year-old designer who spent the past year navigating the world of AI influencers. Let me clear up any confusion right from the start: I’m not here to sell you anything. This is purely a case study to share what worked, what didn’t, and what I’ve learned along the way. I’ll also make sure to answer all your questions in the comments for free whenever I can, so don’t hesitate to ask. Links to Past Topics: If you're curious about some of the groundwork I covered, check out a few of my earlier posts here: How I Make $10,000 Monthly | AI Influencer Management How I Earned $7000+ in 15 Days | AI Influencer Business Update These earlier posts cover a lot of the backstory, so feel free to explore them before diving into this one. So if you're ready, here is the full story: \---- The idea of creating an AI influencer was one of those “what if” moments that wouldn’t leave my mind. At first, it sounded futuristic—even a bit too ambitious. It all started when I stumbled upon an AI influencer on Instagram with the handle AnnaMaes2000. Her content blew me away—the quality, the detail, and just how real everything looked. I was instantly hooked and ended up going through every post, just trying to figure out how she was pulling this off. That’s when I knew I had to learn how this was done. The next step? YouTube. I dived into videos on Stable Diffusion, soaking up everything I could about creating AI-generated images. Those tutorials taught me the basics and got me up to speed. Then, I created my first AI influencer, let's call her Mel for now. Right after that, to complete the storyline and boost engagement, I introduced Mel's “mother,” Jess. Adding Jess gave the whole project depth and a narrative that drew people in, creating a unique family dynamic that instantly elevated traffic and interest. After thousands of bad photos, hundreds of deleted posts, and months of trial and error, you can now see the quality that defines my current accounts. Here’s a rundown of the tools and checkpoints I’ve used from day one, in order: Fooocus on RunDiffusion — Juggernaut V8 Fooocus on RunDiffusion — Juggernaut V9 Fooocus on PC (locally) — Juggernaut V9 Fooocus on PC (locally) —Lyuyang Mix + Juggernaut V9 Flux on PC (couple of photos only since it's so slow even on RTX 4090) Flux on Fal.ai. \---- There’s no magic Instagram hack that guarantees success, despite what everyone thinks and keeps asking me. Quality content, consistent uploads, and solid craftsmanship are what actually help your photos hit trends and show up on the Explore page. Unlike 95% of low-quality AI accounts out there, I don’t rely on faceswap videos, spam Reels, or go around liking comments on other accounts. My approach is fully organic, focused solely on creating my own unique content. By following Instagram's guidelines to the letter, I've managed to direct some of Mel and Jess' fans over to Patreon and Fanvue. There, for a small subscription fee, fans can access exclusive lingerie content. For those looking for more, higher-tier subscriptions give access to even more premium content. Some possible questions and their answers: No, you can't share hardcore NSFW content on Patreon. You can do that on Fanvue. Yes, you can create AI creators on Fanvue — OnlyFans doesn't allow it. Yes, you can use your own ID to get KYC. Yes, we're telling both Mel and Jess is (or use) AI to generate content. And yes, some people leave and some people still have fun with chatting, having a good time and get perfect content for their needs. And yes, we have a chatter team to work on these accounts. \---- This journey wasn’t all smooth sailing. I faced unexpected roadblocks, like platform restrictions that limited certain types of content, and managing fan expectations was more challenging than anticipated. Staying within guidelines while keeping fans engaged required constant adaptation. These hurdles forced me to get creative, adjust my approach, and learn fast. Once I saw Mel and Jess gaining traction, I knew it was time to scale up. Expanding meant finding new ways to keep content fresh, creating deeper narratives, and considering how to bring even more followers into the fold. My focus turned to building a sustainable model that could grow without sacrificing quality or authenticity. If you’re thinking about diving into AI content creation, here’s my advice: patience, consistency, and a focus on quality are key. Don’t cut corners or rely on quick-fix hacks. Invest time in learning the right tools, creating engaging stories, and building an audience that values what you bring to the table. This approach took me from zero to six figures, and it’s what makes the journey worth it. \---- And finally, here’s the income breakdown that everyone’s curious about: Mel on Fanvue: $82,331.58 (Gross earnings because we have chatter cuts like 15%) Mel on Patreon: $50,865.98 (Net earnings) Jess on Fanvue: $89,068.26 (Gross earnings because we have chatter cuts like 15%) Jess on Patreon: $39,040.70 And thanks to Reddit and my old posts, I got a perfect investor like after 5 months, so this is a "payback" for that. Like I said, I'll answer every question in the comments — take care and let me know.

Tickets for everyone

Hey guys , I working currently on a software start up and wanted to ask what u think of the idea in generally It’s a ticket marketplace for concerts , events etc The difference between me and Ticketmaster / Eventbrite that we use a kyc for a face scan to eliminate bots and we try to implement ai to spot links that can go to another ticket / fraud sites / basically disrupting the manipulated and rigged ticket industry Feel free to roast or question

How to get that big idea for your next business? Use trends!

Hello entrepreneurs and aspiring business owners, I am Mikael and I want to share a post about how to spot business ideas. If you're wondering who the owl is, it's Agent O, my sidekick (please bear with him... or me, if you can). Let's get on to it. So, there are basically two ways of getting ideas for your new business: Find a service, product or experience that's already working. Identify and ride a trend. 🦉 : Third, have a rich relative pass you their business and sip margaritas by the sea while scrolling Reddit for the rest of your life! 🕵️ : Refrain yourself, I just got started ffs, I don't want to get banned! So, what are trends? Trends are patterns of adoption of a product, service or experience by people who want to satisfy a common need. Cool, huh? How trends start Trends emerge and evolve as temporary or permanent solutions to human needs. All products, services and experiences are the expression of human needs manifested through a perceived lack, which we humans interpret as problems. Let me make this more clear. Humans have needs: from basic (food, shelter, safety) to advanced (community, knowledge) to evolved (self actualization, spirituality) and everything in between. Don’t see this as a hierarchy, as it’s usually depicted with Maslow’s pyramid. See it as cycles with different degrees of impact on humans that vary in time and intensity. 🦉 : WHAT!?? 🕵️ : Hear me out… How Trends Affect Society Human needs are physical, emotional, intellectual and spiritual. Every day we feel the impact of those needs with different degrees of required fulfillment. You can’t go on without air for more than a few minutes. You can’t live without food and water for more than a few days. So, when it comes to the needs of the body, these have a shorter timeframe in which they need to be addressed. 🦉 : Ahh, I see what you did there… \\🕵️ \\: Thanks! But you can also live with an unfulfilled need for love or friends for a long time. You can live with a decaying health as well. And you also can live your entire life without finding out if there is a God or not. Humans perceive needs as something they lack within, which in turn is expressed as a problem on the outside. I lack food or water, this will create a problem for my survival. So I need to find food and water in my environment. This lack creates a behavior seeking a product, service or experience to fulfill that need. Makes sense? 🦉 : I just went out and got me a “Mice à la Forest” dinner! 🕵️: Bon appétit! See, Agent O fulfilled a bodily need. That’s what animals do, as they’re driven by instinct and are governed by natural laws (survive, reproduce, sleep, repeat). Humans are driven by more complex needs, as our intellect and emotions allow us to override those basic primary instincts. Why Trends Are Important What an entrepreneur does is to shift the perspective: instead of seeing a lack, he/she sees an opportunity by asking the question: how can I fulfill this need? Or, even better put: how can I help people by solving their problem? That’s the first step to solving a problem: asking a question. That is why the best products are actually problems solved by entrepreneurs who work to solve their own need for a product, service or experience. They then provide it to other people for a cost. Easy, right? That’s what entrepreneurship is: solving a problem. The bigger the problem, the bigger the impact. The bigger the impact, the higher the revenue. It’s easier to understand trends now, isn’t it? You can see that trends are nothing more than the initial adoption of a product, service or experience by a group of people who are looking for a solution to their common need. 🦉 : Did you get that from a book? 🕵️ : You snore when you sleep… ¯\\(\ツ)/\¯ 🦉 : $@#&\*! Hooman! Needs are the foundation on which the modern world is built. Once you understand needs, you fundamentally change your perception of problems into opportunities. This mental shift is the entrepreneurial mindset: where others see problems, you see solutions. Where Do Trends Start So, to recap: human needs are translated into problems. Founders understand the root of the problem (the need) and create products, services, experiences as solutions to those needs. They offer the solution to the public through startups and companies, which belong to a specific niche in a particular industry. 🦉 : Aaah, so that’s why it’s called venture capital? 🕵️ : Yeah, because you’re venturing into a new endeavor to let people know about your solution to their (and ideally your) problem. 🦉 : So if you use ads to market your venture, it’s an adventure? 🕵️ : I see what you did there… If the need behind the adoption is strong and real enough, that trend will translate into a niche within an industry. If the adoption isn’t driven by strong fundamental needs, it will turn into a fad and disappear from the perception of the public, no matter how much marketing money is thrown at it. This happens because the solution (product/service/experience) to the need didn’t create the physical, intellectual or emotional response required to create a recurring behavior around it. Remember this: Problem (why) -> Behavior (how) -> Solution (what) Understand this: there are multiple types of trends. There are product or service trends. There are industry driven trends. There are tendency driven trends, like the emergence of a new paradigm that improves a lot of industries (yes, I’m looking at you, AI). Where Do Trends Come From So now you can see that trends are patterns of adoption related to a specific human need that is addressed through one or multiple products or services. This is a bottom up direction coming from evolution. Multiple trends in different industries also emerge from a theme, which is a bigger vision of a human effort to address a high level problem. This is a top down direction, coming from implementation (by governments, different organizations or other interested parties with the power to influence changes at mass level). Conclusion Now you have a better understanding of trends by looking at them through the lens of human needs. Also, you might also understand time better because you realize that human needs have different degrees of impact in time and intensity. So you now see that trends don’t only relate to individuals, but also to groups of people, from the smallest community to countries and even global needs. That is the reason you’ll sometimes hear some say that time is a flat circle: because clothes change, but humans are quite the same. Needs don’t change a lot in time, just the way we address and solve them. Here’s an interesting game for you: take a look at some behaviors in your life. Which of them are driven by a bodily need, which by an intellectual or emotional one? Which ones are completely automated and you had no idea you were doing? How are these behaviors controlling parts of your life that you were unaware of until now? If you made it this far, thank you for taking the time to read this. I hope you enjoyed it, found it useful and entertaining. Ofc, I value your opinion and welcome it in the comments. Thank you!

Idea feedback: AI-native self-improvement & wellness

Hello redditors! Thesis: We're all trying to live our best lives and many of us try to leverage technology to become better faster and easier. I’m trying to build a company that builds an AI-native solution for self-improvement. My thesis is that AI is an incredibly powerful tool for solving problems, particularly in programming and generally life - but ChatGPT isn't really designed to be your long-term 'coach'. It's great for handling specific tasks, answering questions, doing research, etc. - but it's memory and UX isn't optimized around things like behavior change, mental health support, and long-term personal life planning I believe my core problems (which I think are shared by many) are: 1) Staying motivated - it's easy to lose motivation when progress isn't immediately apparent, there are setbacks, etc. 2) Self-doubt - it makes me question myself and waste time wondering if I'm the right person to be doing this, if the idea is too broad, etc. Some of this is good - but a lot of it just makes me less effective 3) Staying on Track - I start a thing, but then gradually pivot a million different directions. This may be a touch of ADHD. I find that I'll have a long-term goal (e.g. launching a successful business), but I'll tend to wonder a lot in the process of executing over weeks and months. Staying on track just feels suprisingly difficult. I do create TODO lists and have a Kanban board I’m considering a bunch of features and have built a version focused more specifically towards mental health which implements a few: \----- • Guided Journaling Guided journaling prompts to facilitate deeper reflection • Specialist AI Coaches Personalized, expert AI coaching for your specific area of focus and goals For startup, marketing, life, fashion, whatever you want. • Goal Tracking Define, track, and achieve your goals • Behavior Change & Habit Formation Leverage the science of behavior change to help you make lasting changes in your life • Mood tracking Track and improve your mood leveraging science-backed techniques • Areas for growth Identify and develop your strengths and manage your weaknesses • Insight reports Get personalized insights into your cognitive and behavioral patterns • Inspirational Quotes Stay motivated with curated daily quotes relevant to your journey • Gamification of Growth & Mood Turn your mental health journey into a game and earn rewards for your progress \---- Would love thoughts on the idea, and feedback - and if anyone is interested in being a design partner / early user, I'd love to chat in greater depth 1:1!

How to get that big idea for your next business? Use trends!

Hello entrepreneurs and aspiring business owners, I am Mikael and I want to share a post about how to spot business ideas. If you're wondering who the owl is, it's Agent O, my sidekick (please bear with him... or me, if you can). Let's get on to it. So, there are basically two ways of getting ideas for your new business: Find a service, product or experience that's already working. Identify and ride a trend. 🦉 : Third, have a rich relative pass you their business and sip margaritas by the sea while scrolling Reddit for the rest of your life! 🕵️ : Refrain yourself, I just got started ffs, I don't want to get banned! So, what are trends? Trends are patterns of adoption of a product, service or experience by people who want to satisfy a common need. Cool, huh? How trends start Trends emerge and evolve as temporary or permanent solutions to human needs. All products, services and experiences are the expression of human needs manifested through a perceived lack, which we humans interpret as problems. Let me make this more clear. Humans have needs: from basic (food, shelter, safety) to advanced (community, knowledge) to evolved (self actualization, spirituality) and everything in between. Don’t see this as a hierarchy, as it’s usually depicted with Maslow’s pyramid. See it as cycles with different degrees of impact on humans that vary in time and intensity. 🦉 : WHAT!?? 🕵️ : Hear me out… How Trends Affect Society Human needs are physical, emotional, intellectual and spiritual. Every day we feel the impact of those needs with different degrees of required fulfillment. You can’t go on without air for more than a few minutes. You can’t live without food and water for more than a few days. So, when it comes to the needs of the body, these have a shorter timeframe in which they need to be addressed. 🦉 : Ahh, I see what you did there… \\🕵️ \\: Thanks! But you can also live with an unfulfilled need for love or friends for a long time. You can live with a decaying health as well. And you also can live your entire life without finding out if there is a God or not. Humans perceive needs as something they lack within, which in turn is expressed as a problem on the outside. I lack food or water, this will create a problem for my survival. So I need to find food and water in my environment. This lack creates a behavior seeking a product, service or experience to fulfill that need. Makes sense? 🦉 : I just went out and got me a “Mice à la Forest” dinner! 🕵️: Bon appétit! See, Agent O fulfilled a bodily need. That’s what animals do, as they’re driven by instinct and are governed by natural laws (survive, reproduce, sleep, repeat). Humans are driven by more complex needs, as our intellect and emotions allow us to override those basic primary instincts. Why Trends Are Important What an entrepreneur does is to shift the perspective: instead of seeing a lack, he/she sees an opportunity by asking the question: how can I fulfill this need? Or, even better put: how can I help people by solving their problem? That’s the first step to solving a problem: asking a question. That is why the best products are actually problems solved by entrepreneurs who work to solve their own need for a product, service or experience. They then provide it to other people for a cost. Easy, right? That’s what entrepreneurship is: solving a problem. The bigger the problem, the bigger the impact. The bigger the impact, the higher the revenue. It’s easier to understand trends now, isn’t it? You can see that trends are nothing more than the initial adoption of a product, service or experience by a group of people who are looking for a solution to their common need. 🦉 : Did you get that from a book? 🕵️ : You snore when you sleep… ¯\\(\ツ)/\¯ 🦉 : $@#&\*! Hooman! Needs are the foundation on which the modern world is built. Once you understand needs, you fundamentally change your perception of problems into opportunities. This mental shift is the entrepreneurial mindset: where others see problems, you see solutions. Where Do Trends Start So, to recap: human needs are translated into problems. Founders understand the root of the problem (the need) and create products, services, experiences as solutions to those needs. They offer the solution to the public through startups and companies, which belong to a specific niche in a particular industry. 🦉 : Aaah, so that’s why it’s called venture capital? 🕵️ : Yeah, because you’re venturing into a new endeavor to let people know about your solution to their (and ideally your) problem. 🦉 : So if you use ads to market your venture, it’s an adventure? 🕵️ : I see what you did there… If the need behind the adoption is strong and real enough, that trend will translate into a niche within an industry. If the adoption isn’t driven by strong fundamental needs, it will turn into a fad and disappear from the perception of the public, no matter how much marketing money is thrown at it. This happens because the solution (product/service/experience) to the need didn’t create the physical, intellectual or emotional response required to create a recurring behavior around it. Remember this: Problem (why) -> Behavior (how) -> Solution (what) Understand this: there are multiple types of trends. There are product or service trends. There are industry driven trends. There are tendency driven trends, like the emergence of a new paradigm that improves a lot of industries (yes, I’m looking at you, AI). Where Do Trends Come From So now you can see that trends are patterns of adoption related to a specific human need that is addressed through one or multiple products or services. This is a bottom up direction coming from evolution. Multiple trends in different industries also emerge from a theme, which is a bigger vision of a human effort to address a high level problem. This is a top down direction, coming from implementation (by governments, different organizations or other interested parties with the power to influence changes at mass level). Conclusion Now you have a better understanding of trends by looking at them through the lens of human needs. Also, you might also understand time better because you realize that human needs have different degrees of impact in time and intensity. So you now see that trends don’t only relate to individuals, but also to groups of people, from the smallest community to countries and even global needs. That is the reason you’ll sometimes hear some say that time is a flat circle: because clothes change, but humans are quite the same. Needs don’t change a lot in time, just the way we address and solve them. Here’s an interesting game for you: take a look at some behaviors in your life. Which of them are driven by a bodily need, which by an intellectual or emotional one? Which ones are completely automated and you had no idea you were doing? How are these behaviors controlling parts of your life that you were unaware of until now? If you made it this far, thank you for taking the time to read this. I hope you enjoyed it, found it useful and entertaining. Ofc, I value your opinion and welcome it in the comments. Thank you!

Can AI Mentorship and Community Support Help Entrepreneurs Succeed?

Starting a business can often feel like you're flying blind, especially without a mentor to guide you. But what if you could tap into AI-powered mentorship tools and a supportive community to get advice and feedback whenever you need it? 🚀 AI mentorship offers personalized guidance and structured frameworks, minus the need for traditional face-to-face time. And platforms like this one allow us to connect, share experiences, and learn from each other. It’s a game-changer, right? Here’s what I’m curious about: Have you tried AI mentorship tools? What was your experience? How do you currently get advice and feedback on your business? Do you think mentorship should always be face-to-face, or can online tools and communities play a big role in helping entrepreneurs succeed? Would you consider using structured learning tools (like lesson-based frameworks or step-by-step guidance) to guide your entrepreneurship journey? I’m working on Procasio, an educational entrepreneurship app designed to promote inclusivity and accessibility. It would combine AI mentorship, structured learning paths, gamified elements, and case studies, helping small business owners, teachers, students, and aspiring entrepreneurs learn effectively without overwhelming costs. 🎓💡 The app would include: Discussion posts and messaging for real-time advice. Goal setting and personalized learning recommendations. Case studies and practical scenarios to put theory into action. A low-cost, accessible approach for entrepreneurs at any stage. I’d love to hear your thoughts—do you think AI-powered mentorship and structured learning can make entrepreneurship education easier and more effective?

How I Made $250.000+ in a Year: A Case Study of My AI Influencer Journey

Update on February 22th: I changed my AI influencer's names because it caused some problems on my business. One year, two AI-powered influencers, and $250K in revenue. Sounds unreal? It’s not. Today, I’m pulling back the curtain on the strategies, tools, and hard-won lessons that took me from concept to a six-figure success story in the AI influencer space. Hey, I'm Ben—a 32-year-old designer who spent the past year navigating the world of AI influencers. Let me clear up any confusion right from the start: I’m not here to sell you anything. This is purely a case study to share what worked, what didn’t, and what I’ve learned along the way. I’ll also make sure to answer all your questions in the comments for free whenever I can, so don’t hesitate to ask. Links to Past Topics: If you're curious about some of the groundwork I covered, check out a few of my earlier posts here: How I Make $10,000 Monthly | AI Influencer Management How I Earned $7000+ in 15 Days | AI Influencer Business Update These earlier posts cover a lot of the backstory, so feel free to explore them before diving into this one. So if you're ready, here is the full story: \---- The idea of creating an AI influencer was one of those “what if” moments that wouldn’t leave my mind. At first, it sounded futuristic—even a bit too ambitious. It all started when I stumbled upon an AI influencer on Instagram with the handle AnnaMaes2000. Her content blew me away—the quality, the detail, and just how real everything looked. I was instantly hooked and ended up going through every post, just trying to figure out how she was pulling this off. That’s when I knew I had to learn how this was done. The next step? YouTube. I dived into videos on Stable Diffusion, soaking up everything I could about creating AI-generated images. Those tutorials taught me the basics and got me up to speed. Then, I created my first AI influencer, let's call her Mel for now. Right after that, to complete the storyline and boost engagement, I introduced Mel's “mother,” Jess. Adding Jess gave the whole project depth and a narrative that drew people in, creating a unique family dynamic that instantly elevated traffic and interest. After thousands of bad photos, hundreds of deleted posts, and months of trial and error, you can now see the quality that defines my current accounts. Here’s a rundown of the tools and checkpoints I’ve used from day one, in order: Fooocus on RunDiffusion — Juggernaut V8 Fooocus on RunDiffusion — Juggernaut V9 Fooocus on PC (locally) — Juggernaut V9 Fooocus on PC (locally) —Lyuyang Mix + Juggernaut V9 Flux on PC (couple of photos only since it's so slow even on RTX 4090) Flux on Fal.ai. \---- There’s no magic Instagram hack that guarantees success, despite what everyone thinks and keeps asking me. Quality content, consistent uploads, and solid craftsmanship are what actually help your photos hit trends and show up on the Explore page. Unlike 95% of low-quality AI accounts out there, I don’t rely on faceswap videos, spam Reels, or go around liking comments on other accounts. My approach is fully organic, focused solely on creating my own unique content. By following Instagram's guidelines to the letter, I've managed to direct some of Mel and Jess' fans over to Patreon and Fanvue. There, for a small subscription fee, fans can access exclusive lingerie content. For those looking for more, higher-tier subscriptions give access to even more premium content. Some possible questions and their answers: No, you can't share hardcore NSFW content on Patreon. You can do that on Fanvue. Yes, you can create AI creators on Fanvue — OnlyFans doesn't allow it. Yes, you can use your own ID to get KYC. Yes, we're telling both Mel and Jess is (or use) AI to generate content. And yes, some people leave and some people still have fun with chatting, having a good time and get perfect content for their needs. And yes, we have a chatter team to work on these accounts. \---- This journey wasn’t all smooth sailing. I faced unexpected roadblocks, like platform restrictions that limited certain types of content, and managing fan expectations was more challenging than anticipated. Staying within guidelines while keeping fans engaged required constant adaptation. These hurdles forced me to get creative, adjust my approach, and learn fast. Once I saw Mel and Jess gaining traction, I knew it was time to scale up. Expanding meant finding new ways to keep content fresh, creating deeper narratives, and considering how to bring even more followers into the fold. My focus turned to building a sustainable model that could grow without sacrificing quality or authenticity. If you’re thinking about diving into AI content creation, here’s my advice: patience, consistency, and a focus on quality are key. Don’t cut corners or rely on quick-fix hacks. Invest time in learning the right tools, creating engaging stories, and building an audience that values what you bring to the table. This approach took me from zero to six figures, and it’s what makes the journey worth it. \---- And finally, here’s the income breakdown that everyone’s curious about: Mel on Fanvue: $82,331.58 (Gross earnings because we have chatter cuts like 15%) Mel on Patreon: $50,865.98 (Net earnings) Jess on Fanvue: $89,068.26 (Gross earnings because we have chatter cuts like 15%) Jess on Patreon: $39,040.70 And thanks to Reddit and my old posts, I got a perfect investor like after 5 months, so this is a "payback" for that. Like I said, I'll answer every question in the comments — take care and let me know.

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

Looking For Tech-Savvy Business Partner

Hi! I'm looking for a business partner to help with one of my product lines or we could create a new product line together. I would like the product to be a digital asset where we can sell it on another website, where the other website brings customers to our product so we don't have to market it at first. Our short-term goal will be to publish a product one month after connecting and then make $1 by the following month. Our 4-month goal will be to generate $2,500 - $7,500 in passive income per year for one product line. I'm not trying to make a lot of money right away, but am looking to setup enough passive income so we can both retire early in a few years. For this year, I wrote down 100's of ideas, tried 30 ideas, have 14 ideas that work, and have only 6 ideas that would be profitable. So I'll bring with me only the best of the best ideas. I'm all about efficiency and doing things in bulk to maximize profit and decrease time spent, using AI to generate text/images/audio but adding on that manual touch to make all digital products high-quality and 5 stars, and using software like Python to automate repetitive processes to create digital products. My main skillset: running a business, project management, creating design and technical documentation, marketing, hiring, budgeting, business analysis, graphic design, software development, app development, web design/development, AI development, databases, data engineering, cloud/Azure, data analysis, and reporting. I know many other skills too and can pick up and learn a new business or technical skill pretty quickly. I also have a friend who's in IT/security/networking/servers if we need to bring him in. A clone of myself would be perfect to connect with, but working with anyone with a different skillset would open up the digital product possibilities. I might put tech-savvy at the top of the list so you could figure out how to create new digital products, while business-savvy might be #2, Other skills might be specific to individual products. If you're interested in working together, then feel free to post below or message me!

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

Looking For Tech-Savvy Business Partner

Hi! I'm looking for a business partner to help with one of my product lines or we could create a new product line together. I would like the product to be a digital asset where we can sell it on another website, where the other website brings customers to our product so we don't have to market it at first. Our short-term goal will be to publish a product one month after connecting and then make $1 by the following month. Our 4-month goal will be to generate $2,500 - $7,500 in passive income per year for one product line. I'm not trying to make a lot of money right away, but am looking to setup enough passive income so we can both retire early in a few years. For this year, I wrote down 100's of ideas, tried 30 ideas, have 14 ideas that work, and have only 6 ideas that would be profitable. So I'll bring with me only the best of the best ideas. I'm all about efficiency and doing things in bulk to maximize profit and decrease time spent, using AI to generate text/images/audio but adding on that manual touch to make all digital products high-quality and 5 stars, and using software like Python to automate repetitive processes to create digital products. My main skillset: running a business, project management, creating design and technical documentation, marketing, hiring, budgeting, business analysis, graphic design, software development, app development, web design/development, AI development, databases, data engineering, cloud/Azure, data analysis, and reporting. I know many other skills too and can pick up and learn a new business or technical skill pretty quickly. I also have a friend who's in IT/security/networking/servers if we need to bring him in. A clone of myself would be perfect to connect with, but working with anyone with a different skillset would open up the digital product possibilities. I might put tech-savvy at the top of the list so you could figure out how to create new digital products, while business-savvy might be #2, Other skills might be specific to individual products. If you're interested in working together, then feel free to post below or message me!

Looking for some legend keen to test an Ai chatbot and in return I give it for free for a whole year

Hey everyone! I’ve created an AI-powered chatbot designed to engage with website visitors, answer common questions, assist with lead generation, and even help provide context for sales calls by gathering customer insights. It’s built to not only save time but also to keep potential customers engaged with your business, making it an ideal tool for small to mid-sized companies looking to boost their online presence and improve sales conversion rates. I’m offering a free, year-long trial to a select group of business owners in exchange for constructive feedback. By using it, you'll get: Improved lead generation: The chatbot engages visitors and collects valuable info, making your sales calls more informed. Time-saving automation: Handles routine inquiries and FAQs, freeing up your team for other tasks. Valuable insights: Gather data on customer questions, preferences, and interests. If you’re interested or have questions, feel free to DM me! I'd love to hear your thoughts and see how we can make this tool as valuable as possible for businesses.

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

Looking for Investors in Dubai – High-Return AI Business Opportunity

We are launching an advanced AI automation business in Dubai, and we are looking for investors who want to be part of the future. Our AI technology is designed to take and make phone calls, revolutionizing customer service, sales, and business communication. This is an opportunity to invest in cutting-edge AI at an early stage, with fixed returns of 30% per year or 2% per month. To ensure security and transparency, all investments come with a legal agreement and post-dated cheques. AI-driven automation is the future, and businesses are actively looking for smarter, more cost-effective solutions. With the demand growing rapidly, this is your chance to be part of a high-potential venture in one of the fastest-growing tech sectors. If you’re interested in learning more, feel free to reach out. Let’s build the future together.

How I Made $250.000+ in a Year: A Case Study of My AI Influencer Journey

Update on February 22th: I changed my AI influencer's names because it caused some problems on my business. One year, two AI-powered influencers, and $250K in revenue. Sounds unreal? It’s not. Today, I’m pulling back the curtain on the strategies, tools, and hard-won lessons that took me from concept to a six-figure success story in the AI influencer space. Hey, I'm Ben—a 32-year-old designer who spent the past year navigating the world of AI influencers. Let me clear up any confusion right from the start: I’m not here to sell you anything. This is purely a case study to share what worked, what didn’t, and what I’ve learned along the way. I’ll also make sure to answer all your questions in the comments for free whenever I can, so don’t hesitate to ask. Links to Past Topics: If you're curious about some of the groundwork I covered, check out a few of my earlier posts here: How I Make $10,000 Monthly | AI Influencer Management How I Earned $7000+ in 15 Days | AI Influencer Business Update These earlier posts cover a lot of the backstory, so feel free to explore them before diving into this one. So if you're ready, here is the full story: \---- The idea of creating an AI influencer was one of those “what if” moments that wouldn’t leave my mind. At first, it sounded futuristic—even a bit too ambitious. It all started when I stumbled upon an AI influencer on Instagram with the handle AnnaMaes2000. Her content blew me away—the quality, the detail, and just how real everything looked. I was instantly hooked and ended up going through every post, just trying to figure out how she was pulling this off. That’s when I knew I had to learn how this was done. The next step? YouTube. I dived into videos on Stable Diffusion, soaking up everything I could about creating AI-generated images. Those tutorials taught me the basics and got me up to speed. Then, I created my first AI influencer, let's call her Mel for now. Right after that, to complete the storyline and boost engagement, I introduced Mel's “mother,” Jess. Adding Jess gave the whole project depth and a narrative that drew people in, creating a unique family dynamic that instantly elevated traffic and interest. After thousands of bad photos, hundreds of deleted posts, and months of trial and error, you can now see the quality that defines my current accounts. Here’s a rundown of the tools and checkpoints I’ve used from day one, in order: Fooocus on RunDiffusion — Juggernaut V8 Fooocus on RunDiffusion — Juggernaut V9 Fooocus on PC (locally) — Juggernaut V9 Fooocus on PC (locally) —Lyuyang Mix + Juggernaut V9 Flux on PC (couple of photos only since it's so slow even on RTX 4090) Flux on Fal.ai. \---- There’s no magic Instagram hack that guarantees success, despite what everyone thinks and keeps asking me. Quality content, consistent uploads, and solid craftsmanship are what actually help your photos hit trends and show up on the Explore page. Unlike 95% of low-quality AI accounts out there, I don’t rely on faceswap videos, spam Reels, or go around liking comments on other accounts. My approach is fully organic, focused solely on creating my own unique content. By following Instagram's guidelines to the letter, I've managed to direct some of Mel and Jess' fans over to Patreon and Fanvue. There, for a small subscription fee, fans can access exclusive lingerie content. For those looking for more, higher-tier subscriptions give access to even more premium content. Some possible questions and their answers: No, you can't share hardcore NSFW content on Patreon. You can do that on Fanvue. Yes, you can create AI creators on Fanvue — OnlyFans doesn't allow it. Yes, you can use your own ID to get KYC. Yes, we're telling both Mel and Jess is (or use) AI to generate content. And yes, some people leave and some people still have fun with chatting, having a good time and get perfect content for their needs. And yes, we have a chatter team to work on these accounts. \---- This journey wasn’t all smooth sailing. I faced unexpected roadblocks, like platform restrictions that limited certain types of content, and managing fan expectations was more challenging than anticipated. Staying within guidelines while keeping fans engaged required constant adaptation. These hurdles forced me to get creative, adjust my approach, and learn fast. Once I saw Mel and Jess gaining traction, I knew it was time to scale up. Expanding meant finding new ways to keep content fresh, creating deeper narratives, and considering how to bring even more followers into the fold. My focus turned to building a sustainable model that could grow without sacrificing quality or authenticity. If you’re thinking about diving into AI content creation, here’s my advice: patience, consistency, and a focus on quality are key. Don’t cut corners or rely on quick-fix hacks. Invest time in learning the right tools, creating engaging stories, and building an audience that values what you bring to the table. This approach took me from zero to six figures, and it’s what makes the journey worth it. \---- And finally, here’s the income breakdown that everyone’s curious about: Mel on Fanvue: $82,331.58 (Gross earnings because we have chatter cuts like 15%) Mel on Patreon: $50,865.98 (Net earnings) Jess on Fanvue: $89,068.26 (Gross earnings because we have chatter cuts like 15%) Jess on Patreon: $39,040.70 And thanks to Reddit and my old posts, I got a perfect investor like after 5 months, so this is a "payback" for that. Like I said, I'll answer every question in the comments — take care and let me know.

