Year

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

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer

Title, Is it actually a good plan ?? If no, why not ?? \\🚀 4-Year Roadmap to Becoming a High-Earning ML Engineer & Entrepreneur\\ \\(With Smartwork & Realistic 60-70% Execution Feasibility)\\ \\🟢 Year 1: Strong Foundation & Initial Projects (0-12 Months)\\ 🎯 \\Goal: Master Python & ML Fundamentals\\ \\🔹 1-4 Months (Python & Math Strengthening)\\ ✅ Python Mastery \- Daily LeetCode Easy problems (minimum 2) \- Build automation projects \- NumPy & Pandas mastery \- DSA fundamentals ✅ Mathematics Foundation \- Linear Algebra basics \- Statistics fundamentals \- Basic calculus concepts ✅ First Mini-Hackathon Participation \- Join beginner-friendly hackathons \- Focus on Python-based challenges \- Team up with other beginners 💡 \\Smart Move:\\ \- Join Discord/Slack hackathon communities \- Practice collaborative coding \- Build network with fellow participants \\🔹 5-8 Months (ML Foundations)\\ ✅ Machine Learning Basics \- Supervised Learning \- Model evaluation \- Feature engineering \- scikit-learn projects ✅ Participate in 2-3 ML Hackathons \- Kaggle Getting Started competitions \- Local ML hackathons \- University hackathons ✅ Start LinkedIn & GitHub Portfolio 💡 \\Smart Move:\\ \- Document hackathon experiences \- Share learnings on LinkedIn \- Focus on completion over winning \\🔹 9-12 Months (Deep Learning Introduction)\\ ✅ Basic Deep Learning \- Neural network fundamentals \- PyTorch basics \- Computer vision tasks \- Basic NLP ✅ Advanced Hackathon Participation \- AI/ML specific hackathons \- Team lead in 1-2 hackathons \- Start mentoring beginners \\🔵 Year 1 Expected Outcome (60-70% Execution)\\ ✔ \\Strong Python & ML foundations\\ ✔ \\5-6 hackathon participations\\ ✔ \\Active GitHub (100+ commits)\\ ✔ \\Growing LinkedIn (300+ connections)\\ 💰 \\Earning Expectation → ₹8K-₹20K per month (Projects/Internship)\\ \\🟢 Year 2: Professional Growth & Specialization (12-24 Months)\\ 🎯 \\Goal: Build Professional Experience & Recognition\\ \\🔹 1-6 Months (Technical Depth)\\ ✅ Advanced ML Topics \- Deep Learning architectures \- Computer Vision OR NLP \- MLOps basics (Docker, FastAPI) \- Cloud fundamentals (AWS/GCP) ✅ Hackathon Achievements \- Win minor prizes in 2-3 hackathons \- Lead teams in major hackathons \- Network with sponsors ✅ Start Technical Blogging 💡 \\Smart Move:\\ \- Focus on hackathon projects that align with career goals \- Build relationships with companies at hackathons \- Create detailed project documentation \\🔹 7-12 Months (Professional Experience)\\ ✅ Secure ML Role/Internship ✅ Advanced Project Building ✅ Open Source Contributions ✅ Organize Small Hackathons 💡 \\Smart Move:\\ \- Use hackathon network for job referrals \- Convert hackathon projects into full products \- Build mentor reputation \\🔵 Year 2 Expected Outcome (60-70% Execution)\\ ✔ \\Professional ML experience\\ ✔ \\10+ hackathon participations\\ ✔ \\1-2 hackathon wins\\ ✔ \\Strong industry network\\ 💰 \\Earning Expectation → ₹40K-₹70K per month (Job/Freelancing)\\ \\🟢 Year 3: Scaling & Business Foundation (24-36 Months)\\ 🎯 \\Goal: Establish Multiple Income Streams\\ \\🔹 1-4 Months (Expertise Building)\\ ✅ Choose Specialization \- MLOps \- Computer Vision \- NLP/LLMs \- Generative AI ✅ Advanced Competitions \- International hackathons \- High-prize competitions \- Corporate ML challenges ✅ Start Consulting Services 💡 \\Smart Move:\\ \- Use hackathon wins for marketing \- Build service packages around expertise \- Network with corporate sponsors \\🔹 5-8 Months (Business Development)\\ ✅ Scale Services ✅ Build Client Network ✅ Create Training Programs ✅ Hackathon Mentorship Program 💡 \\Smart Move:\\ \- Convert hackathon projects to products \- Use event networks for client acquisition \- Build authority through speaking \\🔹 9-12 Months (Growth & Innovation)\\ ✅ Product Development ✅ Team Building ✅ Innovation Focus ✅ Hackathon Organization \\🔵 Year 3 Expected Outcome (60-70% Execution)\\ ✔ \\Established ML business/career\\ ✔ \\Known in hackathon community\\ ✔ \\Multiple income streams\\ ✔ \\Strong industry presence\\ 💰 \\Earning Expectation → ₹1L-₹2L per month (Multiple Streams)\\ \\🟢 Year 4: Scale & Leadership (36-48 Months)\\ 🎯 \\Goal: Build AI Company & Achieve Financial Freedom\\ \\🔹 1-4 Months (Business Scaling)\\ ✅ Company Formation \- AI consulting firm \- Product development \- Training programs ✅ Hackathon Innovation \- Launch own hackathon series \- Corporate partnerships \- Prize sponsorships ✅ Team Expansion 💡 \\Smart Move:\\ \- Use hackathon network for hiring \- Create unique event formats \- Build corporate relationships \\🔹 5-8 Months (Market Leadership)\\ ✅ Product Launch ✅ Service Expansion ✅ International Presence ✅ Innovation Hub Creation 💡 \\Smart Move:\\ \- Create hackathon-to-hiring pipeline \- Build educational programs \- Establish thought leadership \\🔹 9-12 Months (Empire Building)\\ ✅ Multiple Revenue Streams \- AI products \- Consulting services \- Educational programs \- Event organization \- Investment returns ✅ Industry Leadership \- Conference speaking \- Published content \- Community leadership \\🔵 Year 4 Expected Outcome (60-70% Execution)\\ ✔ \\Established AI company\\ ✔ \\Major hackathon organizer\\ ✔ \\Multiple product lines\\ ✔ \\Industry authority status\\ 💰 \\Earning Expectation → ₹3L-₹5L+ per month (Business Income)\\ \\📊 FINAL RATING\\ ✅ \\Comprehensive growth plan\\ ✅ \\Strong community focus\\ ✅ \\Multiple income pathways\\ 💡 \\If 100% Execution → 8.5/10 Feasibility\\ 💡 \\If 50% Execution → 6/10 Feasibility\\ 🔥 \\Conclusion: A balanced path to ML mastery and entrepreneurship, built through consistent growth and community engagement!\\ 🚀 \\Key Success Factors:\\ Regular hackathon participation Strong community involvement Consistent skill development Strategic network building Focus on both technical and business growth