Looking for Investors in Dubai – High-Return AI Business Opportunity

We are launching an advanced AI automation business in Dubai, and we are looking for investors who want to be part of the future. Our AI technology is designed to take and make phone calls, revolutionizing customer service, sales, and business communication. This is an opportunity to invest in cutting-edge AI at an early stage, with fixed returns of 30% per year or 2% per month. To ensure security and transparency, all investments come with a legal agreement and post-dated cheques. AI-driven automation is the future, and businesses are actively looking for smarter, more cost-effective solutions. With the demand growing rapidly, this is your chance to be part of a high-potential venture in one of the fastest-growing tech sectors. If you’re interested in learning more, feel free to reach out. Let’s build the future together.

Looking for some legend keen to test an Ai chatbot and in return I give it for free for a whole year

Hey everyone! I’ve created an AI-powered chatbot designed to engage with website visitors, answer common questions, assist with lead generation, and even help provide context for sales calls by gathering customer insights. It’s built to not only save time but also to keep potential customers engaged with your business, making it an ideal tool for small to mid-sized companies looking to boost their online presence and improve sales conversion rates. I’m offering a free, year-long trial to a select group of business owners in exchange for constructive feedback. By using it, you'll get: Improved lead generation: The chatbot engages visitors and collects valuable info, making your sales calls more informed. Time-saving automation: Handles routine inquiries and FAQs, freeing up your team for other tasks. Valuable insights: Gather data on customer questions, preferences, and interests. If you’re interested or have questions, feel free to DM me! I'd love to hear your thoughts and see how we can make this tool as valuable as possible for businesses.

SaaS, Agency, or job?

Recently, I was fired, and since I have some savings, I decided it’s finally time to start my own venture. After a couple of weeks of research and trying to figure out what I should do, here are my thoughts and some questions at the end. I’d appreciate any feedback or opinions. It’s not that I expect to wake up a multimillionaire, but I see how people make money without working the typical 9-5. Some of the worst examples are on YouTube—those agency, OFM, dropshipping hustle bros. I know it’s naive to believe all of it because they’re just selling courses, but some of them do seem to have built impressive income streams. Anyway, let’s dive into two categories and compare. Agency (providing services, development, consultation): I’ll talk about AI automation because of my background in ML Engineering and Generative AI, but this could apply to any other agency niche. It seems like a good business idea for someone who knows generative AI and can do some impressive things with LLMs, agents, etc. I even started working on it—built a website—but I stopped when I couldn’t define exactly what services to offer. I could do heavy backend tasks with infrastructure, like real machine learning and AI with fine-tuning, but I couldn’t find any examples of agencies doing this. Almost 100% of them are doing simple automations with tools like Zapier or Make. When it comes to business owners, it’s really hard to find clients in general. After reading Reddit threads, articles, and watching videos, it seems like nearly everyone struggles with client acquisition. For a one-person agency offering more complex services like real ML, it would likely be even harder to find clients, compared to big outsourcing companies with sales teams. Even without focusing on the client challenge, which is obvious in any business, looking at what successful agency owners earn, it’s usually around $100k–$200k a year. I’m not talking about the high end, just regular people. I got this information from reading, and a simple example is from interviews with people who claim to make $10k/month. But many others in these communities struggle to even reach that point. It seems like this is a difficult target for most people. SaaS: This area seems more straightforward, and with my background, it feels like a good fit. However, from reading different sources, I’ve found stories like, “It took me six months to get my first client,” or “I worked on a simple SaaS for nine months and just reached my first $1k.” There are also warnings not to believe those who claim to make $10k/month easily, and many people report struggling to grow after getting their first 10 clients. So, it’s clear to me that even with good tech skills, you’re not going to make massive amounts of money overnight, which I understand. However, with so many people becoming startup founders and indie hackers, many seem to struggle despite thinking it’s the way to go. I know both paths can potentially skyrocket, but here’s where I need help: Am I wrong about agencies? Am I wrong about SaaS? The toughest question for me: I don’t want to go back to a 9-5 job, even if I could earn $300k a year. Even if my own business takes more time and I earn less in the first few years, I still believe it will be more profitable long term, and I will be happier. So, should I pursue an agency, SaaS, or a traditional job?

What’s the One Step Before Finishing a Project You’d Want to Automate?

As a knowledge worker, l have tons of notes and files. Even with so many productivity tools and AI, sometimes it just feels like more tools = more clutter. The more I use, the less I’m sure if I’m actually being "productive"  So, what are we mainly aiming for creating notes and file? to finish reports? Tracking progress...? I am thinking, If you could automate one step in getting things done, what would it be? For example: Auto-sorting and categorizing files Extracting key points from documents? Generating charts or visualizations Summarizing content or directly answering specific questions when I upload the file. Would love to hear what’s the hardest part about staying organized, and where do you think automation could actually help?🤔

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

Not sure if this is the right sub for it, but could you guys please roast my CV?

A brief about myself, I am an MSc from a top European University where I focused on NLP mostly hence most of my projects are just in NLP. I do have an experience of 3 years as a SE, did a 6 month stint as a consultant that I did not like, and finally got hired by a company I was doing my university project under to built their first products. The last 2 employments were part-time as I was also completing my masters at the same time. I am looking to apply in India mostly now. What do you think I can do differently, I just feel like something is missing here. Would be very thankful to anyone who can give me some constructive criticism on what to change here. Thanks again!

I built an instant no-code AI tool for training & explaining regression/classification models

Hey everyone! I recently developed a no-code SaaS tool aimed at simplifying and speeding up machine learning workflows, particularly for regression and classification tasks. I’d love to get feedback from the community here, especially from those who are experienced with machine learning and data science workflows. I’ll give a quick rundown of the tool's features, but I want to emphasize that I’m here more to learn about what would be valuable for you than to promote anything. The basic idea: This tool allows you to go from a raw dataset (CSV or tabular text format) to a trained ML model in minutes, rather than needing weeks or months of coding, hyperparameter tuning, and visualization work. It's designed to be intuitive for users without a strong coding background but still offers the depth that experienced users would need. Here’s how it works: Data Upload & Prep: Start by uploading a CSV or other tabular format dataset. The tool includes data prep steps that are designed to be simple but cover essentials (e.g., missing value handling, scaling). Model Training & Tuning: You can choose between regression and classification models, with automatic hyperparameter tuning happening in the background (under a time limit that you can set). It aims to find a good balance without needing direct input but does allow for manual adjustments if desired. Performance Analysis: It provides aggregated performance metrics like F1, recall, precision, R2, and others, alongside charts like AUROC, confusion matrices, and feature importance charts. I also included SHAP plots for deeper insight into feature contributions, as I know they’re becoming a standard for interpretability. Inference Options: The tool lets you do inference on either manually entered data or batch data (again, via CSV). The UI is lightweight and tries to make this as seamless as possible. What I’m hoping to get feedback on: Are there core features that feel like they’re missing? My goal was to provide a well-rounded suite for non-technical users but with enough depth for data scientists to find value. Does this kind of tool fit into your workflow? Or would something like this be more of a beginner tool? How valuable is explainability? I know SHAP is popular, but I’m curious if it actually makes it into the workflows of many data scientists here. Anything else you’d like to see in a tool like this? I know that there are a lot of no-code ML tools out there, so I’m not trying to reinvent the wheel—I just tried to make something a bit more straightforward while still incorporating some flexibility and depth. If you’ve used similar tools or have thoughts on what would make something like this actually useful in practice, I’d really appreciate any insights! Thank you so much for reading, and looking forward to any feedback you’re willing to share. Beta testers are welcome, currently forming a list.

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

GenAI_Agents

🌟 Support This Project: Your sponsorship fuels innovation in GenAI agent development. Become a sponsor to help maintain and expand this valuable resource! GenAI Agents: Comprehensive Repository for Development and Implementation 🚀 Welcome to one of the most extensive and dynamic collections of Generative AI (GenAI) agent tutorials and implementations available today. This repository serves as a comprehensive resource for learning, building, and sharing GenAI agents, ranging from simple conversational bots to complex, multi-agent systems. 📫 Stay Updated! 🚀Cutting-edgeUpdates 💡ExpertInsights 🎯Top 0.1%Content Join over 15,000 of AI enthusiasts getting unique cutting-edge insights and free tutorials! Plus, subscribers get exclusive early access and special 33% discounts to my book and the upcoming RAG Techniques course! Introduction Generative AI agents are at the forefront of artificial intelligence, revolutionizing the way we interact with and leverage AI technologies. This repository is designed to guide you through the development journey, from basic agent implementations to advanced, cutting-edge systems. 📚 Learn to Build Your First AI Agent Your First AI Agent: Simpler Than You Think This detailed blog post complements the repository by providing a complete A-Z walkthrough with in-depth explanations of core concepts, step-by-step implementation, and the theory behind AI agents. It's designed to be incredibly simple to follow while covering everything you need to know to build your first working agent from scratch. 💡 Plus: Subscribe to the newsletter for exclusive early access to tutorials and special discounts on upcoming courses and books! Our goal is to provide a valuable resource for everyone - from beginners taking their first steps in AI to seasoned practitioners pushing the boundaries of what's possible. By offering a range of examples from foundational to complex, we aim to facilitate learning, experimentation, and innovation in the rapidly evolving field of GenAI agents. Furthermore, this repository serves as a platform for showcasing innovative agent creations. Whether you've developed a novel agent architecture or found an innovative application for existing techniques, we encourage you to share your work with the community. Related Projects 📚 Dive into my comprehensive guide on RAG techniques to learn about integrating external knowledge into AI systems, enhancing their capabilities with up-to-date and relevant information retrieval. 🖋️ Explore my Prompt Engineering Techniques guide for an extensive collection of prompting strategies, from fundamental concepts to advanced methods, improving your ability to communicate effectively with AI language models. A Community-Driven Knowledge Hub This repository grows stronger with your contributions! Join our vibrant Discord community — the central hub for shaping and advancing this project together 🤝 GenAI Agents Discord Community Whether you're a novice eager to learn or an expert ready to share your knowledge, your insights can shape the future of GenAI agents. Join us to propose ideas, get feedback, and collaborate on innovative implementations. For contribution guidelines, please refer to our CONTRIBUTING.md file. Let's advance GenAI agent technology together! 🔗 For discussions on GenAI, agents, or to explore knowledge-sharing opportunities, feel free to connect on LinkedIn. Key Features 🎓 Learn to build GenAI agents from beginner to advanced levels 🧠 Explore a wide range of agent architectures and applications 📚 Step-by-step tutorials and comprehensive documentation 🛠️ Practical, ready-to-use agent implementations 🌟 Regular updates with the latest advancements in GenAI 🤝 Share your own agent creations with the community GenAI Agent Implementations Explore our extensive list of GenAI agent implementations, sorted by categories: 🌱 Beginner-Friendly Agents Simple Conversational Agent LangChain PydanticAI Overview 🔎 A context-aware conversational AI maintains information across interactions, enabling more natural dialogues. Implementation 🛠️ Integrates a language model, prompt template, and history manager to generate contextual responses and track conversation sessions. Simple Question Answering Agent Overview 🔎 Answering (QA) agent using LangChain and OpenAI's language model understands user queries and provides relevant, concise answers. Implementation 🛠️ Combines OpenAI's GPT model, a prompt template, and an LLMChain to process user questions and generate AI-driven responses in a streamlined manner. Simple Data Analysis Agent LangChain PydanticAI Overview 🔎 An AI-powered data analysis agent interprets and answers questions about datasets using natural language, combining language models with data manipulation tools for intuitive data exploration. Implementation 🛠️ Integrates a language model, data manipulation framework, and agent framework to process natural language queries and perform data analysis on a synthetic dataset, enabling accessible insights for non-technical users. 🔧 Framework Tutorial: LangGraph Introduction to LangGraph: Building Modular AI Workflows Overview 🔎 This tutorial introduces LangGraph, a powerful framework for creating modular, graph-based AI workflows. Learn how to leverage LangGraph to build more complex and flexible AI agents that can handle multi-step processes efficiently. Implementation 🛠️ Step-by-step guide on using LangGraph to create a StateGraph workflow. The tutorial covers key concepts such as state management, node creation, and graph compilation. It demonstrates these principles by constructing a simple text analysis pipeline, serving as a foundation for more advanced agent architectures. Additional Resources 📚 Blog Post 🎓 Educational and Research Agents ATLAS: Academic Task and Learning Agent System Overview 🔎 ATLAS demonstrates how to build an intelligent multi-agent system that transforms academic support through AI-powered assistance. The system leverages LangGraph's workflow framework to coordinate multiple specialized agents that provide personalized academic planning, note-taking, and advisory support. Implementation 🛠️ Implements a state-managed multi-agent architecture using four specialized agents (Coordinator, Planner, Notewriter, and Advisor) working in concert through LangGraph's workflow framework. The system features sophisticated workflows for profile analysis and academic support, with continuous adaptation based on student performance and feedback. Additional Resources 📚 YouTube Explanation Blog Post Scientific Paper Agent - Literature Review Overview 🔎 An intelligent research assistant that helps users navigate, understand, and analyze scientific literature through an orchestrated workflow. The system combines academic APIs with sophisticated paper processing techniques to automate literature review tasks, enabling researchers to efficiently extract insights from academic papers while maintaining research rigor and quality control. Implementation 🛠️ Leverages LangGraph to create a five-node workflow system including decision making, planning, tool execution, and quality validation nodes. The system integrates the CORE API for paper access, PDFplumber for document processing, and advanced language models for analysis. Key features include a retry mechanism for robust paper downloads, structured data handling through Pydantic models, and quality-focused improvement cycles with human-in-the-loop validation options. Additional Resources 📚 YouTube Explanation Blog Post Chiron - A Feynman-Enhanced Learning Agent Overview 🔎 An adaptive learning agent that guides users through educational content using a structured checkpoint system and Feynman-style teaching. The system processes learning materials (either user-provided or web-retrieved), verifies understanding through interactive checkpoints, and provides simplified explanations when needed, creating a personalized learning experience that mimics one-on-one tutoring. Implementation 🛠️ Uses LangGraph to orchestrate a learning workflow that includes checkpoint definition, context building, understanding verification, and Feynman teaching nodes. The system integrates web search for dynamic content retrieval, employs semantic chunking for context processing, and manages embeddings for relevant information retrieval. Key features include a 70% understanding threshold for progression, interactive human-in-the-loop validation, and structured output through Pydantic models for consistent data handling. Additional Resources 📚 YouTube Explanation 💼 Business and Professional Agents Customer Support Agent (LangGraph) Overview 🔎 An intelligent customer support agent using LangGraph categorizes queries, analyzes sentiment, and provides appropriate responses or escalates issues. Implementation 🛠️ Utilizes LangGraph to create a workflow combining state management, query categorization, sentiment analysis, and response generation. Essay Grading Agent (LangGraph) Overview 🔎 An automated essay grading system using LangGraph and an LLM model evaluates essays based on relevance, grammar, structure, and depth of analysis. Implementation 🛠️ Utilizes a state graph to define the grading workflow, incorporating separate grading functions for each criterion. Travel Planning Agent (LangGraph) Overview 🔎 A Travel Planner using LangGraph demonstrates how to build a stateful, multi-step conversational AI application that collects user input and generates personalized travel itineraries. Implementation 🛠️ Utilizes StateGraph to define the application flow, incorporates custom PlannerState for process management. GenAI Career Assistant Agent Overview 🔎 The GenAI Career Assistant demonstrates how to create a multi-agent system that provides personalized guidance for careers in Generative AI. Using LangGraph and Gemini LLM, the system delivers customized learning paths, resume assistance, interview preparation, and job search support. Implementation 🛠️ Leverages a multi-agent architecture using LangGraph to coordinate specialized agents (Learning, Resume, Interview, Job Search) through TypedDict-based state management. The system employs sophisticated query categorization and routing while integrating with external tools like DuckDuckGo for job searches and dynamic content generation. Additional Resources 📚 YouTube Explanation Project Manager Assistant Agent Overview 🔎 An AI agent designed to assist in project management tasks by automating the process of creating actionable tasks from project descriptions, identifying dependencies, scheduling work, and assigning tasks to team members based on expertise. The system includes risk assessment and self-reflection capabilities to optimize project plans through multiple iterations, aiming to minimize overall project risk. Implementation 🛠️ Leverages LangGraph to orchestrate a workflow of specialized nodes including task generation, dependency mapping, scheduling, allocation, and risk assessment. Each node uses GPT-4o-mini for structured outputs following Pydantic models. The system implements a feedback loop for self-improvement, where risk scores trigger reflection cycles that generate insights to optimize the project plan. Visualization tools display Gantt charts of the generated schedules across iterations. Additional Resources 📚 YouTube Explanation Contract Analysis Assistant (ClauseAI) Overview 🔎 ClauseAI demonstrates how to build an AI-powered contract analysis system using a multi-agent approach. The system employs specialized AI agents for different aspects of contract review, from clause analysis to compliance checking, and leverages LangGraph for workflow orchestration and Pinecone for efficient clause retrieval and comparison. Implementation 🛠️ Implements a sophisticated state-based workflow using LangGraph to coordinate multiple AI agents through contract analysis stages. The system features Pydantic models for data validation, vector storage with Pinecone for clause comparison, and LLM-based analysis for generating comprehensive contract reports. The implementation includes parallel processing capabilities and customizable report generation based on user requirements. Additional Resources 📚 YouTube Explanation E2E Testing Agent Overview 🔎 The E2E Testing Agent demonstrates how to build an AI-powered system that converts natural language test instructions into executable end-to-end web tests. Using LangGraph for workflow orchestration and Playwright for browser automation, the system enables users to specify test cases in plain English while handling the complexity of test generation and execution. Implementation 🛠️ Implements a structured workflow using LangGraph to coordinate test generation, validation, and execution. The system features TypedDict state management, integration with Playwright for browser automation, and LLM-based code generation for converting natural language instructions into executable test scripts. The implementation includes DOM state analysis, error handling, and comprehensive test reporting. Additional Resources 📚 YouTube Explanation 🎨 Creative and Content Generation Agents GIF Animation Generator Agent (LangGraph) Overview 🔎 A GIF animation generator that integrates LangGraph for workflow management, GPT-4 for text generation, and DALL-E for image creation, producing custom animations from user prompts. Implementation 🛠️ Utilizes LangGraph to orchestrate a workflow that generates character descriptions, plots, and image prompts using GPT-4, creates images with DALL-E 3, and assembles them into GIFs using PIL. Employs asynchronous programming for efficient parallel processing. TTS Poem Generator Agent (LangGraph) Overview 🔎 An advanced text-to-speech (TTS) agent using LangGraph and OpenAI's APIs classifies input text, processes it based on content type, and generates corresponding speech output. Implementation 🛠️ Utilizes LangGraph to orchestrate a workflow that classifies input text using GPT models, applies content-specific processing, and converts the processed text to speech using OpenAI's TTS API. The system adapts its output based on the identified content type (general, poem, news, or joke). Music Compositor Agent (LangGraph) Overview 🔎 An AI Music Compositor using LangGraph and OpenAI's language models generates custom musical compositions based on user input. The system processes the input through specialized components, each contributing to the final musical piece, which is then converted to a playable MIDI file. Implementation 🛠️ LangGraph orchestrates a workflow that transforms user input into a musical composition, using ChatOpenAI (GPT-4) to generate melody, harmony, and rhythm, which are then style-adapted. The final AI-generated composition is converted to a MIDI file using music21 and can be played back using pygame. Content Intelligence: Multi-Platform Content Generation Agent Overview 🔎 Content Intelligence demonstrates how to build an advanced content generation system that transforms input text into platform-optimized content across multiple social media channels. The system employs LangGraph for workflow orchestration to analyze content, conduct research, and generate tailored content while maintaining brand consistency across different platforms. Implementation 🛠️ Implements a sophisticated workflow using LangGraph to coordinate multiple specialized nodes (Summary, Research, Platform-Specific) through the content generation process. The system features TypedDict and Pydantic models for state management, integration with Tavily Search for research enhancement, and platform-specific content generation using GPT-4. The implementation includes parallel processing for multiple platforms and customizable content templates. Additional Resources 📚 YouTube Explanation Business Meme Generator Using LangGraph and Memegen.link Overview 🔎 The Business Meme Generator demonstrates how to create an AI-powered system that generates contextually relevant memes based on company website analysis. Using LangGraph for workflow orchestration, the system combines Groq's Llama model for text analysis and the Memegen.link API to automatically produce brand-aligned memes for digital marketing. Implementation 🛠️ Implements a state-managed workflow using LangGraph to coordinate website content analysis, meme concept generation, and image creation. The system features Pydantic models for data validation, asynchronous processing with aiohttp, and integration with external APIs (Groq, Memegen.link) to create a complete meme generation pipeline with customizable templates. Additional Resources 📚 YouTube Explanation Murder Mystery Game with LLM Agents Overview 🔎 A text-based detective game that utilizes autonomous LLM agents as interactive characters in a procedurally generated murder mystery. Drawing inspiration from the UNBOUNDED paper, the system creates unique scenarios each time, with players taking on the role of Sherlock Holmes to solve the case through character interviews and deductive reasoning. Implementation 🛠️ Leverages two LangGraph workflows - a main game loop for story/character generation and game progression, and a conversation sub-graph for character interactions. The system uses a combination of LLM-powered narrative generation, character AI, and structured game mechanics to create an immersive investigative experience with replayable storylines. Additional Resources 📚 YouTube Explanation 📊 Analysis and Information Processing Agents Memory-Enhanced Conversational Agent Overview 🔎 A memory-enhanced conversational AI agent incorporates short-term and long-term memory systems to maintain context within conversations and across multiple sessions, improving interaction quality and personalization. Implementation 🛠️ Integrates a language model with separate short-term and long-term memory stores, utilizes a prompt template incorporating both memory types, and employs a memory manager for storage and retrieval. The system includes an interaction loop that updates and utilizes memories for each response. Multi-Agent Collaboration System Overview 🔎 A multi-agent collaboration system combining historical research with data analysis, leveraging large language models to simulate specialized agents working together to answer complex historical questions. Implementation 🛠️ Utilizes a base Agent class to create specialized HistoryResearchAgent and DataAnalysisAgent, orchestrated by a HistoryDataCollaborationSystem. The system follows a five-step process: historical context provision, data needs identification, historical data provision, data analysis, and final synthesis. Self-Improving Agent Overview 🔎 A Self-Improving Agent using LangChain engages in conversations, learns from interactions, and continuously improves its performance over time through reflection and adaptation. Implementation 🛠️ Integrates a language model with chat history management, response generation, and a reflection mechanism. The system employs a learning system that incorporates insights from reflection to enhance future performance, creating a continuous improvement loop. Task-Oriented Agent Overview 🔎 A language model application using LangChain that summarizes text and translates the summary to Spanish, combining custom functions, structured tools, and an agent for efficient text processing. Implementation 🛠️ Utilizes custom functions for summarization and translation, wrapped as structured tools. Employs a prompt template to guide the agent, which orchestrates the use of tools. An agent executor manages the process, taking input text and producing both an English summary and its Spanish translation. Internet Search and Summarize Agent Overview 🔎 An intelligent web research assistant that combines web search capabilities with AI-powered summarization, automating the process of gathering information from the internet and distilling it into concise, relevant summaries. Implementation 🛠️ Integrates a web search module using DuckDuckGo's API, a result parser, and a text summarization engine leveraging OpenAI's language models. The system performs site-specific or general searches, extracts relevant content, generates concise summaries, and compiles attributed results for efficient information retrieval and synthesis. Multi agent research team - Autogen Overview 🔎 This technique explores a multi-agent system for collaborative research using the AutoGen library. It employs agents to solve tasks collaboratively, focusing on efficient execution and quality assurance. The system enhances research by distributing tasks among specialized agents. Implementation 🛠️ Agents are configured with specific roles using the GPT-4 model, including admin, developer, planner, executor, and quality assurance. Interaction management ensures orderly communication with defined transitions. Task execution involves collaborative planning, coding, execution, and quality checking, demonstrating a scalable framework for various domains. Additional Resources 📚 comprehensive solution with UI Blogpost Sales Call Analyzer Overview 🔎 An intelligent system that automates the analysis of sales call recordings by combining audio transcription with advanced natural language processing. The analyzer transcribes audio using OpenAI's Whisper, processes the text using NLP techniques, and generates comprehensive reports including sentiment analysis, key phrases, pain points, and actionable recommendations to improve sales performance. Implementation 🛠️ Utilizes multiple components in a structured workflow: OpenAI Whisper for audio transcription, CrewAI for task automation and agent management, and LangChain for orchestrating the analysis pipeline. The system processes audio through a series of steps from transcription to detailed analysis, leveraging custom agents and tasks to generate structured JSON reports containing insights about customer sentiment, sales opportunities, and recommended improvements. Additional Resources 📚 YouTube Explanation Weather Emergency & Response System Overview 🔎 A comprehensive system demonstrating two agent graph implementations for weather emergency response: a real-time graph processing live weather data, and a hybrid graph combining real and simulated data for testing high-severity scenarios. The system handles complete workflow from data gathering through emergency plan generation, with automated notifications and human verification steps. Implementation 🛠️ Utilizes LangGraph for orchestrating complex workflows with state management, integrating OpenWeatherMap API for real-time data, and Gemini for analysis and response generation. The system incorporates email notifications, social media monitoring simulation, and severity-based routing with configurable human verification for low/medium severity events. Additional Resources 📚 YouTube Explanation Self-Healing Codebase System Overview 🔎 An intelligent system that automatically detects, diagnoses, and fixes runtime code errors using LangGraph workflow orchestration and ChromaDB vector storage. The system maintains a memory of encountered bugs and their fixes through vector embeddings, enabling pattern recognition for similar errors across the codebase. Implementation 🛠️ Utilizes a state-based graph workflow that processes function definitions and runtime arguments through specialized nodes for error detection, code analysis, and fix generation. Incorporates ChromaDB for vector-based storage of bug patterns and fixes, with automated search and retrieval capabilities for similar error patterns, while maintaining code execution safety through structured validation steps. Additional Resources 📚 YouTube Explanation DataScribe: AI-Powered Schema Explorer Overview 🔎 An intelligent agent system that enables intuitive exploration and querying of relational databases through natural language interactions. The system utilizes a fleet of specialized agents, coordinated by a stateful Supervisor, to handle schema discovery, query planning, and data analysis tasks while maintaining contextual understanding through vector-based relationship graphs. Implementation 🛠️ Leverages LangGraph for orchestrating a multi-agent workflow including discovery, inference, and planning agents, with NetworkX for relationship graph visualization and management. The system incorporates dynamic state management through TypedDict classes, maintains database context between sessions using a db_graph attribute, and includes safety measures to prevent unauthorized database modifications. Memory-Enhanced Email Agent (LangGraph & LangMem) Overview 🔎 An intelligent email assistant that combines three types of memory (semantic, episodic, and procedural) to create a system that improves over time. The agent can triage incoming emails, draft contextually appropriate responses using stored knowledge, and enhance its performance based on user feedback. Implementation 🛠️ Leverages LangGraph for workflow orchestration and LangMem for sophisticated memory management across multiple memory types. The system implements a triage workflow with memory-enhanced decision making, specialized tools for email composition and calendar management, and a self-improvement mechanism that updates its own prompts based on feedback and past performance. Additional Resources 📚 Blog Post 📰 News and Information Agents News TL;DR using LangGraph Overview 🔎 A news summarization system that generates concise TL;DR summaries of current events based on user queries. The system leverages large language models for decision making and summarization while integrating with news APIs to access up-to-date content, allowing users to quickly catch up on topics of interest through generated bullet-point summaries. Implementation 🛠️ Utilizes LangGraph to orchestrate a workflow combining multiple components: GPT-4o-mini for generating search terms and article summaries, NewsAPI for retrieving article metadata, BeautifulSoup for web scraping article content, and Asyncio for concurrent processing. The system follows a structured pipeline from query processing through article selection and summarization, managing the flow between components to produce relevant TL;DRs of current news articles. Additional Resources 📚 YouTube Explanation Blog Post AInsight: AI/ML Weekly News Reporter Overview 🔎 AInsight demonstrates how to build an intelligent news aggregation and summarization system using a multi-agent architecture. The system employs three specialized agents (NewsSearcher, Summarizer, Publisher) to automatically collect, process and summarize AI/ML news for general audiences through LangGraph-based workflow orchestration. Implementation 🛠️ Implements a state-managed multi-agent system using LangGraph to coordinate the news collection (Tavily API), technical content summarization (GPT-4), and report generation processes. The system features modular architecture with TypedDict-based state management, external API integration, and markdown report generation with customizable templates. Additional Resources 📚 YouTube Explanation Journalism-Focused AI Assistant Overview 🔎 A specialized AI assistant that helps journalists tackle modern journalistic challenges like misinformation, bias, and information overload. The system integrates fact-checking, tone analysis, summarization, and grammar review tools to enhance the accuracy and efficiency of journalistic work while maintaining ethical reporting standards. Implementation 🛠️ Leverages LangGraph to orchestrate a workflow of specialized components including language models for analysis and generation, web search integration via DuckDuckGo's API, document parsing tools like PyMuPDFLoader and WebBaseLoader, text splitting with RecursiveCharacterTextSplitter, and structured JSON outputs. Each component works together through a unified workflow to analyze content, verify facts, detect bias, extract quotes, and generate comprehensive reports. Blog Writer (Open AI Swarm) Overview 🔎 A multi-agent system for collaborative blog post creation using OpenAI's Swarm package. It leverages specialized agents to perform research, planning, writing, and editing tasks efficiently. Implementation 🛠️ Utilizes OpenAI's Swarm Package to manage agent interactions. Includes an admin, researcher, planner, writer, and editor, each with specific roles. The system follows a structured workflow: topic setting, outlining, research, drafting, and editing. This approach enhances content creation through task distribution, specialization, and collaborative problem-solving. Additional Resources 📚 Swarm Repo Podcast Internet Search and Generate Agent 🎙️ Overview 🔎 A two step agent that first searches the internet for a given topic and then generates a podcast on the topic found. The search step uses a search agent and search function to find the most relevant information. The second step uses a podcast generation agent and generation function to create a podcast on the topic found. Implementation 🛠️ Utilizes LangGraph to orchestrate a two-step workflow. The first step involves a search agent and function to gather information from the internet. The second step uses a podcast generation agent and function to create a podcast based on the gathered information. 🛍️ Shopping and Product Analysis Agents ShopGenie - Redefining Online Shopping Customer Experience Overview 🔎 An AI-powered shopping assistant that helps customers make informed purchasing decisions even without domain expertise. The system analyzes product information from multiple sources, compares specifications and reviews, identifies the best option based on user needs, and delivers recommendations through email with supporting video reviews, creating a comprehensive shopping experience. Implementation 🛠️ Uses LangGraph to orchestrate a workflow combining Tavily for web search, Llama-3.1-70B for structured data analysis and product comparison, and YouTube API for review video retrieval. The system processes search results through multiple nodes including schema mapping, product comparison, review identification, and email generation. Key features include structured Pydantic models for consistent data handling, retry mechanisms for robust API interactions, and email delivery through SMTP for sharing recommendations. Additional Resources 📚 YouTube Explanation Car Buyer AI Agent Overview 🔎 The Smart Product Buyer AI Agent demonstrates how to build an intelligent system that assists users in making informed purchasing decisions. Using LangGraph and LLM-based intelligence, the system processes user requirements, scrapes product listings from websites like AutoTrader, and provides detailed analysis and recommendations for car purchases. Implementation 🛠️ Implements a state-based workflow using LangGraph to coordinate user interaction, web scraping, and decision support. The system features TypedDict state management, async web scraping with Playwright, and integrates with external APIs for comprehensive product analysis. The implementation includes a Gradio interface for real-time chat interaction and modular scraper architecture for easy extension to additional product categories. Additional Resources 📚 YouTube Explanation 🎯 Task Management and Productivity Agents Taskifier - Intelligent Task Allocation & Management Overview 🔎 An intelligent task management system that analyzes user work styles and creates personalized task breakdown strategies, born from the observation that procrastination often stems from task ambiguity among students and early-career professionals. The system evaluates historical work patterns, gathers relevant task information through web search, and generates customized step-by-step approaches to optimize productivity and reduce workflow paralysis. Implementation 🛠️ Leverages LangGraph for orchestrating a multi-step workflow including work style analysis, information gathering via Tavily API, and customized plan generation. The system maintains state through the process, integrating historical work pattern data with fresh task research to output detailed, personalized task execution plans aligned with the user's natural working style. Additional Resources 📚 YouTube Explanation Grocery Management Agents System Overview 🔎 A multi-agent system built with CrewAI that automates grocery management tasks including receipt interpretation, expiration date tracking, inventory management, and recipe recommendations. The system uses specialized agents to extract data from receipts, estimate product shelf life, track consumption, and suggest recipes to minimize food waste. Implementation 🛠️ Implements four specialized agents using CrewAI - a Receipt Interpreter that extracts item details from receipts, an Expiration Date Estimator that determines shelf life using online sources, a Grocery Tracker that maintains inventory based on consumption, and a Recipe Recommender that suggests meals using available ingredients. Each agent has specific tools and tasks orchestrated through a crew workflow. Additional Resources 📚 YouTube Explanation 🔍 Quality Assurance and Testing Agents LangGraph-Based Systems Inspector Overview 🔎 A comprehensive testing and validation tool for LangGraph-based applications that automatically analyzes system architecture, generates test cases, and identifies potential vulnerabilities through multi-agent inspection. The inspector employs specialized AI testers to evaluate different aspects of the system, from basic functionality to security concerns and edge cases. Implementation 🛠️ Integrates LangGraph for workflow orchestration, multiple LLM-powered testing agents, and a structured evaluation pipeline that includes static analysis, test case generation, and results verification. The system uses Pydantic for data validation, NetworkX for graph representation, and implements a modular architecture that allows for parallel test execution and comprehensive result analysis. Additional Resources 📚 YouTube Explanation Blog Post EU Green Deal FAQ Bot Overview 🔎 The EU Green Deal FAQ Bot demonstrates how to build a RAG-based AI agent that helps businesses understand EU green deal policies. The system processes complex regulatory documents into manageable chunks and provides instant, accurate answers to common questions about environmental compliance, emissions reporting, and waste management requirements. Implementation 🛠️ Implements a sophisticated RAG pipeline using FAISS vectorstore for document storage, semantic chunking for preprocessing, and multiple specialized agents (Retriever, Summarizer, Evaluator) for query processing. The system features query rephrasing for improved accuracy, cross-reference with gold Q&A datasets for answer validation, and comprehensive evaluation metrics to ensure response quality and relevance. Additional Resources 📚 YouTube Explanation Systematic Review Automation System + Paper Draft Creation Overview 🔎 A comprehensive system for automating academic systematic reviews using a directed graph architecture and LangChain components. The system generates complete, publication-ready systematic review papers, automatically processing everything from literature search through final draft generation with multiple revision cycles. Implementation 🛠️ Utilizes a state-based graph workflow that handles paper search and selection (up to 3 papers), PDF processing, and generates a complete academic paper with all standard sections (abstract, introduction, methods, results, conclusions, references). The system incorporates multiple revision cycles with automated critique and improvement phases, all orchestrated through LangGraph state management. Additional Resources 📚 YouTube Explanation 🌟 Special Advanced Technique 🌟 Sophisticated Controllable Agent for Complex RAG Tasks 🤖 Overview 🔎 An advanced RAG solution designed to tackle complex questions that simple semantic similarity-based retrieval cannot solve. This approach uses a sophisticated deterministic graph as the "brain" 🧠 of a highly controllable autonomous agent, capable of answering non-trivial questions from your own data. Implementation 🛠️ • Implement a multi-step process involving question anonymization, high-level planning, task breakdown, adaptive information retrieval and question answering, continuous re-planning, and rigorous answer verification to ensure grounded and accurate responses. Getting Started To begin exploring and building GenAI agents: Clone this repository: Navigate to the technique you're interested in: Follow the detailed implementation guide in each technique's notebook. Contributing We welcome contributions from the community! If you have a new technique or improvement to suggest: Fork the repository Create your feature branch: git checkout -b feature/AmazingFeature Commit your changes: git commit -m 'Add some AmazingFeature' Push to the branch: git push origin feature/AmazingFeature Open a pull request Contributors License This project is licensed under a custom non-commercial license - see the LICENSE file for details. ⭐️ If you find this repository helpful, please consider giving it a star! Keywords: GenAI, Generative AI, Agents, NLP, AI, Machine Learning, Natural Language Processing, LLM, Conversational AI, Task-Oriented AI

Prompt_Engineering

🌟 Support This Project: Your sponsorship fuels innovation in prompt engineering development. Become a sponsor to help maintain and expand this valuable resource! Prompt Engineering Techniques: Comprehensive Repository for Development and Implementation 🖋️ Welcome to one of the most extensive and dynamic collections of Prompt Engineering tutorials and implementations available today. This repository serves as a comprehensive resource for learning, building, and sharing prompt engineering techniques, ranging from basic concepts to advanced strategies for leveraging large language models. 📫 Stay Updated! 🚀Cutting-edgeUpdates 💡ExpertInsights 🎯Top 0.1%Content Join over 15,000 of AI enthusiasts getting unique cutting-edge insights and free tutorials! Plus, subscribers get exclusive early access and special discounts to our upcoming RAG Techniques course! Introduction Prompt engineering is at the forefront of artificial intelligence, revolutionizing the way we interact with and leverage AI technologies. This repository is designed to guide you through the development journey, from basic prompt structures to advanced, cutting-edge techniques. Our goal is to provide a valuable resource for everyone - from beginners taking their first steps in AI to seasoned practitioners pushing the boundaries of what's possible. By offering a range of examples from foundational to complex, we aim to facilitate learning, experimentation, and innovation in the rapidly evolving field of prompt engineering. Furthermore, this repository serves as a platform for showcasing innovative prompt engineering techniques. Whether you've developed a novel approach or found an innovative application for existing techniques, we encourage you to share your work with the community. 📖 Get the Fully Explained Version of This Repo This repository contains 22 hands-on Jupyter Notebook tutorials covering key prompt engineering techniques. If you want to go deeper with full explanations, intuitive insights, and structured exercises, check out the expanded version in book format: 📚 Prompt Engineering from Zero to Hero 📖 All 22 techniques from this repo, fully explained in depth 🧠 Step-by-step breakdowns of key concepts & best practices 🏋️ Hands-on exercises to sharpen your skills 🎯 Designed for learners who want a structured, guided approach 📄 Instant access to the PDF upon purchase 📱 Readable on any device – computer, tablet, or phone 💡 Subscribers to the DiamantAI newsletter receive an exclusive 33% (!) discount on the book. 👉 Get the full explained version here Related Projects 📚 Explore my comprehensive guide on RAG techniques to learn how to enhance AI systems with external knowledge retrieval, complementing language model capabilities with rich, up-to-date information. 🤖 Dive into my GenAI Agents Repository for a wide range of AI agent implementations and tutorials, from simple conversational bots to complex, multi-agent systems for various applications. A Community-Driven Knowledge Hub This repository grows stronger with your contributions! Join our vibrant Discord community — the central hub for shaping and advancing this project together 🤝 DiamantAI Discord Community Whether you're a novice eager to learn or an expert ready to share your knowledge, your insights can shape the future of prompt engineering. Join us to propose ideas, get feedback, and collaborate on innovative implementations. For contribution guidelines, please refer to our CONTRIBUTING.md file. Let's advance prompt engineering technology together! 🔗 For discussions on GenAI, or to explore knowledge-sharing opportunities, feel free to connect on LinkedIn. Key Features 🎓 Learn prompt engineering techniques from beginner to advanced levels 🧠 Explore a wide range of prompt structures and applications 📚 Step-by-step tutorials and comprehensive documentation 🛠️ Practical, ready-to-use prompt implementations 🌟 Regular updates with the latest advancements in prompt engineering 🤝 Share your own prompt engineering creations with the community Prompt Engineering Techniques Explore our extensive list of prompt engineering techniques, ranging from basic to advanced: 🌱 Fundamental Concepts Introduction to Prompt Engineering Overview 🔎 A comprehensive introduction to the fundamental concepts of prompt engineering in the context of AI and language models. Implementation 🛠️ Combines theoretical explanations with practical demonstrations, covering basic concepts, structured prompts, comparative analysis, and problem-solving applications. Basic Prompt Structures Overview 🔎 Explores two fundamental types of prompt structures: single-turn prompts and multi-turn prompts (conversations). Implementation 🛠️ Uses OpenAI's GPT model and LangChain to demonstrate single-turn and multi-turn prompts, prompt templates, and conversation chains. Prompt Templates and Variables Overview 🔎 Introduces creating and using prompt templates with variables, focusing on Python and the Jinja2 templating engine. Implementation 🛠️ Covers template creation, variable insertion, conditional content, list processing, and integration with the OpenAI API. 🔧 Core Techniques Zero-Shot Prompting Overview 🔎 Explores zero-shot prompting, allowing language models to perform tasks without specific examples or prior training. Implementation 🛠️ Demonstrates direct task specification, role-based prompting, format specification, and multi-step reasoning using OpenAI and LangChain. Few-Shot Learning and In-Context Learning Overview 🔎 Covers Few-Shot Learning and In-Context Learning techniques using OpenAI's GPT models and the LangChain library. Implementation 🛠️ Implements basic and advanced few-shot learning, in-context learning, and best practices for example selection and evaluation. Chain of Thought (CoT) Prompting Overview 🔎 Introduces Chain of Thought (CoT) prompting, encouraging AI models to break down complex problems into step-by-step reasoning processes. Implementation 🛠️ Covers basic and advanced CoT techniques, applying them to various problem-solving scenarios and comparing results with standard prompts. 🔍 Advanced Strategies Self-Consistency and Multiple Paths of Reasoning Overview 🔎 Explores techniques for generating diverse reasoning paths and aggregating results to improve AI-generated answers. Implementation 🛠️ Demonstrates designing diverse reasoning prompts, generating multiple responses, implementing aggregation methods, and applying self-consistency checks. Constrained and Guided Generation Overview 🔎 Focuses on techniques to set up constraints for model outputs and implement rule-based generation. Implementation 🛠️ Uses LangChain's PromptTemplate for structured prompts, implements constraints, and explores rule-based generation techniques. Role Prompting Overview 🔎 Explores assigning specific roles to AI models and crafting effective role descriptions. Implementation 🛠️ Demonstrates creating role-based prompts, assigning roles to AI models, and refining role descriptions for various scenarios. 🚀 Advanced Implementations Task Decomposition in Prompts Overview 🔎 Explores techniques for breaking down complex tasks and chaining subtasks in prompts. Implementation 🛠️ Covers problem analysis, subtask definition, targeted prompt engineering, sequential execution, and result synthesis. Prompt Chaining and Sequencing Overview 🔎 Demonstrates how to connect multiple prompts and build logical flows for complex AI-driven tasks. Implementation 🛠️ Explores basic prompt chaining, sequential prompting, dynamic prompt generation, and error handling within prompt chains. Instruction Engineering Overview 🔎 Focuses on crafting clear and effective instructions for language models, balancing specificity and generality. Implementation 🛠️ Covers creating and refining instructions, experimenting with different structures, and implementing iterative improvement based on model responses. 🎨 Optimization and Refinement Prompt Optimization Techniques Overview 🔎 Explores advanced techniques for optimizing prompts, focusing on A/B testing and iterative refinement. Implementation 🛠️ Demonstrates A/B testing of prompts, iterative refinement processes, and performance evaluation using relevant metrics. Handling Ambiguity and Improving Clarity Overview 🔎 Focuses on identifying and resolving ambiguous prompts and techniques for writing clearer prompts. Implementation 🛠️ Covers analyzing ambiguous prompts, implementing strategies to resolve ambiguity, and exploring techniques for writing clearer prompts. Prompt Length and Complexity Management Overview 🔎 Explores techniques for managing prompt length and complexity when working with large language models. Implementation 🛠️ Demonstrates techniques for balancing detail and conciseness, and strategies for handling long contexts including chunking, summarization, and iterative processing. 🛠️ Specialized Applications Negative Prompting and Avoiding Undesired Outputs Overview 🔎 Explores negative prompting and techniques for avoiding undesired outputs from large language models. Implementation 🛠️ Covers basic negative examples, explicit exclusions, constraint implementation using LangChain, and methods for evaluating and refining negative prompts. Prompt Formatting and Structure Overview 🔎 Explores various prompt formats and structural elements, demonstrating their impact on AI model responses. Implementation 🛠️ Demonstrates creating various prompt formats, incorporating structural elements, and comparing responses from different prompt structures. Prompts for Specific Tasks Overview 🔎 Explores the creation and use of prompts for specific tasks: text summarization, question-answering, code generation, and creative writing. Implementation 🛠️ Covers designing task-specific prompt templates, implementing them using LangChain, executing with sample inputs, and analyzing outputs for each task type. 🌍 Advanced Applications Multilingual and Cross-lingual Prompting Overview 🔎 Explores techniques for designing prompts that work effectively across multiple languages and for language translation tasks. Implementation 🛠️ Covers creating multilingual prompts, implementing language detection and adaptation, designing cross-lingual translation prompts, and handling various writing systems and scripts. Ethical Considerations in Prompt Engineering Overview 🔎 Explores the ethical dimensions of prompt engineering, focusing on avoiding biases and creating inclusive and fair prompts. Implementation 🛠️ Covers identifying biases in prompts, implementing strategies to create inclusive prompts, and methods to evaluate and improve the ethical quality of AI outputs. Prompt Security and Safety Overview 🔎 Focuses on preventing prompt injections and implementing content filters in prompts for safe and secure AI applications. Implementation 🛠️ Covers techniques for prompt injection prevention, content filtering implementation, and testing the effectiveness of security and safety measures. Evaluating Prompt Effectiveness Overview 🔎 Explores methods and techniques for evaluating the effectiveness of prompts in AI language models. Implementation 🛠️ Covers setting up evaluation metrics, implementing manual and automated evaluation techniques, and providing practical examples using OpenAI and LangChain. Getting Started To begin exploring and implementing prompt engineering techniques: Clone this repository: Navigate to the technique you're interested in: Follow the detailed implementation guide in each technique's notebook. Contributing We welcome contributions from the community! If you have a new technique or improvement to suggest: Fork the repository Create your feature branch: git checkout -b feature/AmazingFeature Commit your changes: git commit -m 'Add some AmazingFeature' Push to the branch: git push origin feature/AmazingFeature Open a pull request License This project is licensed under a custom non-commercial license - see the LICENSE file for details. ⭐️ If you find this repository helpful, please consider giving it a star! Keywords: Prompt Engineering, AI, Machine Learning, Natural Language Processing, LLM, Language Models, NLP, Conversational AI, Zero-Shot Learning, Few-Shot Learning, Chain of Thought

AI-Scalpel-Trading-Bot

AI-Scalpel-Trading-Bot Disclaimer This software is for educational purposes only. Do not risk money which you are afraid to lose. USE THE SOFTWARE AT YOUR OWN RISK. THE AUTHORS AND ALL AFFILIATES ASSUME NO RESPONSIBILITY FOR YOUR TRADING RESULTS. Always start by running a trading bot in Dry-run and do not engage money before you understand how it works and what profit/loss you should expect. This is an implementation of freqtrade where different machine learning implementations will be tested. Freqtrade is a free and open source crypto trading bot written in Python. It is designed to support all major exchanges and be controlled via Telegram. It contains backtesting, plotting and money management tools as well as strategy optimization by machine learning. !freqtrade Exchange marketplaces supported [X] Bittrex [X] Binance (*Note for binance users) [ ] 113 others to tests. (Some of them might not work) Documentation Documentation. Features [x] Based on Python 3.6+: For botting on any operating system - Windows, macOS and Linux. [x] Persistence: Persistence is achieved through sqlite. [x] Dry-run: Run the bot without playing money. [x] Backtesting: Run a simulation of your buy/sell strategy. [x] Strategy Optimization by machine learning: Use machine learning to optimize your buy/sell strategy parameters with real exchange data. [x] Edge position sizing Calculate your win rate, risk reward ratio, the best stoploss and adjust your position size before taking a position for each specific market. Learn more. [x] Whitelist crypto-currencies: Select which crypto-currency you want to trade or use dynamic whitelists. [x] Blacklist crypto-currencies: Select which crypto-currency you want to avoid. [x] Manageable via Telegram: Manage the bot with Telegram. [x] Display profit/loss in fiat: Display your profit/loss in 33 fiat. [x] Daily summary of profit/loss: Provide a daily summary of your profit/loss. [x] Performance status report: Provide a performance status of your current trades. Quick start Freqtrade provides a Linux/macOS script to install all dependencies and help you to configure the bot. Other installations. Basic Usage Bot commands Telegram RPC commands Telegram is not mandatory. However, this is a great way to control your bot. More details on our documentation /start: Starts the trader /stop: Stops the trader /status [table]: Lists all open trades /count: Displays number of open trades /profit: Lists cumulative profit from all finished trades /forcesell |all: Instantly sells the given trade (Ignoring minimum_roi). /performance: Show performance of each finished trade grouped by pair /balance: Show account balance per currency /daily : Shows profit or loss per day, over the last n days /help: Show help message /version: Show version Development branches The project is currently setup in two main branches: develop - This branch has often new features, but might also cause breaking changes. master - This branch contains the latest stable release. The bot 'should' be stable on this branch, and is generally well tested. feat/* - These are feature branches, which are being worked on heavily. Please don't use these unless you want to test a specific feature. A note on Binance For Binance, please add "BNB/" to your blacklist to avoid issues. Accounts having BNB accounts use this to pay for fees - if your first trade happens to be on BNB, further trades will consume this position and make the initial BNB order unsellable as the expected amount is not there anymore. Support Help / Slack For any questions not covered by the documentation or for further information about the bot, I encourage you to join freqtrade's slack channel. Click here to join Slack channel. Bugs / Issues If you discover a bug in the bot, please search their issue tracker first. If it hasn't been reported, please create a new issue and ensure you follow the template guide so that our team can assist you as quickly as possible. Feature Requests Have you a great idea to improve the bot you want to share? Please, first search if this feature was not already discussed. If it hasn't been requested, please create a new request and ensure you follow the template guide so that it does not get lost in the bug reports. Pull Requests Feel like the bot is missing a feature? Keep em pull requests coming! Please read the Contributing document to understand the requirements before sending pull-requests. Coding is not a neccessity to contribute - maybe start with improving our documentation? Issues labeled good first issue can be good first contributions, and will help get you familiar with the codebase. Note before starting any major new feature work, please open an issue describing what you are planning to do or talk to the team on Slack. This will ensure that interested parties can give valuable feedback on the feature, and let others know that you are working on it. Important: Always create your PR against the develop branch, not master. Requirements Uptodate clock The clock must be accurate, syncronized to a NTP server very frequently to avoid problems with communication to the exchanges. Min hardware required To run this bot we recommend you a cloud instance with a minimum of: Minimal (advised) system requirements: 2GB RAM, 1GB disk space, 2vCPU Software requirements Python 3.6.x pip git TA-Lib virtualenv (Recommended) Docker (Recommended)

Introduction_to_Machine_Learning

Machine Learning Course Welcome to the "Machine Learning" course of Department of Computer Engineering, Sharif University of Technology. You can access slides, Jupyter notebooks, and exercises. Please note that this content is a work in progress and will be updated throughout Fall 2024 semester. For course materials from previous semesters, please visit the Previous Semesters section. Class videos and additional resources can be found on the SharifML website (Persian language). Feel free to use this content, provided you properly cite both the course and this GitHub repository. For more details, see the Creative Commons BY license.

airspace-hugo

Airspace Hugo This theme is suitable for a wide variety of businesses, including marketing, photography, and development enterprises. 👀Demo | Page Speed (95%)🚀 🔑Key Features 📄 9+ Pre-Designed Pages 🌐 Multiple language support (Fr, En) 📊 Google Analytics support 🎨 CSS and JS bundle with Hugo Pipe 🎨 Bootstrap Based ⚙️ Netlify settings predefine 👥 Multiple authors available ✉️ Contact form support 🔄 GDPR consent support 🗺️ Google Maps support 🎉 Fun factors counter 🚀 Google Page Speed optimized 🌐 Open Graph meta tag 🐦 Twitter Card meta tag 📄 9+ Pre-Designed Pages 🏠 Home Page 📚 Blog Page 📝 Blog Single Page 📄 Project Page 🛠️ Services 💰 Pricing ❓ FAQ ℹ️ About Page 📞 Contact Page 🖥️Local development Or Check out Full Documentation. ⚙️Deployment and hosting Follow the steps. 🐞Reporting Issues We use GitHub Issues as the official bug tracker for the Airspace Template. Please Search existing issues. Someone may have already reported the same problem. If your problem or idea has not been addressed yet, feel free to open a new issue. 📱Submit Your Website To Our Showcase Are you using Airspace Hugo theme? Submit it to our showcase. Our showcase aims to demonstrate to the world what amazing websites people like you have created utilizing our Hugo themes and to show that Hugo has tremendous capabilities as a Static Site Generator. View all the websites powered by Airspace Hugo from here. Submit your Airspace Hugo powered website. 📄License Copyright &copy; Designed by Themefisher & Developed by Gethugothemes Code License: Released under the MIT license. Image license: The images are only for demonstration purposes. They have their licenses. We don't have permission to share those images. 🙏Special Thanks Bootstrap Jquery Ionicons Magnific Popup Shuffle Slick Slider Google Fonts All Contributors 👨‍💻Hire Us Besides developing unique, blazing-fast Hugo themes, we also provide customized services. We specialize in creating affordable, high-quality static websites based on Hugo. If you need to customize the theme or complete website development from scratch, you can hire us. Check Our Services 💎Premium Themes By Us | | | | |:---:|:---:|:---:| | Get 55+ Premium Hugo Themes Bundle | Bigspring | Navigator |

awesome-ai-in-finance

Awesome AI in Finance There are millions of trades made in the global financial market every day. Data grows very quickly and people are hard to understand. With the power of the latest artificial intelligence research, people analyze & trade automatically and intelligently. This list contains the research, tools and code that people use to beat the market. [中文资源] Contents LLMs Papers Courses & Books Strategies & Research Time Series Data Portfolio Management High Frequency Trading Event Drive Crypto Currencies Strategies Technical Analysis Lottery & Gamble Arbitrage Data Sources Research Tools Trading System TA Lib Exchange API Articles Others LLMs 🌟🌟 MarS - A Financial Market Simulation Engine Powered by Generative Foundation Model. 🌟🌟 Financial Statement Analysis with Large Language Models - GPT-4 can outperform professional financial analysts in predicting future earnings changes, generating useful narrative insights, and resulting in superior trading strategies with higher Sharpe ratios and alphas, thereby suggesting a potential central role for LLMs in financial decision-making. PIXIU - An open-source resource providing a financial large language model, a dataset with 136K instruction samples, and a comprehensive evaluation benchmark. FinGPT - Provides a playground for all people interested in LLMs and NLP in Finance. MACD + RSI + ADX Strategy (ChatGPT-powered) by TradeSmart - Asked ChatGPT on which indicators are the most popular for trading. We used all of the recommendations given. A ChatGPT trading algorithm delivered 500% returns in stock market. My breakdown on what this means for hedge funds and retail investors Use chatgpt to adjust strategy parameters Hands-on LLMs: Train and Deploy a Real-time Financial Advisor - Train and deploy a real-time financial advisor chatbot with Falcon 7B and CometLLM. ChatGPT Strategy by OctoBot - Use ChatGPT to determine which cryptocurrency to trade based on technical indicators. Papers The Theory of Speculation L. Bachelier, 1900 - The influences which determine the movements of the Stock Exchange are. Brownian Motion in the Stock Market Osborne, 1959 - The common-stock prices can be regarded as an ensemble of decisions in statistical equilibrium. An Investigation into the Use of Reinforcement Learning Techniques within the Algorithmic Trading Domain, 2015 A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem Reinforcement Learning for Trading, 1994 Dragon-Kings, Black Swans and the Prediction of Crises Didier Sornette - The power laws in the distributions of event sizes under a broad range of conditions in a large variety of systems. Financial Trading as a Game: A Deep Reinforcement Learning Approach - Deep reinforcement learning provides a framework toward end-to-end training of such trading agent. Machine Learning for Trading - With an appropriate choice of the reward function, reinforcement learning techniques can successfully handle the risk-averse case. Ten Financial Applications of Machine Learning, 2018 - Slides review few important financial ML applications. FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance, 2020 - Introduce a DRL library FinRL that facilitates beginners to expose themselves to quantitative finance and to develop their own stock trading strategies. Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy, 2020 - Propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. Courses & Books & Blogs 🌟 QuantResearch - Quantitative analysis, strategies and backtests https://letianzj.github.io/ NYU: Overview of Advanced Methods of Reinforcement Learning in Finance Udacity: Artificial Intelligence for Trading AI in Finance - Learn Fintech Online. Advanced-Deep-Trading - Experiments based on "Advances in financial machine learning" book. Advances in Financial Machine Learning - Using advanced ML solutions to overcome real-world investment problems. Build Financial Software with Generative AI - Book about how to build financial software hands-on using generative AI tools like ChatGPT and Copilot. Mastering Python for Finance - Sources codes for: Mastering Python for Finance, Second Edition. MLSys-NYU-2022 - Slides, scripts and materials for the Machine Learning in Finance course at NYU Tandon, 2022. Train and Deploy a Serverless API to predict crypto prices - In this tutorial you won't build an ML system that will make you rich. But you will master the MLOps frameworks and tools you need to build ML systems that, together with tons of experimentation, can take you there. Strategies & Research Time Series Data Price and Volume process with Technology Analysis Indices 🌟🌟 stockpredictionai - A complete process for predicting stock price movements. 🌟 Personae - Implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading. 🌟 Ensemble-Strategy - Deep Reinforcement Learning for Automated Stock Trading. FinRL - A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance. AutomatedStockTrading-DeepQ-Learning - Build a Deep Q-learning reinforcement agent model as automated trading robot. tfdeeprltrader - Trading environment(OpenAI Gym) + PPO(TensorForce). trading-gym - Trading agent to train with episode of short term trading itself. trading-rl - Deep Reinforcement Learning for Financial Trading using Price Trailing. deeprltrader - Trading environment(OpenAI Gym) + DDQN (Keras-RL). Quantitative-Trading - Papers and code implementing Quantitative-Trading. gym-trading - Environment for reinforcement-learning algorithmic trading models. zenbrain - A framework for machine-learning bots. DeepLearningNotes - Machine learning in quant analysis. stockmarketreinforcementlearning - Stock market trading OpenAI Gym environment with Deep Reinforcement Learning using Keras. Chaos Genius - ML powered analytics engine for outlier/anomaly detection and root cause analysis.. mlforecast - Scalable machine learning based time series forecasting. Portfolio Management Deep-Reinforcement-Stock-Trading - A light-weight deep reinforcement learning framework for portfolio management. qtrader - Reinforcement Learning for portfolio management. PGPortfolio - A Deep Reinforcement Learning framework for the financial portfolio management problem. DeepDow - Portfolio optimization with deep learning. skfolio - Python library for portfolio optimization built on top of scikit-learn. High Frequency Trading High-Frequency-Trading-Model-with-IB - A high-frequency trading model using Interactive Brokers API with pairs and mean-reversion. 🌟 SGX-Full-OrderBook-Tick-Data-Trading-Strategy - Solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data. HFTBitcoin - Analysis of High Frequency Trading on Bitcoin exchanges. Event Drive 🌟🌟 stockpredictionai - Complete process for predicting stock price movements. 🌟 trump2cash - A stock trading bot powered by Trump tweets. Crypto Currencies Strategies LSTM-Crypto-Price-Prediction - Predicting price trends in crypto markets using an LSTM-RNN for trading. tforcebtctrader - TensorForce Bitcoin trading bot. Tensorflow-NeuroEvolution-Trading-Bot - A population model that trade cyrpto and breed and mutate iteratively. gekkoga - Genetic algorithm for solving optimization of trading strategies using Gekko. GekkoANNStrategies - ANN trading strategies for the Gekko trading bot. gekko-neuralnet - Neural network strategy for Gekko. bitcoinprediction - Code for "Bitcoin Prediction" by Siraj Raval on YouTube. Technical Analysis quant-trading - Python quantitative trading strategies. Gekko-Bot-Resources - Gekko bot resources. gekkotools - Gekko strategies, tools etc. gekko RSIWR - Gekko RSIWR strategies. gekko HL - Calculate down peak and trade on. EthTradingAlgorithm - Ethereum trading algorithm using Python 3.5 and the library ZipLine. gekkotradingstuff - Awesome crypto currency trading platform. forex.analytics - Node.js native library performing technical analysis over an OHLC dataset with use of genetic algorithmv. BitcoinMACDStrategy - Bitcoin MACD crossover trading strategy backtest. crypto-signal - Automated crypto trading & technical analysis (TA) bot for Bittrex, Binance, GDAX, and more. Gekko-Strategies - Strategies to Gekko trading bot with backtests results and some useful tools. gekko-gannswing - Gann's Swing trade strategy for Gekko trade bot. Lottery & Gamble LotteryPredict - Use LSTM to predict lottery. Arbitrage ArbitrageBot - Arbitrage bot that currently works on bittrex & poloniex. r2 - Automatic arbitrage trading system powered by Node.js + TypeScript. cryptocurrency-arbitrage - A crypto currency arbitrage opportunity calculator. Over 800 currencies and 50 markets. bitcoin-arbitrage - Bitcoin arbitrage opportunity detector. blackbird - Long / short market-neutral strategy. Data Sources Traditional Markets 🌟 Quandl - Get millions of financial and economic dataset from hundreds of publishers via a single free API. yahoo-finance - Python module to get stock data from Yahoo! Finance. Tushare - Crawling historical data of Chinese stocks. Financial Data - Stock Market and Financial Data API. Crypto Currencies CryptoInscriber - A live crypto currency historical trade data blotter. Download live historical trade data from any crypto exchange. Gekko-Datasets - Gekko trading bot dataset dumps. Download and use history files in SQLite format. Research Tools Synthical - AI-powered collaborative environment for Research. 🌟🌟 TensorTrade - Trade efficiently with reinforcement learning. ML-Quant - Quant resources from ArXiv (sanity), SSRN, RePec, Journals, Podcasts, Videos, and Blogs. JAQS - An open source quant strategies research platform. pyfolio - Portfolio and risk analytics in Python. alphalens - Performance analysis of predictive (alpha) stock factors. empyrical - Common financial risk and performance metrics. Used by Zipline and pyfolio. zvt - Zero vector trader. Trading System For Back Test & Live trading Traditional Market System 🌟🌟🌟 OpenBB - AI-powered opensource research and analytics workspace. 🌟🌟 zipline - A python algorithmic trading library. 🌟 TradingView - Get real-time information and market insights. rqalpha - A extendable, replaceable Python algorithmic backtest & trading framework. backtrader - Python backtesting library for trading strategies. kungfu - Kungfu Master trading system. lean - Algorithmic trading engine built for easy strategy research, backtesting and live trading. Combine & Rebuild pylivetrader - Python live trade execution library with zipline interface. CoinMarketCapBacktesting - As backtest frameworks for coin trading strategy. Crypto Currencies zenbot - Command-line crypto currency trading bot using Node.js and MongoDB. bot18 - High-frequency crypto currency trading bot developed by Zenbot. magic8bot - Crypto currency trading bot using Node.js and MongoDB. catalyst - An algorithmic trading library for Crypto-Assets in python. QuantResearchDev - Quant Research dev & Traders open source project. MACD - Zenbot MACD Auto-Trader. abu - A quant trading system base on python. Plugins CoinMarketCapBacktesting - Tests bt and Quantopian Zipline as backtesting frameworks for coin trading strategy. Gekko-BacktestTool - Batch backtest, import and strategy params optimalization for Gekko Trading Bot. TA Lib pandastalib - A Python Pandas implementation of technical analysis indicators. finta - Common financial technical indicators implemented in Python-Pandas (70+ indicators). tulipnode - Official Node.js wrapper for Tulip Indicators. Provides over 100 technical analysis overlay and indicator functions. techan.js - A visual, technical analysis and charting (Candlestick, OHLC, indicators) library built on D3. Exchange API Do it in real world! IbPy - Python API for the Interactive Brokers on-line trading system. HuobiFeeder - Connect HUOBIPRO exchange, get market/historical data for ABAT trading platform backtest analysis and live trading. ctpwrapper - Shanghai future exchange CTP api. PENDAX - Javascript SDK for Trading/Data API and Websockets for cryptocurrency exchanges like FTX, FTXUS, OKX, Bybit, & More Framework tf-quant-finance - High-performance TensorFlow library for quantitative finance. Visualizing playground - Play with neural networks. netron - Visualizer for deep learning and machine learning models. KLineChart - Highly customizable professional lightweight financial charts GYM Environment 🌟 TradingGym - Trading and Backtesting environment for training reinforcement learning agent. TradzQAI - Trading environment for RL agents, backtesting and training. btgym - Scalable, event-driven, deep-learning-friendly backtesting library. Articles The-Economist - The Economist. nyu-mlif-notes - NYU machine learning in finance notes. Using LSTMs to Turn Feelings Into Trades Others zipline-tensorboard - TensorBoard as a Zipline dashboard. gekko-quasar-ui - An UI port for gekko trading bot using Quasar framework. Floom AI gateway and marketplace for developers, enables streamlined integration and least volatile approach of AI features into products Other Resource 🌟🌟🌟 Stock-Prediction-Models - Stock-Prediction-Models, Gathers machine learning and deep learning models for Stock forecasting, included trading bots and simulations. 🌟🌟 Financial Machine Learning - A curated list of practical financial machine learning (FinML) tools and applications. This collection is primarily in Python. 🌟 Awesome-Quant-Machine-Learning-Trading - Quant / Algorithm trading resources with an emphasis on Machine Learning. awesome-quant - A curated list of insanely awesome libraries, packages and resources for Quants (Quantitative Finance). FinancePy - A Python Finance Library that focuses on the pricing and risk-management of Financial Derivatives, including fixed-income, equity, FX and credit derivatives. Explore Finance Service Libraries & Projects - Explore a curated list of Fintech popular & new libraries, top authors, trending project kits, discussions, tutorials & learning resources on kandi.

eiten

Eiten - Algorithmic Investing Strategies for Everyone Eiten is an open source toolkit by Tradytics that implements various statistical and algorithmic investing strategies such as Eigen Portfolios, Minimum Variance Portfolios, Maximum Sharpe Ratio Portfolios, and Genetic Algorithms based Portfolios. It allows you to build your own portfolios with your own set of stocks that can beat the market. The rigorous testing framework included in Eiten enables you to have confidence in your portfolios. If you are looking to discuss these tools in depth and talk about more tools that we are working on, please feel free to join our Discord channel where we have a bunch of more tools too. Files Description | Path | Description | :--- | :---------- | eiten | Main folder. | &boxur; figures | Figures for this github repositories. | &boxur; stocks | Folder to keep your stock lists that you want to use to create your portfolios. | &boxur; strategies | A bunch of strategies implemented in python. | backtester.py | Backtesting module that both backtests and forward tests all portfolios. | data_loader.py | Module for loading data from yahoo finance. | portfolio_manager.py | Main file that takes in a bunch of arguments and generates several portfolios for you. | simulator.py | Simulator that uses historical returns and monte carlo to simulate future prices for the portfolios. | strategy_manager.py | Manages the strategies implemented in the 'strategies' folder. Required Packages You will need to install the following package to train and test the models. Scikit-learn Numpy Tqdm Yfinance Pandas Scipy You can install all packages using the following command. Please note that the script was written using python3. Build your portfolios Let us see how we can use all the strategies given in the toolkit to build our portfolios. The first thing you need to do is modify the stocks.txt file in the stocks folder and add the stocks of your choice. It is recommended to keep the list small i.e anywhere between 5 to 50 stocks should be fine. We have already put a small stocks list containing a bunch of tech stocks like AAPL, MSFT, TSLA etc. Let us build our portfolios now. This is the main command that you need to run. This command will use last 5 years of daily data excluding the last 90 days and build several portfolios for you. Based on those portfolios, it will then test them on the out of sample data of 90 days and show you the performance of each portfolio. Finally, it will also compare the performance with your choice of market index which is QQQ here. Let's dive into each of the parameters in detail. istest: The value determined if the program is going to keep some separate data for future testing. When this is enabled, the value of futurebars should be larger than 5. future_bars: These are the bars that the tool will exclude during portfolio building and will forward test the portfolios on the excluded set. This is also called out of sample data. datagranularityminutes: How much granular data do you want to use to build your portfolios. For long term portfolios, you should use daily data but for short term, you can use hourly or minute level data. The possible values here are 3600, 60, 30, 15, 5, 1. 3600 means daily. historytouse: Whether to use a specific number of historical bars or use everything that we receive from yahoo finance. For minute level data, we only receive up to one month of historical data. For daily, we receive 5 years worth of historical data. If you want to use all available data, the value should be all but if you want to use smaller history, you can set it to an integer value e.g 100 which will only use the last 100 bars to build the portfolios. applynoisefiltering: This uses random matrix theory to filter out the covariance matrix from randomness thus yielding better portfolios. A value of 1 will enable it and 0 will disable it. market_index: Which index do you want to use to compare your portfolios. This should mostly be SPY but since we analyzed tech stocks, we used QQQ. only_long: Whether to use long only portfolio or enable short selling as well. Long only portfolios have shown to have better performance using algorithmic techniques. eigenportfolionumber: Which eigen portfolio to use. Any value between 1-5 should work. The first eigen portfolio (1) represents the market portfolio and should act just like the underlying index such as SPY or QQQ. The second one is orthogonal and uncorrelated to the market and poses the greatest risk and reward. The following ones have reduced risk and reward. Read more on eigen-portfolios. stocksfilepath: File that contains the list of stocks that you want to use to build your portfolio. Some Portfolio Building Examples Here are a few examples for building different types of portfolios. Both long and short portfolios by analyzing last 90 days data and keeping the last 30 days as testing data. This will give us 60 days of portfolio construction data and 30 days of testing. Only long portfolio on 60 minute bars of the last 30 days. No future testing. Compare the results with SPY index instead of QQQ. Do not apply noise filtering on the covariance matrix. Use the first eigen portfolio (market portfolio) and compare with SQQQ, Portfolio Strategies Four different portfolio strategies are currently supported by the toolkit. Eigen Portfolios These portfolios are orthogonal and uncorrelated to the market in general thus yielding high reward and alpha. However, since they are uncorrelated to the market, they can also provide great risk. The first eigen portfolio is considered to be a market portfolio which is often ignored. The second one is uncorrelated to the others and provides the highest risk and reward. As we go down the numbering, the risk as well as the reward are reduced. Minimum Variance Portfolio (MVP) MVP tries to minimize the variance of the portfolio. These portfolios are lowest risk and reward. Maximum Sharpe Ratio Portfolio (MSR) MSR solves an optimization problem that tries to maximize the sharpe ratio of the portfolio. It uses past returns during the optimization process which means if past returns are not the same as future returns, the results can vary in future. Genetic Algorithm (GA) based Portfolio This is our own implementation of a GA based portfolio that again tries to maximize the sharpe ratio but in a slightly more robust way. This usually provides more robust portfolios than the others. When you run the command above, our tool will generate portfolios from all these strategies and give them to you. Let us look at some resulting portfolios. Resulting Portfolios For the purpose these results, we will use the 9 stocks in the stocks/stocks.txt file. When we run the above command, we first get the portfolio weights for all four strategies. For testing purposes, the above command used last five years of daily data up till April 29th. The remaining data for this year was used for forward testing i.e the portfolio strategies had no access to it when building the portfolios. What if my portfolio needs different stocks?: All you need to do is change the stocks in the stocks.txt file and run the tool again. Here is the final command again that we run in order to get our portfolios: Portfolio Weights We can see that the eigen portfolio is giving a large weight to TSLA while the others are dividing their weights more uniformly. An interesting phenomena happening here is the hedging with SQQQ that all the strategies have learned automatically. Every tool is assigning some positive weight to SQQQ while also assigning positive weights to other stocks which indicates that the strategies are automatically trying to hedge the portfolios from risk. Obviously this is not perfect, but just the fact that it's happening is fascinating. Let us look at the backtest results on the last five years prior to April 29, 2020. Backtest Results The backtests look pretty encouraging. The black dotted line is the market index i.e QQQ. Other lines are the strategies. Our custom genetic algorithm implementation seems to have the best backtest results because it's an advanced version of other strategies. The eigen portfolio that weighed TSLA the most have the most volatility but its profits are also very high. Finally, as expected, the MVP has the minimum variance and ultimately the least profits. However, since the variance is extremely low, it is a good portfolio for those who want to stay safe. The most interesting part comes next, let us look at the forward or future test results for these portfolios. Forward Test Results These results are from April 29th, 2020 to September 4th, 2020. The eigen portfolio performed the best but it also had a lot of volatility. Moreover, most of those returns are due to TSLA rocketing in the last few months. After that, our GA algorithm worked quite effectively as it beat the market index. Again, as expected, the MVP had the lowest risk and reward and slowly went up in 4-5 months. This shows the effectiveness and power of these algorithmic portfolio optimization strategies where we've developed different portfolios for different kinds of risk and reward profiles. Conclusion and Discussion We are happy to share this toolkit with the trading community and hope that people will like and contribute to it. As is the case with everything in trading, these strategies are not perfect but they are based on rigorous theory and some great empirical results. Please take care when trading with these strategies and always manage your risk. The above results were not cherry picked but the market has been highly bullish in the last few months which has led to the strong results shown above. We would love for the community to try out different strategies and share them with us. Special Thanks Special thanks to Scott Rome's blog. The eigen portfolios and minimum variance portfolio concepts came from his blog posts. The code for filtering eigen values of the covariance matrix was also mostly obtained from one of his posts. License A product by Tradytics Copyright (c) 2020-present, Tradytics.com

yoha

Yoha A practical hand tracking engine. Note: Yoha is currently unmaintained. Quick Links: Demo (Code) Docs Website npm Installation npm install @handtracking.io/yoha Please note: You need to serve the files from node_modules/@handtracking.io/yoha since the library needs to download the model files from here. (Webpack Example) You need to serve your page with https for webcam access. (Webpack Example) You should use cross-origin isolation as it improves the engine's performance in certain scenarios. (Webpack Example) Description Yoha is a hand tracking engine that is built with the goal of being a versatile solution in practical scenarios where hand tracking is employed to add value to an application. While ultimately the goal is to be a general purpose hand tracking engine supporting any hand pose, the engine evolves around specific hand poses that users/developers find useful. These poses are detected by the engine which allows to build applications with meaningful interactions. See the demo for an example. Yoha is currently in beta. About the name: Yoha is short for ("Your Hand Tracking"). Language Support Yoha is currently available for the web via JavaScript. More languages will be added in the future. If you want to port Yoha to another language and need help feel free reach out. Technical Details Yoha was built from scratch. It uses a custom neural network trained using a custom dataset. The backbone for the inference in the browser is currently TensorFlow.js Features: Detection of 21 2D-landmark coordinates (single hand). Hand presence detection. Hand orientation (left/right hand) detection. Inbuilt pose detection. Supported Hand Poses: Pinch (index finger and thumb touch) Fist Your desired pose is not on this list? Feel free to create an issue for it. Performance Yoha was built with performance in mind. It is able to provide realtime user experience on a broad range of laptops and desktop devices. The performance on mobile devices is not great which hopefuly will change with the further development of inference frameworks like TensorFlow.js Please note that native inference speed can not be compared with the web inference speed. Differently put, if you were to run Yoha natively it would be much faster than via the web browser. Minimal Example Source Running locally: Drawing Demo Live Version Source Running locally:

CollabAI

CollabAI About Welcome to Collabai.software, where we've taken the world of AI to new heights. We've been working tirelessly to bring you the most advanced, user-friendly platform that seamlessly integrates with the powerful OpenAI API, Gemini, and Claude. Imagine running your own ChatGPT on your server, with the ability to manage access for your entire team. Picture creating custom AI assistants that cater to your unique needs, and organizing your employees into groups for streamlined collaboration. With Collabai.software, this is not just a dream, but a reality. Collabai.software Features: Self-Hosting on Your Cloud: Gain full control by hosting the platform on your private cloud. Ensure data privacy by using your API codes, allowing for secure data handling. Enhanced Team Management: Manage teams with private accounts and customizable access levels (Departments). Prompt Templates: Utilize generic templates to streamline team usage. Departmental Access & Assistant Assignment: Assign AI assistants to specific departments for shared team access. Customizable AI Assistants: Create personalized AI assistants for users or organizations. Tagging Feature in Chats: Organize and retrieve chat data efficiently with custom tags. Chat Storage and Retrieval: Save all chats and replies for future analysis, with an option to restore accidentally deleted chats from Trash. Optimized Performance: Experience our high-speed, efficient platform. Our clients have been using it for over a year, with some spending $1500-$2000 per month on the API. File Upload & GPT-4 Vision Integration: Enhance interactions by uploading files for analysis and sending pictures for AI description. OpenAI API, Gemini, and Claude Integration: Seamlessly integrate with the powerful OpenAI API, Gemini, and Claude for a comprehensive suite of AI capabilities. API-Based Function Calls: Execute custom functions and automate tasks directly through the API. Usage Monitoring: Track your daily and monthly API usage costs to optimize spending. Day and Night Mode: Switch between light and dark themes to enhance visual comfort. Additional Features: Private Accounts: Ensure the security and privacy of your team members' data. Customizable Access Levels: Tailor access permissions to meet the specific needs of your organization. Shared Team Access: Foster collaboration by assigning AI assistants to specific departments or teams. AI-Powered File Analysis: Gain insights and automate tasks by uploading files for AI analysis. AI-Generated Image Descriptions: Enhance communication and understanding by sending pictures for AI-powered descriptions. !image !image !image Folder Structure Client The client folder contains the React-based frontend code for the application. This includes JSX, CSS, and JavaScript files, as well as any additional assets such as images or fonts. Below is a brief overview of the main subdirectories within the client folder: src: This directory contains the React components, styles, and scripts for the frontend application. public: Static assets, such as images or favicon.ico, go here. This folder is served as-is and not processed by the build system. Server The server folder contains all the backend-related code for the application, following a Model-View-Controller (MVC) pattern. Here is a breakdown of the main subdirectories within the server folder: controllers: This directory holds the controller files responsible for handling requests, processing data, and interacting with models. models: Data models and database-related code are organized in this folder. config: Configuration files for the backend, such as database configuration or any other service configuration should be stored here, can be stored in this directory. Getting Started Follow the steps below to get the project up and running. Prerequisites Node.js (Version: >=20.x) MongoDB NPM Development Setup Clone the Repository bash cd client Install Dependencies bash cd ../server Install Backend Dependencies bash npm start To initialize the application data and create a superadmin user, you can use either cURL or Postman: Using cURL If you prefer command-line tools, you can use curl to make a POST request to the /init-setup endpoint. Open your terminal and run the following command: curl -X POST http://localhost:8011/api/init -H "Content-Type: application/json" -d '{ "fname": "Super", "lname": "Admin", "email": "superadmin@example.com", "password": "yourSecurePassword", "employeeCount": 100, "companyName": "INIT_COMPANY" }' Initializing Setup with Postman Open Postman: Launch the Postman application. Create a New Request: Click on the '+' or 'New' button to create a new request. Set HTTP Method to POST: Ensure that the HTTP method is set to POST. Enter URL: Enter the URL http://localhost:8011/api/init. Set Headers: Go to the 'Headers' tab. Set Content-Type to application/json. Set Request Body: Switch to the 'Body' tab. Select the 'raw' radio button. Enter the JSON data for your superadmin user: Send Request: Click the 'Send' button to make the request. This will send a POST request to http://localhost:8011/api/init with the provided JSON payload, creating a superadmin user with the specified details. Site Setup: Login with the superadmin credentials and set up your site by adding configs from your settings page, for ex. API keys, etc. Reference CollaborativeAI Reference Guide Contributing If you would like to contribute to the project, we welcome your contributions! Please follow the guidelines outlined in the CONTRIBUTING.md file. Feel free to raise issues, suggest new features, or send pull requests to help improve the project. Your involvement is greatly appreciated! Thank you for contributing to our project! License MIT

Solana_AIAgent_Trading

Solana AI Agent Trading Tool An open-source trading toolkit for connecting AI agents to Solana protocols. Now, any agent, using any model can autonomously perform 15+ Solana actions: Trade tokens Launch new tokens Lend assets Send compressed airdrops Execute blinks Launch tokens on AMMs And more... 💬 Contact Me If you have any question or something, feel free to reach out me anytime via telegram, discord or twitter. 🌹 You're always welcome 🌹 Telegram: @Leo Replit template created by Arpit Singh 🔧 Core Blockchain Features Token Operations Deploy SPL tokens by Metaplex Transfer assets Balance checks Stake SOL Zk compressed Airdrop by Light Protocol and Helius NFTs on 3.Land Create your own collection NFT creation and automatic listing on 3.land List your NFT for sale in any SPL token NFT Management via Metaplex Collection deployment NFT minting Metadata management Royalty configuration DeFi Integration Jupiter Exchange swaps Launch on Pump via PumpPortal Raydium pool creation (CPMM, CLMM, AMMv4) Orca Whirlpool integration Manifest market creation, and limit orders Meteora Dynamic AMM, DLMM Pool, and Alpha Vault Openbook market creation Register and Resolve SNS Jito Bundles Pyth Price feeds for fetching Asset Prices Register/resolve Alldomains Perpetuals Trading with Adrena Protocol Drift Vaults, Perps, Lending and Borrowing Solana Blinks Lending by Lulo (Best APR for USDC) Send Arcade Games JupSOL staking Solayer SOL (sSOL)staking Non-Financial Actions Gib Work for registering bounties 🤖 AI Integration Features LangChain Integration Ready-to-use LangChain tools for blockchain operations Autonomous agent support with React framework Memory management for persistent interactions Streaming responses for real-time feedback Vercel AI SDK Integration Vercel AI SDK for AI agent integration Framework agnostic support Quick and easy toolkit setup Autonomous Modes Interactive chat mode for guided operations Autonomous mode for independent agent actions Configurable action intervals Built-in error handling and recovery AI Tools DALL-E integration for NFT artwork generation Natural language processing for blockchain commands Price feed integration for market analysis Automated decision-making capabilities 📃 Documentation You can view the full documentation of the kit at docs.solanaagentkit.xyz 📦 Installation Quick Start Usage Examples Deploy a New Token Create NFT Collection on 3Land Create NFT on 3Land When creating an NFT using 3Land's tool, it automatically goes for sale on 3.land website Create NFT Collection Swap Tokens Lend Tokens Stake SOL Stake SOL on Solayer Send an SPL Token Airdrop via ZK Compression Fetch Price Data from Pyth Open PERP Trade Close PERP Trade Close Empty Token Accounts Create a Drift account Create a drift account with an initial token deposit. Create a Drift Vault Create a drift vault. Deposit into a Drift Vault Deposit tokens into a drift vault. Deposit into your Drift account Deposit tokens into your drift account. Derive a Drift Vault address Derive a drift vault address. Do you have a Drift account Check if agent has a drift account. Get Drift account information Get drift account information. Request withdrawal from Drift vault Request withdrawal from drift vault. Carry out a perpetual trade using a Drift vault Open a perpertual trade using a drift vault that is delegated to you. Carry out a perpetual trade using your Drift account Open a perpertual trade using your drift account. Update Drift vault parameters Update drift vault parameters. Withdraw from Drift account Withdraw tokens from your drift account. Borrow from Drift Borrow tokens from drift. Repay Drift loan Repay a loan from drift. Withdraw from Drift vault Withdraw tokens from a drift vault after the redemption period has elapsed. Update the address a Drift vault is delegated to Update the address a drift vault is delegated to. Get Voltr Vault Position Values Get the current position values and total value of assets in a Voltr vault. Deposit into Voltr Strategy Deposit assets into a specific strategy within a Voltr vault. Withdraw from Voltr Strategy Withdraw assets from a specific strategy within a Voltr vault. Get a Solana asset by its ID Get a price inference from Allora Get the price for a given token and timeframe from Allora's API List all topics from Allora Get an inference for an specific topic from Allora Examples LangGraph Multi-Agent System The repository includes an advanced example of building a multi-agent system using LangGraph and Solana Agent Kit. Located in examples/agent-kit-langgraph, this example demonstrates: Multi-agent architecture using LangGraph's StateGraph Specialized agents for different tasks: General purpose agent for basic queries Transfer/Swap agent for transaction operations Read agent for blockchain data queries Manager agent for routing and orchestration Fully typed TypeScript implementation Environment-based configuration Check out the LangGraph example for a complete implementation of an advanced Solana agent system. Dependencies The toolkit relies on several key Solana and Metaplex libraries: @solana/web3.js @solana/spl-token @metaplex-foundation/digital-asset-standard-api @metaplex-foundation/mpl-token-metadata @metaplex-foundation/mpl-core @metaplex-foundation/umi @lightprotocol/compressed-token @lightprotocol/stateless.js Contributing Contributions are welcome! Please feel free to submit a Pull Request. Refer to CONTRIBUTING.md for detailed guidelines on how to contribute to this project. Contributors Star History License Apache-2 License Funding If you wanna give back any tokens or donations to the OSS community -- The Public Solana Agent Kit Treasury Address: Solana Network : EKHTbXpsm6YDgJzMkFxNU1LNXeWcUW7Ezf8mjUNQQ4Pa Security This toolkit handles private keys and transactions. Always ensure you're using it in a secure environment and never share your private keys.

How-to-learn-Deep-Learning

Approach A practical, top-down approach, starting with high-level frameworks with a focus on Deep Learning. UPDATED VERSION: 👉 Check out my 60-page guide, No ML Degree, on how to land a machine learning job without a degree. Getting started [2 months] There are three main goals to get up to speed with deep learning: 1) Get familiar to the tools you will be working with, e.g. Python, the command line and Jupyter notebooks 2) Get used to the workflow, everything from finding the data to deploying a trained model 3) Building a deep learning mindset, an intuition for how deep learning models behave and how to improve them Spend a week on codecademy.com and learn the python syntax, command line and git. If you don't have any previous programming experience, it's good to spend a few months learning how to program. Otherwise, it's easy to become overwhelmed. Spend one to two weeks using Pandas and Scikit-learn on Kaggle problems using Jupyter Notebook on Colab, e.g. Titanic, House prices, and Iris. This gives you an overview of the machine learning mindset and workflow. Spend one month implementing models on cloud GPUs. Start with FastAI and PyTorch. The FastAI community is the go-to place for people wanting to apply deep learning and share the state of the art techniques. Once you have done this, you will know how to add value with ML. Portfolio [3 - 12 months] Think of your portfolio as evidence to a potential employer that you can provide value for them. When you are looking for your first job, there are four main roles you can apply for Machine Learning Engineering, Applied Machine Learning Researcher / Residencies, Machine Learning Research Scientist, and Software Engineering. A lot of the work related to machine learning is pure software engineering roles (category 4), e.g. scaling infrastructure, but that's out of scope for this article. It's easiest to get a foot in the door if you aim for Machine Learning Engineering roles. There are a magnitude more ML engineering roles compared to category 2 & 3 roles, they require little to no theory, and they are less competitive. Most employers prefer scaling and leveraging stable implementations, often ~1 year old, instead of allocating scarce resources to implement SOTA papers, which are often time-consuming and seldom work well in practice. Once you can cover your bills and have a few years of experience, you are in a better position to learn theory and advance to category 2 & 3 roles. This is especially true if you are self-taught, you often have an edge against an average university graduate. In general, graduates have weak practical skills and strong theory skills. Context You'll have a mix of 3 - 10 technical and non-technical people looking at your portfolio, regardless of their background, you want to spark the following reactions: the applicant has experience tackling our type of problems, the applicant's work is easy to understand and well organized, and the work was without a doubt 100% made by the applicant. Most ML learners end up with the same portfolio as everyone else. Portfolio items include things as MOOC participation, dog/cat classifiers, and implementations on toy datasets such as the titanic and iris datasets. They often indicate that you actively avoid real-world problem-solving, and prefer being in your comfort zone by copy-pasting from tutorials. These portfolio items often signal negative value instead of signaling that you are a high-quality candidate. A unique portfolio item implies that you have tackled a unique problem without a solution, and thus have to engage in the type of problem-solving an employee does daily. A good starting point is to look for portfolio ideas on active Kaggle competitions, and machine learning consulting projects, and demo versions of common production pipelines. Here's a Twitter thread on how to come up with portfolio ideas. Here are rough guidelines to self-assess the strength of your portfolio: Machine learning engineering: Even though ML engineering roles are the most strategic entry point, they are still highly competitive. In general, there are ~50 software engineering roles for every ML role. From the self-learners I know, 2/3 fail to get a foot in the door and end up taking software engineering roles instead. You are ready to look for a job when you have two high-quality projects that are well-documented, have unique datasets, and are relevant to a specific industry, say banking or insurance. Project Type | Base score | -------------| -----------| Common project | -1 p || Unique project | 10 p | Multiplier Type | Factor -----------------|----------------- Strong documentation | 5x 5000-word article | 5x Kaggle Medal | 10x Employer relevancy | 20x Hireable: 5,250 p Competative: 15,000 p Applied research / research assistant/ residencies: For most companies, the risk of pursuing cutting edge research is often too high, thus only the biggest companies tend to need this skillset. There are smaller research organizations that hire for these positions, but these positions tend to be poorly advertised and have a bias for people in their existing community. Many of these roles don't require a Ph.D., which makes them available to most people with a Bachelor's or Master's degrees, or self-learners with one year of focussed study. Given the status, scarcity, and requirements for these positions, they are the most competitive ML positions. Positions at well-known companies tend to get more than a thousand applicants per position. Daily, these roles require that you understand and can implement SOTA papers, thus that's what they will be looking for in your portfolio. Projects type | Base score --------------| ----------- Common project | -10 p Unique project | 1 p SOTA paper implementation | 20 p Multiplier type | Factor ----------------| --------------- Strong documentation | 5x 5000-word article | 5x SOTA performance | 5x Employer relevancy | 20x Hireable: 52,500 p Competitive: 150,000 p Research Scientist: Research scientist roles require a Ph.D. or equivalent experience. While the former category requires the ability to implement SOTA papers, this category requires you to come up with research ideas. The mainstream research community measure the quality of research ideas by their impact, here is a list of the venues and their impact. To have a competitive portfolio, you need two published papers in the top venues in an area that's relevant to your potential employer. Project type | Base score -------------| ---------------- Common project | -100 p An unpublished paper | 5 p ICML/ICLR/NeurIPS publication | 500p All other publications | 50 p Multiplier type | Factor ------------------| ------------------ First author paper | 10x Employer relevancy | 20x Hireable: 20,000 p Competitive roles and elite PhD positions: 200,000 p Examples: My first portfolio item (after 2 months of learning): Code | Write-up My second portfolio item (after 4 months of learning): Code | Write-up Dylan Djian's first portfolio item: Code | Write-up Dylan Djian's second portfolio item: Code | Write-up Reiichiro Nakano's first portfolio item: Code | Write-up Reiichiro Nakano's second portfolio item: Write-up Most recruiters will spend 10-20 seconds on each of your portfolio items. Unless they can understand the value in that time frame, the value of the project is close to zero. Thus, writing and documentation are key. Here's another thread on how to write about portfolio items. The last key point is relevancy. It's more fun to make a wide range of projects, but if you want to optimize for breaking into the industry, you want to do all projects in one niche, thus making your skillset super relevant for a specific pool of employers. Further Inspiration: FastAI student projects Stanford NLP student projects Stanford CNN student projects Theory 101 [4 months] Learning how to read papers is critical if you want to get into research, and a brilliant asset as an ML engineer. There are three key areas to feel comfortable reading papers: 1) Understanding the details of the most frequent algorithms, gradient descent, linear regression, and MLPs, etc 2) Learning how to translate the most frequent math notations into code 3) Learn the basics of algebra, calculus, statistics, and machine learning For the first week, spend it on 3Blue1Brown's Essence of linear algebra, the Essence of Calculus, and StatQuests' the Basics (of statistics) and Machine Learning. Use a spaced repetition app like Anki and memorize all the key concepts. Use images as much as possible, they are easier to memorize. Spend one month recoding the core concepts in python numpy, including least squares, gradient descent, linear regression, and a vanilla neural network. This will help you reduce a lot of cognitive load down the line. Learning that notations are compact logic and how to translate it into code will make you feel less anxious about the theory. I believe the best deep learning theory curriculum is the Deep Learning Book by Ian Goodfellow and Yoshua Bengio and Aaron Courville. I use it as a curriculum, and the use online courses and internet resources to learn the details about each concept. Spend three months on part 1 of the Deep learning book. Use lectures and videos to understand the concepts, Khan academy type exercises to master each concept, and Anki flashcards to remember them long-term. Key Books: Deep Learning Book by Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD by Jeremy Howard and Sylvain. Gugger. Deep Learning with Python by François Chollet. Neural Networks and Deep Learning by Michael Nielsen. Grokking Deep Learning by Andrew W. Trask. Forums FastAI Keras Slack Distill Slack Pytorch Twitter Other good learning strategies: Emil Wallner S. Zayd Enam Catherine Olsson Greg Brockman V2 Greg Brockman V1 Andrew Ng Amid Fish Spinning Up by OpenAI Confession as an AI researcher YC Threads: One and Two If you have suggestions/questions create an issue or ping me on Twitter. UPDATED VERSION: 👉 Check out my 60-page guide, No ML Degree, on how to land a machine learning job without a degree. Language versions: Korean | English

Overmind

[](https://github.com/bencbartlett/Overmind/releases) [](https://github.com/bencbartlett/Overmind/blob/master/CHANGELOG.md) [](https://bencbartlett.github.io/overmind-docs/) [](https://github.com/bencbartlett/Overmind/wiki) [](https://screeps.slack.com/messages/overmind) [](https://github.com/bencbartlett/Overmind/issues/new) [](https://github.com/bencbartlett/Overmind/issues/new?template=feature_request.md) Current release: Overmind v0.5.2 - Evolution See the changelog for patch notes Documentation is available at the documentation site and the wiki Join the discussion in the #overmind Slack channel! Read blog posts about development Submit an issue here or request a feature here Find me in game here About Overmind What is Screeps? Screeps is an MMO strategy game for programmers. The core objective is to expand your colony, gathering resources and fighting other players along the way. To control your units, you code an AI in JavaScript; everything from moving, mining, building, fighting, and trading is entirely driven by your code. Because Screeps is an MMO, it takes place on a single server that runs 24/7, populated by every other player and their army of creeps. When you log off, your population continues buzzing away with whatever task you set them. Screeps pits your programming prowess head-to-head with other people to see who can think of the most efficient methods of completing tasks or imagine new ways to defeat enemies. What is Overmind? Overmind is my personal codebase that I run on the public server. The structure of the AI is themed loosely around the Zerg's swarm intelligence from Starcraft. Overlords orchestrate Creep actions within each Colony, and the colony Overseer places Directives to adapt to stimuli. Finally, the Assimilator allows all players running Overmind to act as a collective hivemind, sharing creeps and resources and responding jointly to a master ledger of all directives shared by all players. The AI is entirely automated, although it can also run in manual or semiautomatic mode. The latest release should work right out of the box; however, if you find something broken, please submit an issue and I'll try to fix it. Can I use Overmind as my bot? If you're new to Screeps, I would definitely recommend writing your own AI: most of the fun of the game is programming your own bot and watching your little ant farm run! However, I've tried to make the codebase readable and well-documented, so feel free to fork the project or use it as inspiration when writing your AI. If you still want to use Overmind on the public server, that's okay too - there are a number of people already doing this. But please realize that using a mature AI like this gives you a huge advantage over other new players, so don't go out of your way to ruin someone else's fun. In the future, I will be implementing methods for novice players to opt out of excessive aggression by Overmind bots (as long as they don't start a conflict and stay out of its way). Installation Out of the box If you just want to run Overmind without modification, you can copy the compiled main.js file attached to the latest release into your script. While Overmind is fully automated by default, it can be run with varying levels of autonomy; refer to the Overmind wiki for how to configure and operate the bot. Compiling from source To install the full codebase, download or clone the repository. (Please note that while the latest release of Overmind should always be stable, the latest commit may contain unstable features.) Navigate to the Overmind root directory and run . To compile and deploy the codebase, create a screeps.json file from the example file, then do one of the following actions: Compile and deploy to public server: npm run push-main Compile and deploy to private server: npm run push-pserver Compile without deploying: npm run compile Overmind uses rollup to bundle the compiled TypeScript into a single main.js file. The codebase includes functionality to compute checksums for internal validation - if you have a different version of rollup installed globally, different checksums may be computed and some functionality will be disabled. Please ensure the local installation of rollup found in node_modules is used. Setting up the Grafana dashboard Overmind includes a Grafana dashboard (shown below) which tracks detailed operating statistics. To set up the dashboard: Register for grafana service at screepspl.us Setup the ScreepsPlus hosted agent (simpler) or use the NodeJS agent on a free micro instance of Google Compute. Import the dashboard from Overmind.json and change $User to your username. Enjoy your pretty graphs! Design overview Check out the Overmind wiki for in-depth explanations of parts of the design of the AI. (Click the diagram below to see a higher-resolution version.)

bytom

Bytom ====== Official golang implementation of the Bytom protocol. Automated builds are available for stable releases and the unstable master branch. Binary archives are published at https://github.com/Bytom/bytom/releases. What is Bytom? Bytom is software designed to operate and connect to highly scalable blockchain networks confirming to the Bytom Blockchain Protocol, which allows partipicants to define, issue and transfer digitial assets on a multi-asset shared ledger. Please refer to the White Paper for more details. In the current state bytom is able to: Manage key, account as well as asset Send transactions, i.e., issue, spend and retire asset Installing with Homebrew Building from source Requirements Go version 1.8 or higher, with $GOPATH set to your preferred directory Installation Ensure Go with the supported version is installed properly: Get the source code Build source code When successfully building the project, the bytomd and bytomcli binary should be present in cmd/bytomd and cmd/bytomcli directory, respectively. Executables The Bytom project comes with several executables found in the cmd directory. | Command | Description | | ------------ | ------------------------------------------------------------ | | bytomd | bytomd command can help to initialize and launch bytom domain by custom parameters. bytomd --help for command line options. | | bytomcli | Our main Bytom CLI client. It is the entry point into the Bytom network (main-, test- or private net), capable of running as a full node archive node (retaining all historical state). It can be used by other processes as a gateway into the Bytom network via JSON RPC endpoints exposed on top of HTTP, WebSocket and/or IPC transports. bytomcli --help and the bytomcli Wiki page for command line options. | Running bytom Currently, bytom is still in active development and a ton of work needs to be done, but we also provide the following content for these eager to do something with bytom. This section won't cover all the commands of bytomd and bytomcli at length, for more information, please the help of every command, e.g., bytomcli help. Initialize First of all, initialize the node: There are three options for the flag --chain_id: mainnet: connect to the mainnet. testnet: connect to the testnet wisdom. solonet: standalone mode. After that, you'll see config.toml generated, then launch the node. launch available flags for bytomd node: Given the bytomd node is running, the general workflow is as follows: create key, then you can create account and asset. send transaction, i.e., build, sign and submit transaction. query all kinds of information, let's say, avaliable key, account, key, balances, transactions, etc. Dashboard Access the dashboard: In Docker Ensure your Docker version is 17.05 or higher. For the usage please refer to running-in-docker-wiki. Contributing Thank you for considering helping out with the source code! Any contributions are highly appreciated, and we are grateful for even the smallest of fixes! If you run into an issue, feel free to bytom issues in this repository. We are glad to help! License AGPL v3

AI-and-Business-Rules-for-Excel-Power-Users

AI and Business Rules for Excel Power Users This is the code repository for AI and Business Rules for Excel Power Users, published by Packt. Capture and scale your business knowledge into the cloud – with Microsoft 365, Decision Models, and AI tools from IBM and Red Hat What is this book about? Microsoft Excel is widely adopted across diverse industries, but Excel Power Users often encounter limitations such as complex formulas, obscure business knowledge, and errors from using outdated sheets. They need a better enterprise-level solution, and this book introduces Business rules combined with the power of AI to tackle the limitations of Excel. This book covers the following exciting features: Use KIE and Drools decision services to write AI-based business rules Link Business Rules to Excel using Power Query, Script Lab, Office Script, and VBA Build an end-to-end workflow with Microsoft Power Automate and Forms while integrating it with Excel and Kogito Collaborate on and deploy your decision models using OpenShift, Azure, and GitHub Discover advanced editing using the graphical Decision Model Notation (DMN) and testing tools Use Kogito to combine AI solutions with Excel If you feel this book is for you, get your copy today! Instructions and Navigations All of the code is organized into folders. For example, Chapter06. The code will look like the following: Following is what you need for this book: This book is for Excel power users, business users, and business analysts looking for a tool to capture their knowledge and deploy it as part of enterprise-grade systems. Working proficiency with MS Excel is required. Basic knowledge of web technologies and scripting would be an added advantage With the following software and hardware list you can run all code files present in the book (Chapter 1-12). Software and Hardware List | Chapter | Software required | OS required | | -------- | ------------------------------------ | ----------------------------------- | | 6-8 | Microsoft Excel and Office 365 | Windows, Mac OS X, and Linux (Any) | | 10 | Docker | Windows, Mac OS X, and Linux (Any) | | Appendix A | Visual Basic for Applications | Windows, Mac OS X, and Linux (Any) | We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it. Related products Exploring Microsoft Excel’s Hidden Treasures [[Packt]](https://www.packtpub.com/product/exploring-microsoft-excels-hidden-treasures/9781803243948?utmsource=github&utmmedium=repository&utm_campaign=9781803243948) [[Amazon]](https://www.amazon.com/dp/1803243945) VBA Automation for Excel 2019 Cookbook [[Packt]](https://subscription.packtpub.com/search?query=9781789610031&utmsource=github&utmmedium=repository&utm_campaign=9781803242002) [[Amazon]](https://www.amazon.com/dp/1789610036) Get to Know the Author Paul Browne is a Programme Manager - Training and Consulting at Enterprise Ireland. His skillset includes delivering consulting and training into companies to help them grow faster, better and earlier. Particular focus in working on Digital Transformation alongside Sales and Marketing, Manufacturing and Financial teams. His educational qualifications includes Msc Advanced Software Engineering at University College Dublin and BA European Business Studies with French at Ulster University, Northern Ireland. His professional qualifications includes ACCA (Financial management modules), CIPS - Procurement Professional, and Technical certifications from Oracle (Java) and Microsoft. Download a free PDF If you have already purchased a print or Kindle version of this book, you can get a DRM-free PDF version at no cost.Simply click on the link to claim your free PDF. https://packt.link/free-ebook/9781804619544

ai-builder

AI-Driven Website Generator Description: The AI-Driven Website Generator is a project that aims to simplify the website creation process by utilizing AI technology, specifically GPT-3, to automatically generate customized landing pages for businesses. With this generator, you can quickly create visually appealing and responsive landing pages by providing a business name or specific instructions. The generator starts by taking input in the form of a business name or a set of instructions provided by the user. It then utilizes GPT-3 to analyze the input and generate the necessary HTML, CSS, and JavaScript code required to create a functional landing page. The generated code is designed to be compatible with modern web browsers and responsive across different devices. Key Features: Automatic generation of landing pages using AI technology. Customizable output based on business names or user instructions. Responsive and visually appealing user interfaces generated with Tailwind CSS. Efficient and streamlined website creation process. Flexibility to incorporate additional features or components as needed. How It Works The website generator utilizes the power of GPT-3 to analyze the input provided and generate the necessary HTML, CSS, and JavaScript code required to create a functional landing page. The generated code is designed to be compatible with modern web browsers and responsive across different devices. Contributing Contributions to the AI-Driven Website Generator project are welcome! If you have any ideas, suggestions, or bug reports, please feel free to open an issue or submit a pull request. Your contributions will help enhance the functionality and performance of the generator. License This project is licensed under the MIT License. Feel free to modify and distribute it according to the terms of the license. With the AI-Driven Website Generator, you can revolutionize the website creation process by harnessing the power of AI to generate customized landing pages effortlessly. Say goodbye to manual coding and design work, and experience the convenience and speed of generating professional-looking landing pages with just a few clicks.

What Is Vibe Coding? And Why I Hate It....

This video I'll talk about a new trend I've been seeing hit the coding and software development community. VIBE Coding... Make sure to like and subscribe... if you feel like it... you do you king... or queen... Twitter Link (not my finest work): https://x.com/basicdevblog?s=21 Check out the blog: https://basicdev.blog/ #softwaredeveloper #coding #vibecoding #softwareengineer #tech #software #aicoding #ai #twitter

llc-intro-to-ai-master

Ladies Learning Code Introduction to Artificial Intelligence and Machine Learning Quick Links Preview Slides: https://ladieslearningcode.github.io/llc-intro-to-ai-master/slides.html Special Note for Instructors The dataiku platform will need to be activated ahead of time. If you haven't received a custom bitly link via email already, please let us know at content@canadalearningcode.ca and we'll set one up for you. Attributions Content created by Parinaz Sobhani for Canada Learning Code. Slide presentation created by Christina Truong for Canada Learning Code. Email questions & comments to content@canadalearningcode.ca. If you'd like to contribute to future lesson content development, let us know here. We're really happy to see others leverage our content in their community - we’ve developed it to be used by others with attribution through a Creative Commons (CC BY-NC 4.0) license. Here’s an easy way to attribute content back to us - please include it wherever you use or make reference to our content. “Please note that this is not a Canada Learning Code affiliated event, but we want to acknowledge the organization for the creation of the content [INSERT LINK TO GITHUB LINK] being delivered under Creative Commons license" Contributing Our general Rule of Thumb is that it's okay to add examples if you feel it could provide more context for your community. However, we ask that instructors do not remove anything, as the content is designed with intention, whether that be meeting specific learning objectives, or maintaining our organization’s culture through the design. Any suggestions for revisions or updates can be submitted in Github via issues and pull requests. If submitting an issue, please include the slide number(s) in the title.

kodyfire

Kody is a command-line tool for generating artifact files, powered by both classic and AI code generation techniques. It can be used by both technical and non-technical users to generate files across a wide range of technologies and programming languages. The code generation feature in Kody relies on OpenAI GPT, a language model that uses deep learning to generate human-like text, and ChatGPT to provide natural language processing capabilities. Table of Contents Installation Usage Getting Started Terminology Contributing License Installation Prerequisites Node.js (version 14 or later) To install kody, use npm with the following command: or You can check the documentation with Usage Options -v, --version: Output the current version -h, --help: Display help for command Commands prompt|ai [options] [prompt...]: AI powered prompt assistant to quickly generate an artifact batch [options]: Generate multiple digital artifact create [options] : Generate a new blank kody project generate|g [options] [kody] [concept]: Prompt assistant to quickly generate an artifact import|in [options] : Mass create artifacts from a source. init: Initialize a new kodyfire project install|i [kody]: Prompt user to choose to install list|ls [options] [kodyName]: List installed kodies within your current project. publish [template]: Publish the templates of the kody along with the assets.json and schema.ts files ride|↻: Prompt assistant to help build your kody.json file run [options]: Generate a digital artifact based on the selected technology run-script|rs: Run scripts search|s [keywords...]: Search kodyfire packages from npm registry watch|w [options]: Watch for file changes and run kody help [command]: Display help for command Getting Started Open the project you are willing to work on using vscode or your prefered editor. Generate artifacts using AI In case you want to exclusivly rely on AI to generate your artifacts. You don't need to install any additional kodies. Run the kody ai [prompt] command and follow the prompts. For example, to create a Laravel Controller named SampleController under API/V1 and add a comment on top saying Hello Kodyfire, run the following command You can use the experimental Speech-to-Text option to pass your prompt using your voice. The transcription relies on Whisper and requires SoX installed and available in your \$PATH. for the audio recording. For Linux For MacOS For Windows Download the binaries Generate your artifact using the classical method Search and install a kody Based on your project, search availables kodies and select the one that fits your need.. To search availables kodies by keyword runthe following command. if you don't specify a keyword all available kodies will be listed. Install your kody of choice. For example, if you want to install the react kody or Please note you can install as many kodies in the same project as you wish. Generate your artifact There are 2 methods you can generate your artifacts with: The generate command The run command Method 1: Generator mode kody generate The recommended way of using kody is using the generate command. The command will assist you creating your artifact based on the chosen concept. For example, a react component is considered a concept. In order to generate your artifacts, run the generate command. The syntax is kody g|generate [kody] [concept]. the assistant will prompt you to select the missing arguments. As an example, run the following command from your terminal: Method 2: Runner mode kody run The run command is similar to the generate command. The run requires a definition file which is simply a json file containing all the concept definitions you have created using the ride command. The generate command on the other hand creates one or more concept definition on the run and process them on one run. Every command has its use cases. Initialize kody In order to start using kody, you need to initialize your project. This will add the definition files required for kody runs. Important: Please run the command only once. The command will override existing definition files. We will disable overriding in a future version. Ride your kody In order to update your definition, use the kody ride command to assist you populate the required fields Launch a kody run Once you are satisified with your definition file, execute the run command to generate your artifacts. To run all kodies defined within your project, run the following command: Create your own kody In most cases you might need a custom kody to suit your needs Scaffold a new kody Create a basic kody using the scaffold command. Follow the prompts to setup your kody This will create a folder containing the basic structure for a kody. You can start using right away within your project. Setup your kody Install npm dependencies Build your kody Add your concepts and related templates //TODO This will build your kody and export the basic templates files. Add your kody as an NPM dependency to a test project In order to be able to use it within your test project run the following command Publish your kody Please remember that Kody is still in exploration phase and things will change frequently. Contribution is always highly requested. Prepare your kody Add the required kodyfire metadata to your package.json Publish to Github Intialize your project as a git repository and push to a public Github repo To do so, kindly follow these steps:- Intitialize a new Github repository and make it public. Open your project root folder locally from terminal and run the following commands:- Link your project to your Github repository. Publish to npm Once you are satisfied with your kody and you would to like to share it with the community. Run the following command. Note: You'll need an NPM account Share with community Congratulation publishing your first kody. Don't forget to share your kody repo link by opening an issue on Kody's github repository. Terminology Kody: Refers to the code generation command-line tool that generates digital artifacts. Artifacts: Refers to the various digital products generated by Kody based on the input provided. Note: Kody uses classical code generation techniques in addition to AI-powered code generation using OpenAI Codex and ChatGPT. Available kodies | Name | Description | | -------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | | basic-kodyfire | A general purpose code generator that should handle most of the generation use cases | | typescript-kodyfire | Generate typescript related artifacts | | tsconfig-kodyfire | Generate tsconfig files for your typescript projects | | nextjs-kodyfire | Generate nextJs components and related artifacts | | react-kodyfire | Generate react components | | laravel-kodyfire | Laravel artifacts generation | | uml-kodyfire | Uml diagrams generation using plantuml | | readme-kodyfire | Readme file generation | | word-kodyfire | Generate ms word document based on a template | | pdf-kodyfire | Generate PDF document from HTML templates | | social-image-kodyfire | Generate dynamic images for social sharing based on HTML templates | | social-gif-kodyfire | Generate dynamic gif images for social sharing based on HTML templates | | linkedin-quizzes-kodyfire | Practice Linkedin skill assessement tests from your terminal | | chatgpt-kodyfire | Use chatgpt from the terminal. Allows you provide additional data from various sources (not implemented yet) and export to serveral outputs (markdown only now). | Contributing If you encounter any issues while using Kody or have suggestions for new features, feel free to open an issue or submit a pull request. Please read our contributing guidelines before making contributions. License Kody is MIT licensed.

internet-tools-collection

Internet Tools Collection A collection of tools, website and AI for entrepreneurs, web designers, programmers and for everyone else. Content by category Artificial Intelligence Developers Design Entrepreneur Video Editing Stock videos Stock Photos Stock music Search Engine Optimization Blog Posts Resume Interviews No code website builder No code game builder Side Hustle Browser Extensions Other Students Artificial Intelligence Jasper - The Best AI Writing Assistant [](https://www.jasper.ai/) Create content 5x faster with artificial intelligence. Jasper is the highest quality AI copywriting tool with over 3,000 5-star reviews. Best for writing blog posts, social media content, and marketing copy. AutoDraw [](https://www.autodraw.com/) Fast drawing for everyone. AutoDraw pairs machine learning with drawings from talented artists to help you draw stuff fast. Rytr - Best AI Writer, Content Generator & Writing Assistant [](https://rytr.me/) Rytr is an AI writing assistant that helps you create high-quality content, in just a few seconds, at a fraction of the cost! Neevo - Neevo [](https://www.neevo.ai/) Kinetix Tech [](https://kinetix.tech/) Kinetix is a no-code 3D creation tool powered by Artificial Intelligence. The web-based platform leverages AI motion capture to convert a video into a 3D animation and lets you customize your avatars and environments. We make 3D animation accessible to every creator so they can create engaging stories. LALAL.AI: 100% AI-Powered Vocal and Instrumental Tracks Remover [](https://www.lalal.ai/) Split vocal and instrumental tracks quickly and accurately with LALAL.AI. Upload any audio file and receive high-quality extracted tracks in a few seconds. Copy.ai: Write better marketing copy and content with AI [](https://www.copy.ai/) Get great copy that sells. Copy.ai is an AI-powered copywriter that generates high-quality copy for your business. Get started for free, no credit card required! Marketing simplified! OpenAI [](https://openai.com/) OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits all of humanity. DALL·E 2 [](https://openai.com/dall-e-2/) DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language. Steve.ai - World’s fastest way to create Videos [](https://www.steve.ai/) Steve.AI is an online Video making software that helps anyone to create Videos and animations in seconds. Octie.ai - Your A.I. ecommerce marketing assistant [](https://octie.ai/) Write emails, product descriptions, and more, with A.I. Created by Octane AI. hypnogram.xyz [](https://hypnogram.xyz/) Generate images from text descriptions using AI FakeYou. Deep Fake Text to Speech. [](https://fakeyou.com/) FakeYou is a text to speech wonderland where all of your dreams come true. Craiyon, formerly DALL-E mini [](https://www.craiyon.com/) Craiyon, formerly DALL-E mini, is an AI model that can draw images from any text prompt! Deck Rocks - Create Pictch Decks [](https://www.deck.rocks/) Writely | Using AI to Improve Your Writing [](https://www.writelyai.com/) Making the art of writing accessible to all Writesonic AI Writer - Best AI Writing Assistant [](https://writesonic.com/) Writesonic is an AI writer that's been trained on top-performing SEO content, high-performing ads, and converting sales copy to help you supercharge your writing and marketing efforts. Smart Copy - AI Copywriting Assistant | Unbounce [](https://unbounce.com/product/smart-copy/) Generate creative AI copy on-the-spot across your favourite tools Synthesia | #1 AI Video Generation Platform [](https://www.synthesia.io/) Create AI videos by simply typing in text. Easy to use, cheap and scalable. Make engaging videos with human presenters — directly from your browser. Free demo. NVIDIA Canvas: Turn Simple Brushstrokes into Realistic Images [](https://www.nvidia.com/en-us/studio/canvas/) Create backgrounds quickly, or speed up your concept exploration so you can spend more time visualizing ideas with the help of NVIDIA Canvas. Hotpot.ai - Hotpot.ai [](https://hotpot.ai/) Hotpot.ai makes graphic design and image editing easy. AI tools allow experts and non-designers to automate tedious tasks while attractive, easy-to-edit templates allow anyone to create device mockups, social media posts, marketing images, app icons, and other work graphics. Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. Search listening tool for market, customer & content research - AnswerThePublic [](https://answerthepublic.com/) Use our free tool to get instant, raw search insights, direct from the minds of your customers. Upgrade to a paid plan to monitor for new ways that people talk & ask questions about your brand, product or topic. Topic Mojo [](https://topicmojo.com/) Discover unique & newest queries around any topic and find what your customers are searching for. Pulling data from 50+ sources to enhance your topic research. AI Image Enlarger | Enlarge Image Without Losing Quality! [](https://imglarger.com/) AI Image Enlarger is a FREE online image enlarger that could upscale and enhance small images automatically. Make jpg/png pictures big without losing quality. Midjourney [](https://www.midjourney.com/app/) Kaedim - AI for turning 2D images to 3D models [](https://www.kaedim3d.com/webapp) AI for turning 2D images, sketches and photos to 3D models in seconds. Overdub: Ultra realistic text to speech voice cloning - Descript [](https://www.descript.com/overdub) Create a text to speech model of your voice. Try a live demo. Getting Started [](https://magenta.tensorflow.org/get-started) Resources to learn about Magenta Photosonic AI Art Generator | Create Unique Images with AI [](https://photosonic.writesonic.com/) Transform your imagination into stunning digital art with Photosonic - the AI art generator. With its creative suggestions, this Writesonic's AI image generator can help unleash your inner artist and share your creations with the world. Image Computer [](https://image.computer/) Most downloaded Instagram Captions App (+more creator tools) [](https://captionplus.app/) Join 3 Million+ Instagram Creators who use CaptionPlus to find Instagram Captions, Hashtags, Feed Planning, Reel Ideas, IG Story Design and more. Writecream - Best AI Writer & Content Generator - Writecream [](https://www.writecream.com/) Sentence Rewriter is a free tool to reword a sentence, paragraph and even entire essays in a short amount of time. Hypotenuse AI: AI Writing Assistant and Text Generator [](https://www.hypotenuse.ai/) Turn a few keywords into original, insightful articles, product descriptions and social media copy with AI copywriting—all in just minutes. Try it free today. Text to Speach Listnr: Generate realistic Text to Speech voiceovers in seconds [](https://www.listnr.tech/) AI Voiceover Generator with over 600+ voiceovers in 80+ languages, go from Text to Voice in seconds. Get started for Free! Free Text to Speech: Online, App, Software, Commercial license with Natural Sounding Voices. [](https://www.naturalreaders.com/) Free text to speech online app with natural voices, convert text to audio and mp3, for personal and commercial use Developers OverAPI.com | Collecting all the cheat sheets [](https://overapi.com/) OverAPI.com is a site collecting all the cheatsheets,all! Search Engine For Devs [](https://you.com/) Spline - Design tool for 3D web browser experiences [](https://spline.design/) Create web-based 3D browser experiences Image to HTML CSS converter. Convert image to HTML CSS with AI: Fronty [](https://fronty.com/) Fronty - Image to HTML CSS code converter. Convert image to HTML powered by AI. Sketchfab - The best 3D viewer on the web [](https://sketchfab.com/) With a community of over one million creators, we are the world’s largest platform to publish, share, and discover 3D content on web, mobile, AR, and VR. Railway [](https://railway.app/) Railway is an infrastructure platform where you can provision infrastructure, develop with that infrastructure locally, and then deploy to the cloud. JSON Crack - Crack your data into pieces [](https://jsoncrack.com/) Simple visualization tool for your JSON data. No forced structure, paste your JSON and view it instantly. Locofy.ai - ship your products 3-4x faster — with low code [](https://www.locofy.ai/) Turn your designs into production-ready frontend code for mobile apps and web. Ship products 3-4x faster with your existing design tools, tech stacks & workflows. Oh Shit, Git!?! [](https://ohshitgit.com/) Carbon | Create and share beautiful images of your source code [](https://carbon.now.sh/) Carbon is the easiest way to create and share beautiful images of your source code. GPRM : GitHub Profile ReadMe Maker [](https://gprm.itsvg.in/) Best Profile Generator, Create your perfect GitHub Profile ReadMe in the best possible way. Lots of features and tools included, all for free ! HubSpot | Software, Tools, and Resources to Help Your Business Grow Better [](https://www.hubspot.com/) HubSpot’s integrated CRM platform contains the marketing, sales, service, operations, and website-building software you need to grow your business. QuickRef.ME - Quick Reference Cheat Sheet [](https://quickref.me/) Share quick reference and cheat sheet for developers massCode | A free and open source code snippets manager for developers [](https://masscode.io/) Code snippets manager for developers, developed using web technologies. Snyk | Developer security | Develop fast. Stay secure. [](https://snyk.io/) Snyk helps software-driven businesses develop fast and stay secure. Continuously find and fix vulnerabilities for npm, Maven, NuGet, RubyGems, PyPI and more. Developer Roadmaps [](https://roadmap.sh/) Community driven roadmaps, articles, guides, quizzes, tips and resources for developers to learn from, identify their career paths, know what they don't know, find out the knowledge gaps, learn and improve. CSS Generators Get Waves – Create SVG waves for your next design [](https://getwaves.io/) A free SVG wave generator to make unique SVG waves for your next web design. Choose a curve, adjust complexity, randomize! Box Shadows [](https://box-shadow.dev/) Tridiv | CSS 3D Editor [](http://tridiv.com/) Tridiv is a web-based editor for creating 3D shapes in CSS Glassmorphism CSS Generator - Glass UI [](https://ui.glass/generator/) Generate CSS and HTML components using the glassmorphism design specifications based on the Glass UI library. Blobmaker - Make organic SVG shapes for your next design [](https://www.blobmaker.app/) Make organic SVG shapes for your next design. Modify the complexity, contrast, and color, to generate unique SVG blobs every time. Keyframes.app [](https://keyframes.app/) cssFilters.co - Custom and Instagram like photo filters for CSS [](https://www.cssfilters.co/) Visual playground for generating CSS for custom and Instagram like photo filters. Experiment with your own uploaded photo or select one from the Unsplash collection. CSS Animations Animista - CSS Animations on Demand [](https://animista.net/) Animista is a CSS animation library and a place where you can play with a collection of ready-made CSS animations and download only those you will use. Build Internal apps Superblocks | Save 100s of developer hours on internal tools [](https://www.superblocks.com/) Superblocks is the fast, easy and secure way for developers to build custom internal tools fast. Connect your databases & APIs. Drag and drop UI components. Extend with Python or Javascript. Deploy in 1-click. Secure and Monitor using your favorite tools Budibase | Build internal tools in minutes, the easy way [](https://budibase.com/) Budibase is a modern, open source low-code platform for building modern internal applications in minutes. Retool | Build internal tools, remarkably fast. [](https://retool.com/) Retool is the fast way to build internal tools. Drag-and-drop our building blocks and connect them to your databases and APIs to build your own tools, instantly. Connects with Postgres, REST APIs, GraphQL, Firebase, Google Sheets, and more. Built by developers, for developers. Trusted by startups and Fortune 500s. Sign up for free. GitHub Repositories GitHub - vasanthk/how-web-works: What happens behind the scenes when we type www.google.com in a browser? [](https://github.com/vasanthk/how-web-works) What happens behind the scenes when we type www.google.com in a browser? - GitHub - vasanthk/how-web-works: What happens behind the scenes when we type www.google.com in a browser? GitHub - kamranahmedse/developer-roadmap: Interactive roadmaps, guides and other educational content to help developers grow in their careers. [](https://github.com/kamranahmedse/developer-roadmap) Interactive roadmaps, guides and other educational content to help developers grow in their careers. - GitHub - kamranahmedse/developer-roadmap: Interactive roadmaps, guides and other educational content to help developers grow in their careers. GitHub - apptension/developer-handbook: An opinionated guide on how to become a professional Web/Mobile App Developer. [](https://github.com/apptension/developer-handbook) An opinionated guide on how to become a professional Web/Mobile App Developer. - GitHub - apptension/developer-handbook: An opinionated guide on how to become a professional Web/Mobile App Developer. ProfileMe.dev | Create an amazing GitHub profile in minutes [](https://www.profileme.dev/) ProfileMe.dev | Create an amazing GitHub profile in minutes GitHub - Kristories/awesome-guidelines: A curated list of high quality coding style conventions and standards. [](https://github.com/Kristories/awesome-guidelines) A curated list of high quality coding style conventions and standards. - GitHub - Kristories/awesome-guidelines: A curated list of high quality coding style conventions and standards. GitHub - tiimgreen/github-cheat-sheet: A list of cool features of Git and GitHub. [](https://github.com/tiimgreen/github-cheat-sheet) A list of cool features of Git and GitHub. Contribute to tiimgreen/github-cheat-sheet development by creating an account on GitHub. GitHub - andreasbm/web-skills: A visual overview of useful skills to learn as a web developer [](https://github.com/andreasbm/web-skills) A visual overview of useful skills to learn as a web developer - GitHub - andreasbm/web-skills: A visual overview of useful skills to learn as a web developer GitHub - Ebazhanov/linkedin-skill-assessments-quizzes: Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers [](https://github.com/Ebazhanov/linkedin-skill-assessments-quizzes) Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers - GitHub - Ebazhanov/linkedin-skill-assessments-quizzes: Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers Blockchain/Crypto Dashboards [](https://dune.com/) Blockchain ecosystem analytics by and for the community. Explore and share data from Ethereum, xDai, Polygon, Optimism, BSC and Solana for free. Introduction - The Anchor Book v0.24.0 [](https://book.anchor-lang.com/introduction/introduction.html) Crypto & Fiat Exchange Super App | Trade, Save & Spend | hi [](https://hi.com/) Buy, Trade, Send and Earn Crypto & Fiat. Deposit Bitcoin, ETH, USDT and other cryptos and start earning. Get the hi Debit Card and Multi-Currency IBAN Account. Moralis Web3 - Enterprise-Grade Web3 APIs [](https://moralis.io/) Bridge the development gap between Web2 and Web3 with Moralis’ powerful Web3 APIs. Mirror [](https://mirror.xyz/) Built on web3 for web3, Mirror’s robust publishing platform pushes the boundaries of writing online—whether it’s the next big white paper or a weekly community update. Makerdao [](https://blog.makerdao.com/) Sholi — software for Investors & Traders / Sholi MetriX [](https://sholi.io/) Sholi — software for Investors & Traders / Sholi MetriX Stock Trading Quiver Quantitative [](https://www.quiverquant.com/) Quiver Quantitative Chart Prime - The only tool you'll need for trading assets across all markets [](https://chartprime.com/) ChartPrime offers a toolkit that will take your trading game to the next level. Visit our site for a full rundown of features and helpful tutorials. Learning Hacker Rank [](https://www.hackerrank.com/) Coderbyte | Code Screening, Challenges, & Interview Prep [](https://coderbyte.com/) Improve your coding skills with our library of 300+ challenges and prepare for coding interviews with content from leading technology companies. Competitive Programming | Participate & Learn | CodeChef [](https://www.codechef.com/) Learn competitive programming with the help of CodeChef's coding competitions. Take part in these online coding contests to level up your skills Learn to Code - for Free | Codecademy [](https://www.codecademy.com/) Learn the technical skills to get the job you want. Join over 50 million people choosing Codecademy to start a new career (or advance in their current one). Free Code Camp [](https://www.freecodecamp.org/) Learn to Code — For Free Sololearn: Learn to Code [](https://www.sololearn.com/home) Join Now to learn the basics or advance your existing skills Mimo: The coding app you need to learn to code! Python, HTML, JavaScript [](https://getmimo.com/) Join more than 17 million learners worldwide. Learn to code for free. Learn Python, JavaScript, CSS, SQL, HTML, and more with our free code learning app. Free for developers [](https://free-for.dev/#/) Your Career in Web Development Starts Here | The Odin Project [](https://www.theodinproject.com/) The Odin Project empowers aspiring web developers to learn together for free Code Learning Games CheckiO - coding games and programming challenges for beginner and advanced [](https://checkio.org/) CheckiO - coding websites and programming games. Improve your coding skills by solving coding challenges and exercises online with your friends in a fun way. Exchanges experience with other users online through fun coding activities Coding for Kids | Game-Based Programming | CodeMonkey [](https://www.codemonkey.com/) CodeMonkey is a leading coding for kids program. Through its award-winning courses, millions of students learn how to code in real programming languages. Coding Games and Programming Challenges to Code Better [](https://www.codingame.com/) CodinGame is a challenge-based training platform for programmers where you can play with the hottest programming topics. Solve games, code AI bots, learn from your peers, have fun. Learn VIM while playing a game - VIM Adventures [](https://vim-adventures.com/) VIM Adventures is an online game based on VIM's keyboard shortcuts. It's the "Zelda meets text editing" game. So come have some fun and learn some VIM! CodeCombat - Coding games to learn Python and JavaScript [](https://codecombat.com/) Learn typed code through a programming game. Learn Python, JavaScript, and HTML as you solve puzzles and learn to make your own coding games and websites. Design Useberry - Codeless prototype analytics [](https://www.useberry.com/) User testing feedback & rich insights in minutes, not months! Figma: the collaborative interface design tool. [](https://www.figma.com/) Build better products as a team. Design, prototype, and gather feedback all in one place with Figma. Dribbble - Discover the World’s Top Designers & Creative Professionals [](https://dribbble.com/) Find Top Designers & Creative Professionals on Dribbble. We are where designers gain inspiration, feedback, community, and jobs. Your best resource to discover and connect with designers worldwide. Photopea | Online Photo Editor [](https://www.photopea.com/) Photopea Online Photo Editor lets you edit photos, apply effects, filters, add text, crop or resize pictures. Do Online Photo Editing in your browser for free! Toools.design – An archive of 1000+ Design Resources [](https://www.toools.design/) A growing archive of over a thousand design resources, weekly updated for the community. Discover highly useful design tools you never thought existed. All Online Tools in One Box | 10015 Tools [](https://10015.io/) All online tools you need in one box for free. Build anything online with “all-in-one toolbox”. All tools are easy-to-use, blazing fast & free. Phase - Digital Design Reinvented| Phase [](https://phase.com/) Design and prototype websites and apps visually and intuitively, in a new powerful product reworked for the digital age. Animated Backgrounds [](https://animatedbackgrounds.me/) A Collection of 30+ animated backgrounds for websites and blogs.With Animated Backgrounds, set a simple, elegant background animations on your websites and blogs. Trianglify.io · Low Poly Pattern Generator [](https://trianglify.io/) Trianglify.io is a tool for generating low poly triangle patterns that can be used as wallpapers and website assets. Cool Backgrounds [](https://coolbackgrounds.io/) Explore a beautifully curated selection of cool backgrounds that you can add to blogs, websites, or as desktop and phone wallpapers. SVG Repo - Free SVG Vectors and Icons [](https://www.svgrepo.com/) Free Vectors and Icons in SVG format. ✅ Download free mono or multi color vectors for commercial use. Search in 300.000+ Free SVG Vectors and Icons. Microcopy - Short copy text for your website. [](https://www.microcopy.me/) Search micro UX copy text: slogans, headlines, notifications, CTA, error messages, email, account preferences, and much more. 3D icons and icon paks - Free3Dicon [](https://free3dicon.com/) All 3D icons you need in one place. This is a collection of free, beautiful, trending 3D icons, that you can use in any project. Love 3D Icon [](https://free3dicons.com/) Downloads free 3D icons GIMP - GNU Image Manipulation Program [](https://www.gimp.org/) GIMP - The GNU Image Manipulation Program: The Free and Open Source Image Editor blender.org - Home of the Blender project - Free and Open 3D Creation Software [](https://www.blender.org/) The Freedom to Create 3D Design Software | 3D Modeling on the Web | SketchUp [](https://www.sketchup.com/) SketchUp is a premier 3D design software that truly makes 3D modeling for everyone, with a simple to learn yet robust toolset that empowers you to create whatever you can imagine. Free Logo Maker - Create a Logo in Seconds - Shopify [](https://www.shopify.com/tools/logo-maker) Free logo maker tool to generate custom design logos in seconds. This logo creator is built for entrepreneurs on the go with hundreds of templates, free vectors, fonts and icons to design your own logo. The easiest way to create business logos online. All your design tools in one place | Renderforest [](https://www.renderforest.com/) Time to get your brand noticed. Create professional videos, logos, mockups, websites, and graphics — all in one place. Get started now! Prompt Hero [](https://prompthero.com/) Type Scale - A Visual Calculator [](https://type-scale.com/) Preview and choose the right type scale for your project. Experiment with font size, scale and different webfonts. DreamFusion: Text-to-3D using 2D Diffusion [](https://dreamfusion3d.github.io/) DreamFusion: Text-to-3D using 2D Diffusion, 2022. The branding style guidelines documents archive [](https://brandingstyleguides.com/) Welcome to the brand design manual documents directory. Search over our worldwide style assets handpicked collection, access to PDF documents for inspiration. Super designer | Create beautiful designs with a few clicks [](https://superdesigner.co/) Create beautiful designs with a few clicks. Simple design tools to generate unique patterns, backgrounds, 3D shapes, colors & images for social media, websites and more Readymag—a design tool to create websites without coding [](https://readymag.com/) Meet the most elegant, simple and powerful web-tool for designing websites, presentations, portfolios and all kinds of digital publications. ffflux: Online SVG Fluid Gradient Background Generator | fffuel [](https://fffuel.co/ffflux/) SVG generator to make fluid gradient backgrounds that feel organic and motion-like. Perfect to add a feeling of motion and fluidity to your web designs. Generate unique SVG design assets | Haikei [](https://haikei.app/) A web-based design tool to generate unique SVG design assets for websites, social media, blog posts, desktop and mobile wallpapers, posters, and more! Our generators let you discover, customize, randomize, and export generative SVG design assets ready to use with your favorite design tools. UI/UX - Inspirational Free Website Builder Software | 10,000+ Free Templates [](https://nicepage.com/) Nicepage is your website builder software breaking limitations common for website builders with revolutionary freehand positioning. 7000+ Free Templates. Easy Drag-n-Drop. No coding. Mobile-friendly. Clean HTML. Super designer | Create beautiful designs with a few clicks [](https://superdesigner.co/) Create beautiful designs with a few clicks. Simple design tools to generate unique patterns, backgrounds, 3D shapes, colors & images for social media, websites and more Pika – Create beautiful mockups from screenshots [](https://pika.style/) Quickly create beautiful website and device mockup from screenshot. Pika lets you capture website screenshots form URL, add device and browser frames, customize background and more LiveTerm [](https://liveterm.vercel.app/) Minimal Gallery – Web design inspiration [](https://minimal.gallery/) For the love of beautiful, clean and functional websites. Awwwards - Website Awards - Best Web Design Trends [](https://www.awwwards.com/) Awwwards are the Website Awards that recognize and promote the talent and effort of the best developers, designers and web agencies in the world. Design Systems For Figma [](https://www.designsystemsforfigma.com/) A collection of Design Systems for Figma from all over the globe. Superside: Design At Scale For Ambitious Brands [](https://www.superside.com/) We are an always-on design company. Get a team of dedicated designers, speedy turnarounds, magical creative collaboration tech and the top 1% of global talent. UXArchive - Made by Waldo [](https://uxarchive.com/) UXArchive the world's largest library of mobile user flows. Be inspired to design the best user experiences. Search by Muzli [](https://search.muz.li/) Search, discover, test and create beautiful color palettes for your projects Siteinspire | Web Design Inspiration [](https://www.siteinspire.com/) SAVEE [](https://savee.it/) The best way to save and share inspiration. A little corner of the internet to find good landing page copywriting examples [](https://greatlandingpagecopy.com/) A little corner of the internet to find great landing page copywriting examples. The Best Landing Page Examples For Design Inspiration - SaaS Landing Page [](https://saaslandingpage.com/) SaaS Landing Page showcases the best landing page examples created by top-class SaaS companies. Get ideas and inspirations for your next design project. Websites Free templates Premium Bootstrap Themes and Templates: Download @ Creative Tim [](https://www.creative-tim.com/) UI Kits, Templates and Dashboards built on top of Bootstrap, Vue.js, React, Angular, Node.js and Laravel. Join over 2,014,387+ creatives to access all our products! Free Bootstrap Themes, Templates, Snippets, and Guides - Start Bootstrap [](https://startbootstrap.com/) Start Bootstrap develops free to download, open source Bootstrap 5 themes, templates, and snippets and creates guides and tutorials to help you learn more about designing and developing with Bootstrap. Free Website Templates [](https://freewebsitetemplates.com/) Get your free website templates here and use them on your website without needing to link back to us. One Page Love - One Page Website Inspiration and Templates [](https://onepagelove.com/) One Page Love is a One Page website design gallery showcasing the best Single Page websites, templates and resources. Free CSS | 3400 Free Website Templates, CSS Templates and Open Source Templates [](https://www.free-css.com/) Free CSS has 3400 free website templates, all templates are free CSS templates, open source templates or creative commons templates. Free Bootstrap Themes and Website Templates | BootstrapMade [](https://bootstrapmade.com/) At BootstrapMade, we create beautiful website templates and bootstrap themes using Bootstrap, the most popular HTML, CSS and JavaScript framework. Free and Premium Bootstrap Themes, Templates by Themesberg [](https://themesberg.com/) Free and Premium Bootstrap themes, templates, admin dashboards and UI kits used by over 38820 web developers and software companies HTML, Vue.js and React templates for startup landing pages - Cruip [](https://cruip.com/) Cruip is a gallery of premium and free HTML, Vue.js and React templates for startups and SaaS. Free Website Templates Download | WordPress Themes - W3Layouts [](https://w3layouts.com/) Want to download free website templates? W3Layouts WordPress themes and website templates are built with responsive web design techniques. Download now! Free HTML Landing Page Templates and UI Kits | UIdeck [](https://uideck.com/) Free HTML Landing Page Templates, Bootstrap Themes, React Templates, HTML Templates, Tailwind Templates, and UI Kits. Create Online Graphics Snappa - Quick & Easy Graphic Design Software [](https://snappa.com/) Snappa makes it easy to create any type of online graphic. Create & publish images for social media, blogs, ads, and more! Canva [](https://www.canva.com/) Polotno Studio - Make graphical designs [](https://studio.polotno.com) Free online design editor. Create images for social media, youtube previews, facebook covers Free Logo Maker: Design Custom Logos | Adobe Express [](https://www.adobe.com/express/create/logo) The Adobe Express logo maker is instant, intuitive, and intelligent. Use it to generate a wide range of possibilities for your own logo. Photo Editor: Fotor – Free Online Photo Editing & Image Editor [](https://www.fotor.com/) Fotor's online photo editor helps you edit photos with free online photo editing tools. Crop photos, resize images, and add effects/filters, text, and graphics in just a few clicks. Photoshop online has never been easier with Fotor's free online photo editor. VistaCreate – Free Graphic Design Software with 70,000+ Free Templates [](https://create.vista.com/) Looking for free graphic design software? Easily create professional designs with VistaCreate, a free design tool with powerful features and 50K+ ready-made templates Draw Freely | Inkscape [](https://inkscape.org/) Inkscape is professional quality vector graphics software which runs on Linux, Mac OS X and Windows desktop computers. Visual & Video Maker Trusted By 11 Million Users - Piktochart [](https://piktochart.com/) With Piktochart, you can create professional-looking infographics, flyers, posters, charts, videos, and more. No design experience needed. Start for free. The Web's Favorite Online Graphic Design Tool | Stencil [](https://getstencil.com/) Stencil is a fantastically easy-to-use online graphic design tool and image editor built for business owners, social media marketers, and bloggers. Pablo by Buffer - Design engaging images for your social media posts in under 30 seconds [](https://pablo.buffer.com/) Buffer makes it super easy to share any page you're reading. Keep your Buffer topped up and we automagically share them for you through the day. Free Online Graphic Design Software | Create stunning designs in seconds. [](https://desygner.com/) Easy drag and drop graphic design tool for anyone to use with 1000's of ready made templates. Create & print professional business cards, flyers, social posts and more. Color Pallet Color Palettes for Designers and Artists - Color Hunt [](https://colorhunt.co/) Discover the newest hand-picked color palettes of Color Hunt. Get color inspiration for your design and art projects. Coolors - The super fast color palettes generator! [](https://coolors.co/) Generate or browse beautiful color combinations for your designs. Get color palette inspiration from nature - colorpalettes.earth [](https://colorpalettes.earth/) Color palettes inspired by beautiful nature photos Color Palette Generator - Create Beautiful Color Schemes [](https://colors.muz.li/) Search, discover, test and create beautiful color palettes for your projects A Most Useful Color Picker | 0to255 [](https://0to255.com/) Find lighter and darker colors based on any color. Discover why over two million people have used 0to255 to choose colors for their website, logo, room interior, and print design projects. Colour Contrast Checker [](https://colourcontrast.cc/) Check the contrast between different colour combinations against WCAG standards Fonts Google Fonts [](https://fonts.google.com/) Making the web more beautiful, fast, and open through great typography Fonts In Use – Type at work in the real world. [](https://fontsinuse.com/) A searchable archive of typographic design, indexed by typeface, format, and topic. Wordmark - Helps you choose fonts! [](https://wordmark.it/) Wordmark helps you choose fonts by quickly displaying your text with your fonts. OH no Type Company [](https://ohnotype.co/) OH no Type Co. Retail and custom typefaces. Life’s a thrill, fonts are chill! Illustrations Illustrations | unDraw [](https://undraw.co/illustrations) The design project with open-source illustrations for any idea you can imagine and create. Create beautiful websites, products and applications with your color, for free. Design Junction [](https://designjunction.xyz/) Design Junction is a one-stop resource library for Designers and Creatives with curated list of best resources handpicked from around the web Humaaans: Mix-&-Match illustration library [](https://www.humaaans.com/) Mix-&-match illustrations of people with a design library for InVIsion Studio and Sketch. Stubborn - Free Illustrations Generator [](https://stubborn.fun/) Free illustrations generator for Figma and Sketch. Get the opportunity to design your characters using symbols and styles. Open Peeps, Hand-Drawn Illustration Library [](https://www.openpeeps.com/) Open Peeps is a hand-drawn illustration library to create scenes of people. You can use them in product illustration, marketing, comics, product states, user flows, personas, storyboarding, quinceañera invitations, or whatever you want! ⠀ Reshot | Free icons & illustrations [](https://www.reshot.com/) Design freely with instant downloads of curated SVG icons and vector illustrations. All free with commercial licensing. No attribution required. Blush: Illustrations for everyone [](https://blush.design/) Blush makes it easy to add free illustrations to your designs. Play with fully customizable graphics made by artists across the globe. Mockups Angle 4 - 5000+ Device Mockups for Figma, Sketch and XD [](https://angle.sh/) Vector mockups for iPhone, iPad, Android and Mac devices, including the new iPhone 13, Pro, Pro Max and Mini. Perfect for presenting your apps. Huge library of components, compositions, wallpapers and plugins made for Figma, Sketch and XD. Make Mockups, Logos, Videos and Designs in Seconds [](https://placeit.net/) Get unlimited downloads on all our 100K templates! You can make a logo, video, mockup, flyer, business card and social media image in seconds right from your browser. Free and premium tools for graphic designers | Lstore Graphics [](https://www.ls.graphics/) Free and premium mockups, UI/UX tools, scene creators for busy designers Logo Design & Brand Identity Platform for Entrepreneurs | Looka [](https://looka.com/) Logojoy is now Looka! Design a Logo, make a website, and create a Brand Identity you’ll love with the power of Artificial Intelligence. 100% free to use. Create stunning product mockups easily and online - Smartmockups [](https://smartmockups.com/) Smartmockups enables you to create stunning high-resolution mockups right inside your browser within one interface across multiple devices. Previewed - Free mockup generator for your app [](https://previewed.app/) Join Previewed to create stunning 3D image shots and animations for your app. Choose from hundreds of ready made mockups, or create your own. Free Design Software - Graphic Online Maker - Glorify [](https://www.glorify.com/) Create professional and high converting social media posts, ads, infographics, presentations, and more with Glorify, a free design software & graphic maker. Other BuiltWith Technology Lookup [](https://builtwith.com/) Web technology information profiler tool. Find out what a website is built with. Compress JPEG Images Online [](https://compressjpeg.com/) Compress JPEG images and photos for displaying on web pages, sharing on social networks or sending by email. PhotoRoom - Remove Background and Create Product Pictures [](https://www.photoroom.com/) Create product and portrait pictures using only your phone. Remove background, change background and showcase products. Magic Eraser - Remove unwanted things from images in seconds [](https://www.magiceraser.io/) Magic Eraser - Use AI to remove unwanted things from images in seconds. Upload an image, mark the bit you need removed, download the fixed up image. Compressor.io - optimize and compress JPEG photos and PNG images [](https://compressor.io/) Optimize and compress JPEG, PNG, SVG, GIF and WEBP images online. Compress, resize and rename your photos for free. Remove Video Background – Unscreen [](https://www.unscreen.com/) Remove the background of any video - 100% automatically, online & free! Goodbye Greenscreen. Hello Unscreen. Noun Project: Free Icons & Stock Photos for Everything [](https://thenounproject.com/) Noun Project features the most diverse collection of icons and stock photos ever. Download SVG and PNG. Browse over 5 million art-quality icons and photos. Design Principles [](https://principles.design/) An Open Source collection of Design Principles and methods Shapefest™ - A massive library of free 3D shapes [](https://www.shapefest.com/) A massive free library of beautifully rendered 3D shapes. 160,000+ high resolution PNG images in one cohesive library. Learning UX Degreeless.design - Everything I Learned in Design School [](https://degreeless.design/) This is a list of everything I've found useful in my journey of learning design, and an ongoing list of things I think you should read. For budding UX, UI, Interaction, or whatever other title designers. UX Tools | Practical UX skills and tools [](https://uxtools.co/) Lessons and resources from two full-time product designers. Built For Mars [](https://builtformars.com/) On a mission to help the world build better user experiences by demystifying UX. Thousands of hours of research packed into UX case studies. Case Study Club – Curated UX Case Study Gallery [](https://www.casestudy.club/) Case Study Club is the biggest curated gallery of the best UI/UX design case studies. Get inspired by industry-leading designers, openly sharing their UX process. The Guide to Design [](https://start.uxdesign.cc/) A self-guided class to help you get started in UX and answer key questions about craft, design, and career Uxcel - Where design careers are built [](https://app.uxcel.com/explore) Available on any device anywhere in the world, Uxcel is the best way to improve and learn UX design online in just 5 minutes per day. UI & UX Design Tips by Jim Raptis. [](https://www.uidesign.tips/) Learn UI & UX Design with practical byte-sized tips and in-depth articles from Jim Raptis. Entrepreneur Instant Username Search [](https://instantusername.com/#/) Instant Username Search checks out if your username is available on more than 100 social media sites. Results appear instantly as you type. Flourish | Data Visualization & Storytelling [](https://flourish.studio/) Beautiful, easy data visualization and storytelling PiPiADS - #1 TikTok Ads Spy Tool [](https://www.pipiads.com/) PiPiADS is the best tiktok ads spy tool .We provide tiktok advertising,advertising on tiktok,tiktok ads examples,tiktok ads library,tiktok ads best practices,so you can understand the tiktok ads cost and master the tiktok ads 2021 and tiktok ads manager. Minea - The best adspy for product search in ecommerce and dropshipping [](https://en.minea.com/) Minea is the ultimate e-commerce product search tool. Minea tracks all ads on all networks. Facebook Ads, influencer product placements, Snapspy, all networks are tracked. Stop paying adspy 149€ for one network and discover Minea. AdSpy [](https://adspy.com/) Google Trends [](https://trends.google.com/) ScoreApp: Advanced Quiz Funnel Marketing | Make a Quiz Today [](https://www.scoreapp.com/) ScoreApp makes quiz funnel marketing easy, so you can attract relevant warm leads, insightful data and increase your sales. Try for free today Mailmodo - Send Interactive Emails That Drive Conversions [](https://www.mailmodo.com/) Use Mailmodo to create and send interactive emails your customers love. Drive conversions and get better email ROI. Sign up for a free trial now. 185 Top E-Commerce Sites Ranked by User Experience Performance – Baymard Institute [](https://baymard.com/ux-benchmark) See the ranked UX performance of the 185 largest e-commerce sites in the US and Europe. The chart summarizes 50,000+ UX performance ratings. Metricool - Analyze, manage and measure your digital content [](https://metricool.com/) Social media scheduling, web analytics, link in bio and reporting. Metricool is free per live for one brand. START HERE Visualping: #1 Website change detection, monitoring and alerts [](https://visualping.io/) More than 1.5 millions users monitor changes in websites with Visualping, the No1 website change detection, website checker, webpage change monitoring and webpage change detection tool. Gumroad – Sell what you know and see what sticks [](https://gumroad.com/) Gumroad is a powerful, but simple, e-commerce platform. We make it easy to earn your first dollar online by selling digital products, memberships and more. Product Hunt – The best new products in tech. [](https://www.producthunt.com/) Product Hunt is a curation of the best new products, every day. Discover the latest mobile apps, websites, and technology products that everyone's talking about. 12ft Ladder [](https://12ft.io/) Show me a 10ft paywall, I’ll show you a 12ft ladder. namecheckr | Social and Domain Name Availability Search For Brand Professionals [](https://www.namecheckr.com/) Social and Domain Name Availability Search For Brand Professionals Excel AI Formula Generator - Excelformulabot.com [](https://excelformulabot.com/) Transform your text instructions into Excel formulas in seconds with the help of AI. Z-Library [](https://z-lib.org/) Global Print On Demand Platform | Gelato [](https://www.gelato.com/) Create and sell custom products online. With local production in 33 countries, easy integration, and 24/7 customer support, Gelato is an all-in-one platform. Freecycle: Front Door [](https://freecycle.org/) Free eBooks | Project Gutenberg [](https://www.gutenberg.org/) Project Gutenberg is a library of free eBooks. Convertio — File Converter [](https://convertio.co/) Convertio - Easy tool to convert files online. More than 309 different document, image, spreadsheet, ebook, archive, presentation, audio and video formats supported. Namechk [](https://namechk.com/) Crazy Egg Website — Optimization | Heatmaps, Recordings, Surveys & A/B Testing [](https://www.crazyegg.com/) Use Crazy Egg to see what's hot and what's not, and to know what your web visitors are doing with tools, such as heatmaps, recordings, surveys, A/B testing & more. Ifttt [](https://ifttt.com/) Also Asked [](https://alsoasked.com/) Business Name Generator - Easily create Brandable Business Names - Namelix [](https://namelix.com/) Namelix uses artificial intelligence to create a short, brandable business name. Search for domain availability, and instantly generate a logo for your new business Merch Informer [](https://merchinformer.com/) Headline Generator [](https://www.title-generator.com/) Title Generator: create 700 headlines with ONE CLICK: Content Ideas + Catchy Headlines + Ad Campaign E-mail Subject Lines + Emotional Titles. Simple - Efficient - One Click Make [](https://www.make.com/en) Create and add calculator widgets to your website | CALCONIC_ [](https://www.calconic.com/) Web calculator builder empowers you to choose from a pre-made templates or build your own calculator widgets from a scratch without any need of programming knowledge Boost Your Views And Subscribers On YouTube - vidIQ [](https://vidiq.com/) vidIQ helps you acquire the tools and knowledge needed to grow your audience faster on YouTube and beyond. Learn More Last Pass [](https://www.lastpass.com/) Starter Story: Learn How People Are Starting Successful Businesses [](https://www.starterstory.com/) Starter Story interviews successful entrepreneurs and shares the stories behind their businesses. In each interview, we ask how they got started, how they grew, and how they run their business today. How To Say No [](https://www.starterstory.com/how-to-say-no) Saying no is hard, but it's also essential for your sanity. Here are some templates for how to say no - so you can take back your life. Think with Google - Discover Marketing Research & Digital Trends [](https://www.thinkwithgoogle.com/) Uncover the latest marketing research and digital trends with data reports, guides, infographics, and articles from Think with Google. ClickUp™ | One app to replace them all [](https://clickup.com/) Our mission is to make the world more productive. To do this, we built one app to replace them all - Tasks, Docs, Goals, and Chat. The Manual [](https://manual.withcompound.com/) Wealth-planning resources for founders and startup employees Software for Amazon FBA Sellers & Walmart Sellers | Helium 10 [](https://www.helium10.com/) If you're looking for the best software for Amazon FBA & Walmart sellers on the market, check out Helium 10's capabilities online today! Buffer: All-you-need social media toolkit for small businesses [](https://buffer.com/) Use Buffer to manage your social media so that you have more time for your business. Join 160,000+ small businesses today. CPGD — The Consumer Packaged Goods Directory [](https://www.cpgd.xyz/) The Consumer Packaged Goods Directory is a platform to discover new brands and resources. We share weekly trends in our newsletter and partner with services to provide vetted, recommended platforms for our Directory brands. Jungle Scout [](https://www.junglescout.com/) BuzzSumo | The World's #1 Content Marketing Platform [](https://buzzsumo.com/) BuzzSumo powers the strategies of 500k+ marketers, with content marketing data on 8b articles, 42m websites, 300t engagements, 500k journalists & 492m questions. Login - Capital [](https://app.capital.xyz/) Raise, hold, spend, and send funds — all in one place. Marketing Pictory – Video Marketing Made Easy - Pictory.ai [](https://pictory.ai/) Pictory's powerful AI enables you to create and edit professional quality videos using text, no technical skills required or software to download. Tolstoy | Communicate with interactive videos [](https://www.gotolstoy.com/) Start having face-to-face conversations with your customers. Create Email Marketing Your Audience Will Love - MailerLite [](https://www.mailerlite.com/) Email marketing tools to grow your audience faster and drive revenue smarter. Get free access to premium features with a 30-day trial! Sign up now! Hypefury - Schedule & Automate Social Media Marketing [](https://hypefury.com/) Save time on social media while creating more value, and growing your audience faster. Schedule & automate your social media experience! Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. Online Email & Lead Scraper | Klean Leads [](https://www.kleanleads.com/) Klean Leads is an online email scraper & email address finder. Use it to book more appointments, get more replies, and close more sales. PhantomBuster [](https://phantombuster.com/) Call to Action Examples - 300+ CTA Phrases [](https://ctaexamples.com/) See the best CTA example in every situation covered by the library of 300+ CTA goals. Use the examples to create your own CTAs in minutes. Creative Center: one-stop creative solution for TikTok [](https://ads.tiktok.com/business/creativecenter/pc/en?from=001010) Come to get your next great idea for TikTok. Here you can find the best performing ads, viral videos, and trending hashtags across regions and verticals. Groove.cm GrooveFunnels, GrooveMail with CRM and Digital Marketing Automation Platform - Groove.cm with GrooveFunnels, GroovePages, GrooveKart [](https://groove.cm/) Groove is a website creator, page builder, sales funnel maker, membership site platform, email autoresponder, blog tool, shopping cart system, ecommerce store solution, affiliate manager, video marketing software and more apps to help build your online business. SurveyMonkey: The World’s Most Popular Free Online Survey Tool [](https://www.surveymonkey.com/) Use SurveyMonkey to drive your business forward by using our free online survey tool to capture the voices and opinions of the people who matter most to you. Video Maker | Create Videos Online | Promo.com [](https://promo.com/) Free customizable video maker to help boost your business. Video creator for ads, social media, product and explainer videos, and for anything else you need! beehiiv — The newsletter platform built for growth [](https://www.beehiiv.com/) Access the best tools available in email, helping your newsletter scale and monetize like never before. GetResponse | Professional Email Marketing for Everyone [](https://www.getresponse.com/) No matter your level of expertise, we have a solution for you. At GetResponse, it's email marketing done right. Start your free account today! Search Email Newsletter Archives : Email Tuna [](https://emailtuna.com/) Explore newsletters without subscribing. Get email design ideas, discount coupon codes and exclusive newsletters deals. Database of email newsletters archived from all over the internet. Other Tools Simplescraper — Scrape Websites and turn them into APIs [](https://simplescraper.io/) Web scraping made easy — a powerful and free Chrome extension for scraping websites in your browser, automated in the cloud, or via API. No code required. Exploding Topics - Discover the hottest new trends. [](https://explodingtopics.com/) See new market opportunities, trending topics, emerging technology, hot startups and more on Exploding Topics. Scribe | Visual step-by-step guides [](https://scribehow.com/) By capturing your process while you work, Scribe automatically generates a visual guide, ready to share with the click of a button. Get It Free – The internet's BEST place to find free stuff! [](https://getitfree.us/) The internet's BEST place to find free stuff! Inflact by Ingramer – Marketing toolkit for Instagram [](https://inflact.com/) Sell on Instagram, build your audience, curate content with the right set of tools. Free Online Form Builder & Form Creator | Jotform [](https://www.jotform.com/) We believe the right form makes all the difference. Go from busywork to less work with powerful forms that use conditional logic, accept payments, generate reports, and automate workflows. Manage Your Team’s Projects From Anywhere | Trello [](https://trello.com/en) Trello is the ultimate project management tool. Start up a board in seconds, automate tedious tasks, and collaborate anywhere, even on mobile. TikTok hashtag generator - tiktokhashtags.com [](https://tiktokhashtags.com/) Find out which are the best hashtags for your TikTok post. Create Infographics, Reports and Maps - Infogram [](https://infogram.com/) Infogram is an easy to use infographic and chart maker. Create and share beautiful infographics, online reports, and interactive maps. Make your own here. Confetto - Create Instagram content in minutes [](https://www.confet.to/) Confetto is an all-in-one social media marketing tool built for SMBs and Social Media Managers. Confetto helps you create high-quality content for your audience that maximizes your reach and engagement on social media. Design, copy-write, plan and schedule content all in one place. Find email addresses in seconds • Hunter (Email Hunter) [](https://hunter.io/) Hunter is the leading solution to find and verify professional email addresses. Start using Hunter and connect with the people that matter for your business. PlayPhrase.me: Site for cinema archaeologists. [](https://playphrase.me/) Travel and explore the world of cinema. Largest collection of video quotes from movies on the web. #1 Free SEO Tools → SEO Review Tools [](https://www.seoreviewtools.com/) SEO Review Tools: 42+ Free Online SEO Tools build with ❤! → Rank checker → Domain Authority Checker → Keyword Tool → Backlink Checker Podcastle: Seamless Podcast Recording & Editing [](https://podcastle.ai/) Podcastle is the simplest way to create professional-quality podcasts. Record, edit, transcribe, and export your content with the power of AI, in an intuitive web-based platform. Save Ads from TikTok & Facebook Ad Library - Foreplay [](https://www.foreplay.co/) The best way to save ads from TikTok Creative Center and Facebook Ad Library, Organize them into boards and share ad inspiration with your team. Supercharge your creative strategy. SiteRight - Automate Your Business [](https://www.siteright.co/) SiteRight combines the abilities of multiple online resources into a single dashboard allowing you to have full control over how you manage your business. Diffchecker - Compare text online to find the difference between two text files [](https://www.diffchecker.com/) Diffchecker will compare text to find the difference between two text files. Just paste your files and click Find Difference! Yout.com [](https://yout.com/) Yout.com allows you to record videos from YouTube, FaceBook, SoundCloud, VK and others too many formats with clipping. Intuitively easy to use, with Yout the Internet DVR, with a bit of extra. AI Content Generation | Competitor Analysis - Predis.ai [](https://predis.ai/) Predis helps brands and influencers communicate better on social media by providing AI-powered content strategy analysis, content and hashtag recommendations. Castr | #1 Live Video Streaming Solution With Video Hosting [](https://castr.io/) Castr is a live video streaming solution platform that delivers enterprise-grade live videos globally with CDN. Live event streaming, video hosting, pre-recorded live, multi stream – all in one place using Castr. Headliner - Promote your podcast, radio show or blog with video [](https://www.headliner.app/) Easily create videos to promote your podcast, radio show or blog. Share to Instagram, Facebook, Twitter, YouTube, Linkedin and anywhere video lives Create Presentations, Infographics, Design & Video | Visme [](https://www.visme.co/) Create professional presentations, interactive infographics, beautiful design and engaging videos, all in one place. Start using Visme today. Designrr - Create eBooks, Kindle books, Leadmagnets, Flipbooks and Blog posts from your content in 2 minutes [](https://designrr.io/) Upload any web page, MS Word, Video, Podcast or YouTube and it will create a stunning ebook and convert it to pdf, epub, Kindle or Flipbook. Quick and Easy to use. Full Training, 24x7 Support and Facebook Group Included. SwipeWell | Swipe File Software [](https://www.swipewell.app/) The only Chrome extension dedicated to helping you save, organize, and reference marketing examples (so you never feel stumped). Tango | Create how-to guides, in seconds [](https://www.tango.us/) Tango takes the pain out of documenting processes by automatically generating how-to guides while you work. Empower your team to do their best work. Ad Creative Bank [](https://www.theadcreativebank.com/) Get inspired by ads from across industries, learn new best practices, and start thinking creatively about your brand’s digital creative. Signature Hound • Free Email Signature and Template Generator [](https://signaturehound.com/) Our email signature generator is free and easy to use. Our customizable templates work with Gmail, Outlook, Office 365, Apple Mail and more. Organize All Of Your Marketing In One Place - CoSchedule [](https://coschedule.com/) Get more done in less time with the only work management software for marketers. B Ok - Books [](https://b-ok.xyz/categories) OmmWriter [](https://ommwriter.com/) Ommwriter Rebrandly | Custom URL Shortener, Branded Link Management, API [](https://www.rebrandly.com/) URL Shortener with custom domains. Shorten, brand and track URLs with the industry-leading link management platform. Free to try. API, Short URL, Custom Domains. Common Tools [](https://www.commontools.org/) Book Bolt [](https://bookbolt.io/) Zazzle [](https://www.zazzle.com/) InspiroBot [](https://inspirobot.me/) Download Free Cheat Sheets or Create Your Own! - Cheatography.com: Cheat Sheets For Every Occasion [](https://cheatography.com/) Find thousands of incredible, original programming cheat sheets, all free to download. No Code Chatbot Platform | Free Chatbot Platform | WotNot [](https://wotnot.io/) WotNot is the best no code chatbot platform to build AI bot easily without coding. Deploy bots and live chat on the Website, Messenger, WhatsApp, and more. SpyFu - Competitor Keyword Research Tools for Google Ads PPC & SEO [](https://www.spyfu.com/) Systeme.io - The only tool you need to launch your online business [](https://systeme.io/) Systeme.io has all the tools you need to grow your online business. Click here to create your FREE account! Productivity Temp Mail [](https://temp-mail.org/en/) The Visual Collaboration Platform for Every Team | Miro [](https://miro.com/) Scalable, secure, cross-device and enterprise-ready team collaboration whiteboard for distributed teams. Join 35M+ users from around the world. Grammarly: Free Online Writing Assistant [](https://www.grammarly.com/) Millions trust Grammarly’s free writing app to make their online writing clear and effective. Getting started is simple — download Grammarly’s extension today. Rize · Maximize Your Productivity [](https://rize.io/) Rize is a smart time tracker that improves your focus and helps you build better work habits. Motion | Manage calendars, meetings, projects & tasks in one app [](https://www.usemotion.com/) Automatically prioritize tasks, schedule meetings, and resolve calendar conflicts. Used by over 10k CEOs and professionals to improve focus, get more done, and streamline workday. Notion – One workspace. Every team. [](https://www.notion.so/) We’re more than a doc. Or a table. Customize Notion to work the way you do. Loom: Async Video Messaging for Work | Loom [](https://www.loom.com/) Record your screen, share your thoughts, and get things done faster with async video. Zapier | Automation that moves you forward [](https://zapier.com/) Workflow automation for everyone. Zapier automates your work across 5,000+ app integrations, so you can focus on what matters. Rows — The spreadsheet with superpowers [](https://rows.com/) Combine the power of a spreadsheet with built-in integrations from your business apps. Automate workflows and build tools that make work simpler. Free Online Form Builder | Tally [](https://tally.so/) Tally is the simplest way to create free forms & surveys. Create any type of form in seconds, without knowing how to code, and for free. Highbrow | Learn Something New Every Day. Join for Free! [](https://gohighbrow.com/) Highbrow helps you learn something new every day with 5-minute lessons delivered to your inbox every morning. Join over 400,000 lifelong learners today! Slick Write | Check your grammar. Proofread online. [](https://www.slickwrite.com/#!home) Slick Write is a powerful, FREE application that makes it easy to check your writing for grammar errors, potential stylistic mistakes, and other features of interest. Whether you're a blogger, novelist, SEO professional, or student writing an essay for school, Slick Write can help take your writing to the next level. Reverso [](https://www.reverso.net) Hemingway Editor [](https://hemingwayapp.com/) Web Apps by 123apps - Edit, Convert, Create [](https://123apps.com/) Splitbee – Your all-in-one analytics and conversion platform [](https://splitbee.io/) Track and optimize your online business with Splitbee. Analytics, Funnels, Automations, A/B Testing and more. PDF Tools Free PDF, Video, Image & Other Online Tools - TinyWow [](https://tinywow.com/) Smallpdf.com - A Free Solution to all your PDF Problems [](https://smallpdf.com/) Smallpdf - the platform that makes it super easy to convert and edit all your PDF files. Solving all your PDF problems in one place - and yes, free. Sejda helps with your PDF tasks [](https://www.sejda.com/) Sejda helps with your PDF tasks. Quick and simple online service, no installation required! Split, merge or convert PDF to images, alternate mix or split scans and many other. iLovePDF | Online PDF tools for PDF lovers [](https://www.ilovepdf.com/) iLovePDF is an online service to work with PDF files completely free and easy to use. Merge PDF, split PDF, compress PDF, office to PDF, PDF to JPG and more! Text rewrite QuillBot [](https://quillbot.com/) Pre Post SEO : Online SEO Tools [](https://www.prepostseo.com/) Free Online SEO Tools: plagiarism checker, grammar checker, image compressor, website seo checker, article rewriter, back link checker Wordtune | Your personal writing assistant & editor [](https://www.wordtune.com/) Wordtune is the ultimate AI writing tool that rewrites, rephrases, and rewords your writing! Trusted by over 1,000,000 users, Wordtune strengthens articles, academic papers, essays, emails and any other online content. Aliexpress alternatives CJdropshipping - Dropshipping from Worldwide to Worldwide! [](https://cjdropshipping.com/) China's reliable eCommerce dropshipping fulfillment supplier, helps small businesses ship worldwide, dropship and fulfillment services that are friendly to start-ups and small businesses, Shopify dropshipping. SaleHoo [](https://www.salehoo.com/) Alibaba.com: Manufacturers, Suppliers, Exporters & Importers from the world's largest online B2B marketplace [](https://www.alibaba.com/) Find quality Manufacturers, Suppliers, Exporters, Importers, Buyers, Wholesalers, Products and Trade Leads from our award-winning International Trade Site. Import & Export on alibaba.com Best Dropshipping Suppliers for US + EU Products | Spocket [](https://www.spocket.co/) Spocket allows you to easily start dropshipping top products from US and EU suppliers. Get started for free and see why Spocket consistently gets 5 stars. Best dropshipping supplier to the US [](https://www.usadrop.com/) THE ONLY AMERICAN-MADE FULFILLMENT CENTER IN CHINA. Our knowledge of the Worldwide dropshipping market and the Chinese Supply-Chain can't be beat! 阿里1688 [](https://www.1688.com/) 阿里巴巴（1688.com）是全球企业间（B2B）电子商务的著名品牌，为数千万网商提供海量商机信息和便捷安全的在线交易市场，也是商人们以商会友、真实互动的社区平台。目前1688.com已覆盖原材料、工业品、服装服饰、家居百货、小商品等12个行业大类，提供从原料--生产--加工--现货等一系列的供应产品和服务 Dropshipping Tools Oberlo | Where Self Made is Made [](https://www.oberlo.com/) Start selling online now with Shopify. All the videos, podcasts, ebooks, and dropshipping tools you'll need to build your online empire. Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. SMSBump | SMS Marketing E-Commerce App for Shopify [](https://smsbump.com/) SMSBump is an SMS marketing & automation app for Shopify. Segment customers, recover orders, send campaign text messages with a 35%+ click through rate. AfterShip: The #1 Shipment Tracking Platform [](https://www.aftership.com/) Order status lookup, branded tracking page, and multi-carrier tracking API for eCommerce. Supports USPS, FedEx, UPS, and 900+ carriers worldwide. #1 Dropshipping App | Zendrop [](https://zendrop.com/) Start and scale your own dropshipping business with Zendrop. Sell and easily fulfill your orders with the fastest shipping in the industry. Best Dropshipping Suppliers for US + EU Products | Spocket [](https://www.spocket.co/) Spocket allows you to easily start dropshipping top products from US and EU suppliers. Get started for free and see why Spocket consistently gets 5 stars. Video Editing Jitter • The simplest motion design tool on the web. [](https://jitter.video/) Animate your designs easily. Export your creations as videos or GIFs. All in your browser. DaVinci Resolve 18 | Blackmagic Design [](https://www.blackmagicdesign.com/products/davinciresolve) Professional video editing, color correction, visual effects and audio post production all in a single application. Free and paid versions for Mac, Windows and Linux. Online Video Editor | Video Creator | InVideo [](https://invideo.io/) InVideo's Online Video Editor Helps You Make Professional Videos From Premium Templates, Images, And Music. All your video needs in one place | Clipchamp [](https://clipchamp.com/) Fast-forward your creations with our video editing platform. Start with a video template or record your webcam or screen. Get the pro look with filters, transitions, text and more. Then, export in minutes and share in an instant. Descript | All-in-one audio/video editing, as easy as a doc. [](https://www.descript.com/) Record, transcribe, edit, mix, collaborate, and master your audio and video with Descript. Download for free →. Kapwing — Reach more people with your content [](https://www.kapwing.com/) Kapwing is a collaborative, online content creation platform that you can use to edit video and create content. Join over 10 million modern creators who trust Kapwing to create, edit, and grow their content on every channel. Panzoid [](https://panzoid.com/) Powerful, free online apps and community for creating beautiful custom content. Google Web Designer - Home [](https://webdesigner.withgoogle.com/) Kapwing — Reach more people with your content [](https://www.kapwing.com/) Kapwing is a collaborative, online content creation platform that you can use to edit video and create content. Join over 10 million modern creators who trust Kapwing to create, edit, and grow their content on every channel. ClipDrop [](https://clipdrop.co/) Create professional visuals without a photo studio CapCut [](https://www.capcut.com/) CapCut is an all-in-one online video editing software which makes creation, upload & share easier, with frame by frame track editor, cloud drive etc. VEED - Online Video Editor - Video Editing Made Simple [](https://www.veed.io/) Make stunning videos with a single click. Cut, trim, crop, add subtitles and more. Online, no account needed. Try it now, free. VEED Free Video Maker | Create & Edit Your Videos Easily - Animoto [](https://animoto.com/k/welcome) Create, edit, and share videos with our online video maker. Combine your photos, video clips, and music to make quality videos in minutes. Get started free! Runway - Online Video Editor | Everything you need to make content, fast. [](https://runwayml.com/) Discover advanced video editing capabilities to take your creations to the next level. CreatorKit - A.I. video creator for marketers [](https://creatorkit.com/) Create videos with just one click, using our A.I. video editor purpose built for marketers. Create scroll stopping videos, Instagram stories, Ads, Reels, and TikTok videos. Pixar in a Box | Computing | Khan Academy [](https://www.khanacademy.org/computing/pixar) 3D Video Motions Plask - AI Motion Capture and 3D Animation Tool [](https://plask.ai/) Plask is an all-in-one browser-based AI motion capture tool and animation editor that anybody can use, from motion designers to every day content creators. Captions Captions [](https://www.getcaptions.app/) Say hello to Captions, the only camera and editing app that automatically transcribes, captions and clips your talking videos for you. Stock videos Pexels [](https://www.pexels.com/) Pixabay [](https://pixabay.com/) Mixkit - Awesome free assets for your next video project [](https://mixkit.co/) Download Free Stock Video Footage, Stock Music & Premiere Pro Templates for your next video editing project. All assets can be downloaded for free! Free Stock Video Footage HD 4K Download Royalty-Free Clips [](https://www.videvo.net/) Download free stock video footage with over 300,000 video clips in 4K and HD. We also offer a wide selection of music and sound effect files with over 180,000 clips available. Click here to download royalty-free licensing videos, motion graphics, music and sound effects from Videvo today. Free Stock Video Footage HD Royalty-Free Videos Download [](https://mazwai.com/) Download free stock video footage with clips available in HD. Click here to download royalty-free licensing videos from Mazwai now. Royalty Free Stock Video Footage Clips | Vidsplay.com [](https://www.vidsplay.com/) Royalty Free Stock Video Footage Clips Free Stock Video Footage, Royalty Free Videos for Download [](https://coverr.co/) Download royalty free (for personal and commercial use), unique and beautiful video footage for your website or any project. No attribution required. Stock Photos Beautiful Free Images & Pictures | Unsplash [](https://unsplash.com/) Beautiful, free images and photos that you can download and use for any project. Better than any royalty free or stock photos. When we share, everyone wins - Creative Commons [](https://creativecommons.org/) Creative Commons licenses are 20! Honoring 20 years of open sharing using CC licenses, join us in 2022 to celebrate Better Sharing — advancing universal access to knowledge and culture, and fostering creativity, innovation, and collaboration. Help us reach our goal of raising $15 million for a future of Better Sharing.  20 Years of Better … Read More "When we share, everyone wins" Food Pictures • Foodiesfeed • Free Food Photos [](https://www.foodiesfeed.com/) Download 2000+ food pictures ⋆ The best free food photos for commercial use ⋆ CC0 license Free Stock Photos and Images for Websites & Commercial Use [](https://burst.shopify.com/) Browse thousands of beautiful copyright-free images. All our pictures are free to download for personal and commercial use, no attribution required. EyeEm | Authentic Stock Photography and Royalty-Free Images [](https://www.eyeem.com/) Explore high-quality, royalty-free stock photos for commercial use. License individual images or save money with our flexible subscription and image pack plans. picjumbo: Free Stock Photos [](https://picjumbo.com/) Free stock photos and images for your projects and websites.️ Beautiful 100% free high-resolution stock images with no watermark. Free Stock Photos, Images, and Vectors [](https://www.stockvault.net/) 139.738 free stock photos, textures, backgrounds and graphics for your next project. No attribution required. Free Stock Photos, PNGs, Templates & Mockups | rawpixel [](https://www.rawpixel.com/) Free images, PNGs, stickers, backgrounds, wallpapers, graphic templates and PSD mockups. All safe to use with commercial licenses. Free Commercial Stock Photos & Royalty Free Images | PikWizard [](https://pikwizard.com/) Free images, videos & free stock photos. Unlimited downloads ✓ Royalty-free Images ✓Copyright-free for commercial use ✓ No Attribution Required Design Bundles [](https://designbundles.net/) Stock music Royalty Free Music for video creators | Epidemic Sound [](https://www.epidemicsound.com/) Download premium Royalty free Music and SFX! Our free trial gives you access to over 35,000 tracks and 90,000 sound effects for video, streaming and more! Royalty-Free Music & SFX for Video Creators | Artlist [](https://artlist.io/) Explore the ultimate royalty-free music & sound effects catalogs for unlimited use in YouTube videos, social media & films created by inspiring indie artists worldwide. The go-to music licensing choice for all creators Royalty Free Audio Tracks - Envato Elements [](https://elements.envato.com/audio) Download Royalty Free Stock Audio Tracks for your next project from Envato Elements. Premium, High Quality handpicked Audio files ideal for any genre. License popular music for videos • Lickd [](https://lickd.co/) The only place you can license popular music for videos. Access 1M+ mainstream tracks, plus high-quality stock music for content creators NCS (NoCopyrightSounds) - free music for content creators [](https://ncs.io/) NCS is a Record Label dedicated to giving a platform to the next generation of Artists in electronic music, representing genres from house to dubstep via trap, drum & bass, electro pop and more. Search Engine Optimization Keyword Tool For Monthly Search Volume, CPC & Competition [](https://keywordseverywhere.com/) Keywords Everywhere is a browser add-on for Chrome & Firefox that shows search volume, CPC & competition on multiple websites. Semrush - Online Marketing Can Be Easy [](https://www.semrush.com/) Turn the algorithm into a friend. Make your business visible online with 55+ tools for SEO, PPC, content, social media, competitive research, and more. DuckDuckGo — Privacy, simplified. [](https://duckduckgo.com/) The Internet privacy company that empowers you to seamlessly take control of your personal information online, without any tradeoffs. SEO Software for 360° Analysis of Your Website [](https://seranking.com/) Leading SEO software for business owners, agencies, and SEO specialists. Track your rankings, monitor competitors, spot technical errors, and more. Skyrocket your organic traffic with Surfer [](https://surferseo.com/) Use Surfer to research, write, optimize, and audit! Everything you need to create a comprehensive content strategy that yields real results is right here. Ahrefs - SEO Tools & Resources To Grow Your Search Traffic [](https://ahrefs.com/) You don't have to be an SEO pro to rank higher and get more traffic. Join Ahrefs – we're a powerful but easy to learn SEO toolset with a passionate community. Neon Tools [](https://neontools.io/) Google Index Search [](https://lumpysoft.com/) Google Index Search SEO Backlink Checker & Link Building Toolset | Majestic.com [](https://majestic.com/) Develop backlink strategies with our Link Intelligence data, build the strongest SEO backlink campaigns to drive organic traffic and boost your rankings today. PageOptimizer Pro [](https://pageoptimizer.pro/) Plans Services SEO Consulting Learn SEO About Blog POP SEO Community Podcast Support POP On Page Workshops With Kyle Roof POP Chrome Extension Guide Tutorial Videos Frequently Asked Questions Best Practices Login Cancel Anytime Plans Services SEO Consulting Learn SEO About Blog POP SEO Community Podcast Support POP On Page… Keyword Chef - Keywords for Publishers [](https://keywordchef.com/) Rank Insanely Fast for Keywords Your Competition Can’t Find “Every long-tail keyword I find ends up ranking within a day” – Dane Eyerly, Owner at TextGoods.com Keyword Chef automatically finds and filters keywords for you. Real-time SERP analysis lets you find keywords nearly guaranteed to rank. Try for free → Let’s face it, most keyword tools ... Read more Notifier - Social Listening for Social Media and More! [](https://notifier.so/) Track keywords. Market your product for free. Drive the conversation. Easy. Free Trial. No obligation ever. Simple. Fast. Trusted by Top Companies. Free Keyword Research Tool from Wordtracker [](https://www.wordtracker.com/) The best FREE alternative to the Keyword Planner. Use Wordtracker to reveal 1000s of profitable longtail keywords with up to 10,000 results per search Blog Posts The 60 Hottest Front-end Tools of 2021 | CSS-Tricks - CSS-Tricks [](https://css-tricks.com/hottest-front-end-tools-in-2021/) A complete list of the most popular front-end tools in 2021, according to the Web Tools Weekly newsletter. See which resources made the list. Resume ResumeGlow - AI Powered Resume Builder [](https://resumeglow.com/) Get hired fast with a resume that grabs attention. Designed by a team of HR experts and typographers. Customizable templates with more than a million possible Create Your Job-winning Resume - (Free) Resume maker · Resume.io [](https://resume.io/) Free online resume maker, allows you to create a perfect Resume or Cover Letter in 5 minutes. See how easy it is to write a professional resume - apply for jobs today! Rezi - The Leading AI-Powered Free Resume Builder [](https://www.rezi.ai/) Rezi’s award-winning AI-powered resume builder is trusted by hundreds of thousands of job seekers. Create your perfect resume in minutes with Rezi. Create a Perfect Resume | Free Resume Builder | Resumaker.ai [](https://resumaker.ai/) Create your professional resume with this online resume maker. Choose a designer-made template and grab any employer attention in seconds. Trusted AI Resume Maker Helps You Get Hired Fast [](https://skillroads.com/) Reach a 96.4% success rate in the job hunt race with the best resume creator. Our innovative technologies and 24/7 support help you to become a perfect candidate for any job. Do not lose your chance to become the One. Kickresume | Best Online Resume & Cover Letter Builder [](https://www.kickresume.com/) Create your best resume yet. Online resume and cover letter builder used by 1,300,000 job seekers worldwide. Professional templates approved by recruiters. ResumeMaker.Online | Create a Professional Resume for Free [](https://www.resumemaker.online/) Save time with the easiest-to-use Resume Maker Online. Create an effective resume in just minutes and land your dream job. No Sign-up required, start now! Interviews Interview Warmup - Grow with Google [](https://grow.google/certificates/interview-warmup/) A quick way to prepare for your next interview. Practice key questions, get insights about your answers, and get more comfortable interviewing. No code website builder Carrd - Simple, free, fully responsive one-page sites for pretty much anything [](https://carrd.co/) A free platform for building simple, fully responsive one-page sites for pretty much anything. Webflow: Create a custom website | No-code website builder [](https://webflow.com/) Create professional, custom websites in a completely visual canvas with no code. Learn how to create a website by trying Webflow for free! Google Sites: Sign-in [](https://sites.google.com/) FlutterFlow - Build beautiful, modern apps incredibly fast! [](https://flutterflow.io/) FlutterFlow lets you build apps incredibly fast in your browser. Build fully functional apps with Firebase integration, API support, animations, and more. Export your code or even easier deploy directly to the app stores! Free Website Builder: Build a Free Website or Online Store | Weebly [](https://www.weebly.com/) Weebly’s free website builder makes it easy to create a website, blog, or online store. Find customizable templates, domains, and easy-to-use tools for any type of business website. Glide • No Code App Builder • Nocode Application Development [](https://www.glideapps.com/) Create the apps your business needs, without coding, waiting or overpaying. Get started for free and build an app today Adalo - Build Your Own No Code App [](https://www.adalo.com/) Adalo makes creating apps as easy as putting together a slide deck. Turn your idea into a real native app — no code needed! Siter.io - The collaborative web design tool, no-code website builder [](https://siter.io/) Siter.io is a visual website builder for designers. Prototype, design, and create responsive websites in the browser. Work together with your team in one place. Elementor: #1 Free WordPress Website Builder | Elementor.com [](https://elementor.com/) Elementor is the platform web creators choose to build professional WordPress websites, grow their skills, and build their business. Start for free today! No code app builder | Bravo Studio [](https://www.bravostudio.app/) Your no-code mobile app builder for iOS and Android. Create MVP’s, validate ideas and publish on App Store and Google Play Store. Home [](https://typedream.com/) The simplest way to build a website with no-code, as easy as writing on Notion. Try Typedream for free and upgrade for custom domains, collaborators, and unlimited pages. Free Website Builder | Create a Free Website | Wix.com [](https://www.wix.com/) Create a website with Wix’s robust website builder. With 900+ strategically designed templates and advanced SEO and marketing tools, build your brand online today. Free responsive Emails & Landing Pages drag-and-drop Editor | BEE [](https://beefree.io/) Free responsive emails and landing pages editor. With BEE drag-and-drop builders embedded in many software applications you can start designing now! Home [](https://typedream.com/) The simplest way to build a website with no-code, as easy as writing on Notion. Try Typedream for free and upgrade for custom domains, collaborators, and unlimited pages. Ownit Connected Checkout [](https://www.ownit.co/) Ownit Connected Checkout Bookmark.com | No-code Website Builder to Start Your Business [](https://www.bookmark.com/) Our AI powered platform ensures your business is future proof. Try Bookmark for free. The best way to build web apps without code | Bubble [](https://bubble.io/) Bubble introduces a new way to build software. It’s a no-code tool that lets you build SaaS platforms, marketplaces and CRMs without code. Bubble hosts all web apps on its cloud platform. Responsive Web Design | Website Creation | Editor X [](https://www.editorx.com/) Experience the future of website design with responsive layouts, CSS precision and smooth drag and drop. Create a Website for Free. Tilda Website Builder [](https://tilda.cc/) Create a website, online store, landing page with Tilda intuitive website builder. Build your site from hundreds of pre-designed templates and publish it today. No code required. No-code headless commerce and websites | Unstack Inc. [](https://www.unstack.com/) Deploy high performance eCommerce storefronts and websites without the engineering overhead using Unstack's no-code CMS Best Drag-and-Drop Website Builder | Jemi [](https://jemi.so/) The modern website builder for creatives, entrepreneurs, and dreamers. Build a beautiful link in bio site, portfolio, or landing page in minutes. No-code website builder that works like Notion [](https://popsy.co/) Create a beautiful no-code website in minutes. Popsy works just like Notion but is built from the ground up for building websites. Choose a free template. Edit content just like in Notion. Customize styles without code. Free Notion icons and illustrations. Unbounce - The Landing Page Builder & Platform [](https://unbounce.com/) Grow your relevance, leads, and sales with Unbounce. Use Unbounce to easily create and optimize landing pages for your small business and boost conversions with AI insights. Low-code Front-end Design & Development Platform | TeleportHQ [](https://teleporthq.io/) Front-end development platform, with a visual builder and headless content modelling capabilities. Static website creation, and UI development tools. Other tools used in no code website MemberSpace - Turn any part of your website into members-only with just a few clicks [](https://www.memberspace.com/) Create memberships on your website for anything you want like courses, video tutorials, member directories, and more while having 100% control over look & feel. Triggre | The number one true no-code platform to run your business [](https://www.triggre.com/) The best no-code platform to create highly advanced business applications in hours, without programming. Try it now for free! No code game builder Welcome to Buildbox [](https://signup.buildbox.com/) Welcome to Buildbox Flowlab Game Creator - Make games online [](https://flowlab.io/) Flowlab is an online game creator. Make your own games to share with friends. Make 2D Games With GameMaker | Free Video Game Maker [](https://gamemaker.io/) Make a game with GameMaker, the best free video game engine. Perfect for beginners and professionals. Learn to build your own 2D games with our simple tutorials. Side Hustle Side Hustle Stack [](https://sidehustlestack.co/) Side Hustle Stack is a resource for finding platform-based work, ranging from gig work and side hustles to platforms that help you start a small business that can grow. Fiverr [](https://www.fiverr.com/) Remotasks: Work From Home, Online Bootcamp Training [](https://www.remotasks.com/en) Make money doing tasks. Start earning today! Free bootcamp training offered online. Sign up for a free Remotasks account and work from home. Earn up to $200/month. Transcribe Speech to Text | Rev [](https://www.rev.com/) Transcribe Speech to Text with Rev. Reach your audience with clear and accurate captions, transcripts, and subtitles. AI Training Data and other Data Management Services [](https://www.clickworker.com/) AI training data, SEO texts, web research, tagging, surveys and more - Use the crowdsourcing principle with the power of >4.5M Clickworkers. Automate your Busy Work - Byron People-Powered Assistants [](https://www.hibyron.com/) Byron is an on demand US based virtual assistant platform that gives individuals and teams the ability to quickly outsource their non-essential tasks. Jobs Websites - Remote Latest Crypto Jobs, Web3 Jobs and Blockchain Jobs in the leading tech companies. [](https://cryptojobslist.com/) New Cryptocurrency Jobs, Web3 Jobs and Blockchain Jobs on CryptoJobsList — the leading site to find and post jobs. Connect with companies hiring in a few clicks and begin your next experience in the industry. Updated daily. Remote Jobs: Design, Marketing, Programming, Writing & More [](https://justremote.co/) Discover Remote Jobs from around the world. Give up the commute, work remotely and do what you love, daily, from anywhere. Find your perfect remote development, design, sales or marketing job today. Remote Ok [](https://remoteok.com/) Hire Freelancers & Remote Workers For Free [](https://talent.hubstaff.com/) Find and hire the highest quality freelancers from around the world - for free. Choose from thousands of developers, digital marketers, creatives and more. We Work Remotely: Remote jobs in design, programming, marketing and more [](https://weworkremotely.com/) Find the most qualified people in the most unexpected places: Hire remote! We Work Remotely is the best place to find and list remote jobs that aren't restricted by commutes or a particular geographic area. Browse thousands of remote work jobs today. Angel [](https://angel.co/) Remote Work: Jobs, Companies & Virtual Teams - Remote.co [](https://remote.co/) Remote.co is the definitive remote work job board for online job seekers and companies hiring. Start your remote job search here! FlexJobs: Best Remote Jobs, Work from Home Jobs, Online Jobs & More [](https://www.flexjobs.com/) The #1 job search site for hand-screened flexible and remote jobs (work from home jobs) since 2007. Plus get resume, coaching and career help. Join today! Remote jobs remotefront.io [](https://remotefront.io/) All remote jobs at remotefront.io Daily Virtual Events Helping You Grow Professionally [](https://powertofly.com/) PowerToFly is where you receive expert career advice, free video training, coaching and exclusive access to jobs and events at top companies. Best Remote and Work from Home Jobs - Virtual Vocations [](https://www.virtualvocations.com/) Best work from home jobs and remote jobs in over 50 categories for professionals, digital nomads, telecommuting workers and entry level jobseekers. Education, healthcare, medical, customer support and tech job openings. Remote Jobs | Working Nomads [](https://www.workingnomads.com/jobs) Remote jobs for digital working nomads. Start your telecommuting career and work remotely from home or places around the world. Job Search, Companies Hiring Near Me, and Advice | The Muse [](https://www.themuse.com/) Find jobs at the best companies hiring near you and get free career advice. Startupers [](https://www.startupers.com/) NoDesk - Where Everyone Works Remote [](https://nodesk.co/) Browse and apply to the best new remote jobs at leading remote companies and startups for free. Join hundreds of companies that use NoDesk to build their remote teams. Browser Extensions Blackbox - Select. Copy. Paste & Search - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/blackbox-select-copy-past/mcgbeeipkmelnpldkobichboakdfaeon) Fastest Way to Copy Text from Videos & Images Octotree - GitHub code tree - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/octotree-github-code-tree/bkhaagjahfmjljalopjnoealnfndnagc) GitHub on steroids WhatFont - Chrome Web Store [](https://chrome.google.com/webstore/detail/whatfont/jabopobgcpjmedljpbcaablpmlmfcogm?hl=en) The easiest way to identify fonts on web pages. Window Resizer - Chrome Web Store [](https://chrome.google.com/webstore/detail/window-resizer/kkelicaakdanhinjdeammmilcgefonfh?hl=en) Resize the browser window to emulate various screen resolutions. Amino: CSS Editor - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/amino-css-editor/pbcpfbcibpcbfbmddogfhcijfpboeaaf) Live CSS Editor. Write custom CSS for any website and see your changes in real time. Checkbot: SEO, Web Speed & Security Tester 🚀 - Chrome Web Store [](https://chrome.google.com/webstore/detail/checkbot-seo-web-speed-se/dagohlmlhagincbfilmkadjgmdnkjinl?hl=en) Test SEO/speed/security of 100s of pages in a click! Check broken links, HTML/JavaScript/CSS, URL redirects, duplicate titles... Honey: Automatic Coupons & Rewards - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/honey-automatic-coupons-r/bmnlcjabgnpnenekpadlanbbkooimhnj) Save money and earn rewards when you shop online. Tango: screenshots, training, & documentation - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/tango-screenshots-trainin/lggdbpblkekjjbobadliahffoaobaknh) Automatically create beautiful step-by-step guides with screenshots, in seconds. No code browser automation | axiom.ai [](https://axiom.ai/) Build browser bots quickly, without code. Automate website actions and repetitive tasks using just your browser, on any website or web app. No Code Browser extensions builder Bildr - Visual Web Development in your Browser [](https://www.bildr.com/) Visually build SaaS products, Chrome extensions, and web3 dApps Other Repurposing content for social media the easy way » Repurpose.io [](https://repurpose.io/) Repurposing content for social media made easy. Automatically repurpose YouTube, TikTok, Lives, Podcasts, and Zoom calls. Try it for FREE. Smart Serials: Your serial numbers database [](https://smartserials.com/) This is your main source of free serial numbers, unlock keys in a clean environment safe to browse by all ages. Old versions of Windows, Mac and Linux Software, Apps & Abandonware Games - Download at OldVersion.com [](http://www.oldversion.com/) Online Room Planner - Design Your Room [](http://www.planyourroom.com/) Planyourroom.com is a wonderful website to redesign each room in your house by picking out perfect furniture options to fit your unique space. BoredHumans.com - Fun AI Programs You Can Use Online [](https://boredhumans.com/) Fun AI programs you can use online. AI games, fake people, computer generated art, machine learning demos, and more. BNProject | Home [](https://buynothingproject.org/) Open Source Alternatives to Proprietary Software [](https://www.opensourcealternative.to/) Discover 400+ popular open source alternatives to proprietary SaaS. URL Shortener - Short URLs & Custom Free Link Shortener | Bitly [](https://bitly.com/) Bitly’s Connections Platform is more than a free URL shortener, with robust link management software, advanced QR Code features, and a Link-in-bio solution. TinEye Reverse Image Search [](https://tineye.com/) Good Books | Books recommended by successful people [](https://www.goodbooks.io/) Looking for the best books to read in 2022? Discover the best book recommendations from the world's most successful, influential and interesting people. Directory - Website Recommendations [](https://tokapps.com/directory/) 0 TRIED & TESTED WEBSITES LISTED Insanely Useful Websites A combination of useful websites for businesses, freelancers, DIYers, and individuals in a centralised area.All websites have been tried and tested. Filter Websites Audio Business Tools Copywriting Design Entertainment Graphics Guides Health Marketing PC Resources Savings SEO Software Travel Video Apply filter Watch Anime Online, Free Anime Streaming Online on Zoro.to Anime Website [](https://zoro.to/) Zoro is a Free anime streaming website which you can watch English Subbed and Dubbed Anime online with No Account and Daily update. WATCH NOW! Animated Drawings [](https://sketch.metademolab.com/) Bring children's drawings to life, by animating characters to move around! Alternativeto [](https://alternativeto.net/) Chatroulette [](https://chatroulette.com/) Random meetings around the world Tiktok Downloader - Download Video tiktok Without Watermark - SnapTik [](https://snaptik.app/en) TikTok Video Downloader - SnapTik.App is one of the best free Download video Tiktok No Watermark tool available online. You can download TikTok video from any device you have. Imgflip - Create and Share Awesome Images [](https://imgflip.com/) Flip through memes, gifs, and other funny images. Make your own images with our Meme Generator or Animated GIF Maker. Fake Text Message | Make Fake Text Conversation [](https://ifaketextmessage.com/) Fake Text Message is a tool to create a Fake Text Conversation and a Fake iMessage. ✂Templatemaker ︎ [](https://www.templatemaker.nl/en/) Omni Calculator [](https://www.omnicalculator.com/) Omni Calculator solves 2960 problems anywhere from finance and business to health. It’s so fast and easy you won’t want to do the math again! Watch Movies Online Free | Watch Series HD Free [](https://hdtoday.tv/) Free Access to the Biggest library of HD Movies and HD Series online - NO ADS - No Account Required - Fast Free Streaming Students Answers - The Most Trusted Place for Answering Life's Questions [](https://www.answers.com/) Answers is the place to go to get the answers you need and to ask the questions you want Wolfram|Alpha: Computational Intelligence [](https://www.wolframalpha.com/) Compute answers using Wolfram's breakthrough technology & knowledgebase, relied on by millions of students & professionals. For math, science, nutrition, history, geography, engineering, mathematics, linguistics, sports, finance, music… Online Math Tools - Simple, free and easy to use math utilities [](https://onlinemathtools.com/) World's simplest collection of useful mathematics utilities. Generate number sequences, draw fractals, do quick matrix and numerical calculations and more! edX | Free Online Courses by Harvard, MIT, & more | edX [](https://www.edx.org/) Access 2000 free online courses from 140 leading institutions worldwide. Gain new skills and earn a certificate of completion. Join today. Sci-Hub [](https://sci-hub.hkvisa.net/) Sci-Hub,mg.scihub.ltd,sci-hub.tw,The project is supported by user donations. Imagine the world with free access to knowledge for everyone ‐ a world without any paywalls. DigitalDefynd - Find the Best + Free Courses Online [](https://digitaldefynd.com/) 4 Million+ Learners | 96,000+ Courses | 45,000+ Free Courses | 1200+ Free Certificates Learn Anything [](https://learn-anything.xyz/) Search Interactive Mind Maps to learn anything HubSpot Academy - Homepage [](https://academy.hubspot.com/) HubSpot Academy is the worldwide leader in inbound marketing, sales, and customer service/support training.

You're Not Behind: Become AI-Native in 2025

🎯 Grab my free AI Toolkit: https://academy.jeffsu.org/ai-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=172 Feeling overwhelmed by all the #AI noise? This video breaks down three key strategies to become AI-native in 2025: building a focused "Minimum Viable Toolkit" instead of chasing every new tool, implementing friction-free prompt #workflows, and creating sustainable learning systems to stay current with AI developments. Perfect for non-technical professionals looking to effectively integrate AI into their daily work. TIMESTAMPS 00:00 I feel overwhelmed by AI 00:37 The problem with learning AI 01:20 Challenge 1: AI Tools Paralysis 04:40 Challenge 2: Death by Prompts 07:18 Challenge 3: Update Suffocation 09:34 Recap of 3 Strategies RESOURCES MENTIONED AI Action Plan Doc: https://docs.google.com/document/d/1fs7hq12UqZHk7uSq6yN9x0vISouroAmVFLn3Dm_R4/copy My AI Toolkit: https://academy.jeffsu.org/ai-toolkit?utmsource=youtube&utmmedium=video&utm_campaign=172 My Perplexity Tutorial: https://youtu.be/YoWdogtZRw8 BE MY FRIEND: 📧 Subscribe to my newsletter - https://www.jeffsu.org/newsletter/?utmsource=youtube&utmmedium=video&utm_campaign=description 📸 Instagram - https://instagram.com/j.sushie 🤝 LinkedIn - https://www.linkedin.com/in/jsu05/ MY FAVORITE GEAR 🎬 My YouTube Gear - https://www.jeffsu.org/yt-gear/ 🎒 Everyday Carry - https://www.jeffsu.org/my-edc/ MY TOP 3 FAVORITE SOFTWARE ❎ CleanShot X - https://geni.us/cleanshotx ✍️ Skillshare - https://geni.us/skillshare-jeff 💼 Teal - http://tealhq.co/jeffsu

air-support

!air-support Air Support: Tools for Automating Airdrops of Solana NFTs The Skeleton Crew | Twitter: @skeletoncrewrip | Discord: Skeleton Crew Feeling generous? Your contributions help fund future development. Send tips to our Solana wallet: CH6afYjjydFLPSrfQYEUNCdSNohLCAQV6ir6QnYeZU3t See also: Treat Toolbox, a generative art manager for NFT projects from the Skeleton Crew. Background The Skeleton Crew launched on Oct 1, and has since been delivering daily airdrops of artwork from indie artists, with plans to continue for the entire month of October. In order to execute on this plan, we needed tools that allowed us to automate the process. This repository is the result of that effort, which we now share with you in the hopes of more teams spending less time giving themselves Carpal tunnel syndrome doing all of this manually inside of Phantom :) IMPORTANT - Before you Start Creating and sending NFTs in bulk comes with costs. On Solana, the costs are significantly better than some other chains. BUT, it's a good idea to try a drop on devnet first to be sure you understand the fees involved. We assume no responsibility for any costs incurred through the use of these tools. Use at your own risk. Getting Started In order to use Air Support, you will need to install and configure the current version of Metaplex. We run this locally with some customizations for speed (ex. hardcoding some metadata which is common across all of our drops). Also, have a look at the configuration options at the top of the Makefile. At minimum, you'll need to specify paths to Metaplex, your keyfile, and an RPC Host. It's highly recommended that you use a third-party RPC provider to perform large airdrops. DROP is a name for a set of airdrops; in our case we numbered these 1-31 for each day in October. TYPE is a name for a single airdropped item that's part of a drop; in our case we had a "trick" and a "treat" as part of each drop, sometimes even "trick1", "trick2"... etc. The name will be "token" by default, and is used to prefix log files in each step below. For the generate step to work, you will need to build Metaplex's rust tools. Inside metaplex/rust, run: You will also need a few other pieces of software installed, including: gshuf: brew install coreutils jq: brew install jq How to Use Air Support Prerequisites: follow all steps in the Getting Started section above. Then, the basic workflow looks something like this: 📇 prepare: Collect a list of token mint addresses, for which the holders of those tokens represent a community you wish to airdrop to. This is sometimes done by providing your Candy Machine address to https://tools.abstratica.art. Store this in the air support root directory as token-mint-addresses.json. ✍️ record: run this to fetch the wallet addresses of all users that hold the tokens, and don't have them listed on a secondary exchange. The goal here is to avoid sending airdrops to exchanges where they may not be recoverable. Note: As of now, Air Support can only identify tokens listed on Digital Eyes, Magic Eden, Solanart, and Alpha.art. FTX and Solsea use unique addresses for escrow wallets. The command below will fetch the addresses and store them in airdrops/1/token-holders.log. 🎨 create: Start Metaplex, and use it to create your Master Edition NFT with a limited supply (the number of airdrops you want to send). 🖨 generate: run this to generate prints of the Master Edition. These will be stored in the wallet associated with the keys you specify as options. The below command would create 500 prints of the Master with mint address RPdCMRxBx4YPcJv6HUb2S5zHGJcDrDrZszUNNGmLwfT. 🏅 choose: run this next to decide who will receive the airdrop. Important to note that if 2 tokens are owned by the same wallet, by design they have twice the chance to receive an airdrop as someone with only 1 token when using this script to pick recipients. If you have 10,000 token owners recorded as not listed on marketplaces in step 2, and 500 airdrops to send, this will randomly select 500 of those recorded tokens. 📬 distribute: the last step is to send the airdrops out. This script will run through the addresses generated in step 4 and the recipients chosen in step 5 and send airdrops 1-by-1. It is possible that failures will occur. Logs are saved during the process in a {NAME}_sent.log file. Because distribution happens line-by-line, it is safe to rerun the script again to attempt to correct failures. You can also check your wallet to see that all tokens have been distributed. (Note that your Master edition will still remain as only prints are recorded to be sent in step 4. You can keep these for yourself or a community vault.) There is also an optional STARTINDEX param that can be used if you need to restart a distribution from somewhere in the middle. 🔥 burn: if you realize you made a mistake on your Master NFT, but only after you went ahead and started printing a bunch of editions, this command will automate the process of sending those costly mistakes to the Solana incinerator. There is also an optional STARTINDEX param that can be used if you need to restart a distribution from somewhere in the middle. Other Tips Transparency is key when running airdrop campaigns to your communities. In an ideal world, where we had more than 24 hours between our launch and the start of our month of airdrops, we might have attempted to bring some or all of these processes on-chain. The next best thing we could offer is a transparency repo, where we publish the daily receipts of our airdrops, to make it easy for our community to investigate the drops on the blockchain if they feel the desire to do so. Our tools give you the receipts as output to do the same if you wish. You can have a look at that repo here: https://github.com/theskeletoncrew/airdrop-transparency Acknowledgements The record step utilizes code created by the Exiled Apes organization, shared under an Apache License, originally found here: https://github.com/exiled-apes/exiled-holders

flappy-es

Playing Flappy Bird using Evolution Strategies ============================================== After reading Evolution Strategies as a Scalable Alternative to Reinforcement Learning, I wanted to experiment something using Evolution Strategies, and Flappy Bird has always been one of my favorites when it comes to Game experiments. A simple yet challenging game. The model learns to play very well after 3000 epochs, but not completely flawless and it rarely loses in difficult cases (high difference between two wall entrances). Training process is pretty fast as there is no backpropagation, and is not very costy in terms of memory as there is no need to record actions as in policy gradients. Here is a demonstration of the model after 3000 epochs (~5 minutes on an Intel(R) Core(TM) i7-4770HQ CPU @ 2.20GHz): !after training Before training: !Before training There is also a a web version available for ease of access. For each frame the bird stays alive, +0.1 score is given to him. For each wall he passes, +10 score is given. Demonstration of rewards for individuals and the mean reward over time (y axis is logarithmic): !reward chart Try it yourself You need python3.5 and pip for installing and running the code. First, install dependencies (you might want to create a virtualenv): The pretrained parameters are in a file named load.npy and will be loaded when you run train.py or demo.py. train.py will train the model, saving the parameters to saves//save-. demo.py shows the game in a GTK window so you can see how the AI actually plays (like the GIF above). play.py if you feel like playing the game yourself, space: jump, once lost, press enter to play again. :grin: pro tip: reach 100 score and you will become THUG FOR LIFE :smoking: Notes It seems training past a maximum point reduces performance, learning rate decay might help with that. My interpretation is that after finding a local maximum for accumulated reward and being able to receive high rewards, the updates become pretty large and will pull the model too much to sides, thus the model will enter a state of oscillation. To try it yourself, there is a long.npy file, rename it to load.npy (backup load.npy before doing so) and run demo.py, you will see the bird failing more often than not. long.py was trained for only 100 more epochs than load.npy.

coursera-practical-data-science-specialization

Solutions on Practical Data Science Specialization Access all courses in the Coursera Practical Data Science Specialization Specialization offered by deeplearning.ai. This repo contains the SOLUTIONS of exercises/labs to achieve the badge. Course keynotes and solutions of related quizzes, assignments Practical Data Science Specialization on Coursera contains three courses: Course 1: Analyze Datasets and Train ML Models using AutoML Week 1: Artificial Intelligence (AI) mimics human behavior. Machine Learning (ML) is a subset of AI that uses statistical methods and algorithms that are able to learn from data without being explicitly programmed. Deep learning (DL) is a subset of machine learning that uses artificial neural networks to learn from data. AWS SageMaker --> [x] Practice Quiz: Week 1. [x] Graded External Tool: Register and visualize dataset. Week 2: Statistical Bias: Training data does not comprehensively represent the underlying problem space. Statistical Bias Causes: Activity Bias, Societal Bias, Selection Bias, Data Drift/Shift, ... Class Imbalance (CI) measures the imbalance in the number of members between different facet values. Detecting Statistical Bias by AWS SageMaker DataWrangler and AWS SageMaker Clarify. Feature Importance explains the features that make up the training data using a score. How useful or valuable the feature is relative to other features? SHAP (SHapley Additive exPlanations) --> [x] Practice Quiz: Week 2. [x] Graded External Tool: Detect data bias with Amazon SageMaker Clarify. Week 3: Data Prepreration includes Ingesting & Analyzing, Prepraring & Transforming, Training & Tuning, and Deploying & Managing. AutoML aims at automating the process of building a model. Model Hosting. --> [x] Practice Quiz: Week 3. [x] Graded External Tool: Train a model with Amazon SageMaker Autopilot. Week 4: Built-in Alogrithms in AWS SageMaker supports Classification, Regression, and Clustering problems. Text Analysis Evolution: Word2Vec (CBOW & Skip-gram), GloVe, FastText, Transformer, BlazingText, ELMo, GPT, BERT, ... --> [x] Practice Quiz: Week 4. [x] Graded External Tool: Train a text classifier using Amazon SageMaker BlazingText built-in algorithm. Course 2: Build, Train, and Deploy ML Pipelines using BERT Week 1 Feature Engineering involves converting raw data from one or more sources into meaningful features that can be used for training machine learning models. Feature Engineering Step includes feature selection, creation, and transformation. BERT is Transformer-based pretrained language models that sucessfully capture bidirectional contexts in word representation. Feature Store: centralized, reusable, discoverable. --> [x] Practice Quiz: Week 1. [x] Graded External Tool: Feature transformation with Amazon SageMaker processing job and Feature Store. Week 2 Learn how to train a customized Pretrained BERT and its variant models, debug, and profile with AWS SageMaker. --> [x] Practice Quiz: Week 2. [x] Graded External Tool: Train a review classifier with BERT and Amazon SageMaker. Week 3 MLOps builds on DevOps practices that encompass people, process, and technology. MLOps also includes considerations and practices that are really unique to machine learning workloads. --> [x] Practice Quiz: Week 3. [x] Graded External Tool: SageMaker pipelines to train a BERT-Based text classifier. Course 3: Optimize ML Models and Deploy Human-in-the-Loop Pipelines Week 1 Model Tuning aims to fit the model to the underlying data patterns in your training data and learn the best possible parameters for your model. Automatic Model Tuning includes grid search, random search, bayesian optimization, hyperband. Challenges: checkpointing, distribution training strategy. --> [x] Practice Quiz: Week 1. [x] Graded External Tool: Optimize models using Automatic Model Tuning. Week 2 [x] Practice Quiz: Week 2. [x] Graded External Tool: A/B testing, traffic shifting and autoscaling. Week 3 [x] Practice Quiz: Week 3. [x] Graded External Tool: Data labeling and human-in-the-loop pipelines with Amazon Augmented AI (A2I). Disclaimer The solutions here are ONLY FOR REFERENCE to guide you if you get stuck somewhere. Highly recommended to try out the quizzes and assignments yourselves first before referring to the solutions here. Feel free to discuss further with me on .

Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist

Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist️ Music To Coding To Focus And Focus 🎧 lofi hip hop 💻 Coding Songs Playlist️ 💻 Welcome to Lofi boost your mood : Boost your productivity and lock into the flow with smooth lofi hip hop beats, designed to keep your mind sharp during coding sessions. Whether you're debugging, creating new code, or working on a big project, these calming rhythms will help you stay focused and in the zone. Perfect for programmers who need to enhance their workflow without distractions. Subscribe for more lofi coding playlists to fuel your focus and creativity! ✨Help me reach 100,000 subscribers: https://www.youtube.com/channel/UCESVcUXbcDOrJ293_KWotyQ 🎵 Another Vibes for you : • Coding Session 💻 : https://youtu.be/qZjWUkohSQg • Lofi Playlist to Coding 💻: https://youtu.be/zWQjn2uVpUg • Night Coding Vibes 💻: https://youtu.be/S810accnrRc • 3 PM Coding Session 💻: https://youtu.be/akrgSiPLngY LIKE 👍COMMENT & ╔═╦╗╔╦╗╔═╦═╦╦╦╦╗╔═╗ ║╚╣║║║╚╣╚╣╔╣╔╣║╚╣═╣ ╠╗║╚╝║║╠╗║╚╣║║║║║═╣ ╚═╩══╩═╩═╩═╩╝╚╩═╩═╝!!! 🔔 🍃 ＦＯＣＵＳ ＡＮＤ ＣＯＤＥ ＷＩＴＨ ＬＯＦＩ 🍃 Lofi Music | Coding Beats 🍃 For Deep Work / Study / Code 🍃 Music to Help You Stay Productive 🎉Join our Discord server to download high-quality wallpapers, connect with others, and share your thoughts and feelings 🤗 : 🌷 https://discord.gg/MuPgsHJ5MW 🎨 Artwork and Animations by Ethan James : ✨ https://www.instagram.com/ethanjames30801/ "💜 Music provided by Purrple Cat → https://playlist.purrplecat.com → https://spotify.purrplecat.com → https://apple.purrplecat.com → https://amazon.purrplecat.com → https://bandcamp.purrplecat.com → https://soundcloud.purrplecat.com → https://instagram.purrplecat.com → https://tiktok.purrplecat.com → https://discord.purrplecat.com → https://twitter.purrplecat.com → https://facebook.purrplecat.com → https://youtube.purrplecat.com" 🎸 🎼 Tracklist: 00:00:00 - 01 Purrple Cat - FieldOf Fireflies https://open.spotify.com/track/4rfE7mNI2PoUOm5l1hwpgr?autoplay=true 00:02:41 - 02 Purrple Cat - WaitWhat https://open.spotify.com/track/1w7IfXgbG5nBHhoI1bGaGM 00:05:27 - 03 Purrple Cat - BlackCherry https://open.spotify.com/track/0b8j3Ixmk6aUa4VegYH2Ui?autoplay=true 00:08:31 - 04 Purrple Cat - BoxOf Kittens https://open.spotify.com/track/5VtS7LGk0TTKBwRtpMmqWM?autoplay=true 00:11:49 - 05 Purrple Cat - AlleyCat https://open.spotify.com/track/4ud4SB7SM5mXF6vhzib8iQ?autoplay=true 00:14:45 - 06 Purrple Cat - DarkChocolate https://open.spotify.com/track/138KkineYUu5WiAUVTjid9?autoplay=true 00:17:42 - 07 Purrple Cat - IHave Too Many Feelings https://open.spotify.com/track/1Qd0XQgXg11YV9myZv5m71?autoplay=true 00:20:57 - 08 Purrple Cat - GentleBreeze https://open.spotify.com/track/4CbAvhRbdt2up0YZzTpbbG?autoplay=true 00:24:13 - 09 Purrple Cat - Openingthe Window For Some Fresh Air https://open.spotify.com/track/7BuHGYghASIz8WOfopDkfY?autoplay=true 00:25:53 - 10 Purrple Cat - Bliss https://open.spotify.com/track/7DT4LT416UcdtoPv2L0ria?autoplay=true 00:28:53 - 11 Purrple Cat - TheRed Dot https://open.spotify.com/track/0GB1qIvHAudmgp3nJ7wdza 00:31:14 - 12 Purrple Cat - PitterPatter https://open.spotify.com/track/35uCQ9RzCpNHrvoSNiP2Gt?autoplay=true 00:34:14 - 13 Purrple Cat - SundaeSunset https://open.spotify.com/track/00JByF6azH3FC82HUWLJJk?autoplay=true 00:36:32 - 14 Purrple Cat - Mary https://open.spotify.com/track/4Xnfyvi8qZPdcxjyK4Gd9g 00:38:45 - 15 Purrple Cat - Festivalof Lights https://open.spotify.com/track/4T3i2PKPiBkNvPCgSKKdeL?autoplay=true ✨The Lofi music is perfect to Calm your anxiety, Learn, read books, paint, work from home, play video games, do your homework, sleep, prepare exams, have a break, cook, or chill drive, simply chill out with your friends. ✨ Artwork and Animations by © 2024 Lofi boost your mood #lofi #lofihiphop #lofistudy #lofimusic #lofibeats

Chill Work Music — Deep Focus and Productivity Mix for Programming, Coding

This carefully curated mix of tracks is specifically designed to help you focus on work and be productive. Music in genres like chillstep, future garage, and chill electronic will create the perfect background for tackling complex projects or routine tasks. Perfect as a programming music and for intense coding sessions. Thanks to the relaxing atmosphere of this musical accompaniment, you will be able to immerse yourself in the creative process with special concentration and inspiration. These tracks will help you maintain a high level of attention and productivity to achieve maximum results. Discover new horizons of efficiency with our playlist! 🎯 Tips for Chill and Productive Work: Using Artificial Intelligence: Utilize AI tools to automate routine tasks. This will allow you to focus on more creative and complex aspects of your work. Gratitude Journal: At the end of each workday, write down three things you are grateful for. This will help you end the day on a positive note and reduce stress. Experiment with Rhythms: Try working at different times of the day. You might find that your productivity is significantly higher at night than during the day. Change of Scenery: If you feel you're losing concentration, try changing your workspace. Sit in a different chair, move to another room, or even go outside if possible. Music therapy with our Chill Music Lab playlists: Listen to our playlists or radio, which include relaxing and focusing tracks. Such music can help improve concentration and create a calm working atmosphere for your goals. If you enjoyed this video like, comment or subscribe to the channel. 🙏 Join our English-speaking Discord to get in contact with us and fellow music lovers. ❤️ https://discord.gg/5p8D8GdVfp Genre: Electronic Music Style: Chillstep, Future Garage Mood: Cyber, Deep, Atmospheric Feature: No prominent lyrics 📹 Similar videos ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkf6X1lbOpL3tAWERvlYej2L ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkeSTmryNClNxUkioFpq3Btx ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkdbssGgnnIDm3EnE2gmHyEQ ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkeH0adsnxZupMARfGxY6qik ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkf0gwWO9-qeu-La5vSJPmPc ► https://www.youtube.com/playlist?list=PLdE7uo_7KBkdsNAZNbzOUj61OQ5N0Ka26 🎧 Tracklist ► 00:00 Arnydmusic - Polaris ► 03:22 Arnyd - Hypernova ► 06:58 Neskre - Saviour ► 10:24 Exal & SkyFlair - Afterlife ► 14:11 Warmth - Solstice (Aurora Principle Remix) ► 18:06 Himalia - Growing Upwards. ► 24:26 Lonely Bird - Foggy Night ► 27:19 F0x3r - Precious Little Things ► 31:09 Deadfeelings - Melancholia ► 34:42 AK - Gone ► 37:51 Skandition - Chasing A Dream ► 43:18 Foxer - You ► 46:51 4lienetic - If Only ► 49:35 Tecnosine - Capacious ► 52:36 Vonnboyd - Lost without you ► 55:16 Blackbird - Love In Purple ► 59:21 Infinitum - Reborn ► 1:02:42 Future Skyline - Silent Moon ► 1:07:12 Code of Kasilid - Proto ► 1:11:11 AK - We're Older Now ► 1:14:12 Iketa - Under ► 1:16:42 Yzuva - Forget ► 1:20:22 Direct - Millions ► 1:25:20 Lazarus Moment - Forests Calling ► 1:28:51 Hystvme - Dream ► 1:31:32 Synthetic Epiphany - Infinite ► 1:34:56 Turno - Nocturno ► 1:37:13 4Lienetic - The Most Painful Goodbye #WorkMusic #FocusMusic #ChillMusic

Chillstep Music for Programming / Cyber / Coding — Future Garage Playlist

"Chillstep Music for Programming / Cyber / Coding — Future Garage Playlist" is a selection of chill step and Future Garage tunes. This compilation is designed to facilitate a rhythmic and immersive coding experience for programmers and cyber enthusiasts alike, fostering an environment of concentration and creativity. If you found this video informative, feel free to like, comment, or subscribe to the channel. 🌞 For contact and submit music: lofi@entstella.com ©️ All content on Chill Flow is protected by copyright © All music and videos are produced by us and are copyrighted ✔ All rights belong to their respective owners Chillstep Music for Programming / Cyber / Coding — Future Garage Playlist Chillstep Music for Programming / Cyber / Coding — Future Garage Playlist Chillstep Music for Programming / Cyber / Coding — Future Garage Playlist #ProgrammingMusic #CodingMusic #HackingMusic