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer

Title, Is it actually a good plan ?? If no, why not ?? \\🚀 4-Year Roadmap to Becoming a High-Earning ML Engineer & Entrepreneur\\ \\(With Smartwork & Realistic 60-70% Execution Feasibility)\\ \\🟢 Year 1: Strong Foundation & Initial Projects (0-12 Months)\\ 🎯 \\Goal: Master Python & ML Fundamentals\\ \\🔹 1-4 Months (Python & Math Strengthening)\\ ✅ Python Mastery \- Daily LeetCode Easy problems (minimum 2) \- Build automation projects \- NumPy & Pandas mastery \- DSA fundamentals ✅ Mathematics Foundation \- Linear Algebra basics \- Statistics fundamentals \- Basic calculus concepts ✅ First Mini-Hackathon Participation \- Join beginner-friendly hackathons \- Focus on Python-based challenges \- Team up with other beginners 💡 \\Smart Move:\\ \- Join Discord/Slack hackathon communities \- Practice collaborative coding \- Build network with fellow participants \\🔹 5-8 Months (ML Foundations)\\ ✅ Machine Learning Basics \- Supervised Learning \- Model evaluation \- Feature engineering \- scikit-learn projects ✅ Participate in 2-3 ML Hackathons \- Kaggle Getting Started competitions \- Local ML hackathons \- University hackathons ✅ Start LinkedIn & GitHub Portfolio 💡 \\Smart Move:\\ \- Document hackathon experiences \- Share learnings on LinkedIn \- Focus on completion over winning \\🔹 9-12 Months (Deep Learning Introduction)\\ ✅ Basic Deep Learning \- Neural network fundamentals \- PyTorch basics \- Computer vision tasks \- Basic NLP ✅ Advanced Hackathon Participation \- AI/ML specific hackathons \- Team lead in 1-2 hackathons \- Start mentoring beginners \\🔵 Year 1 Expected Outcome (60-70% Execution)\\ ✔ \\Strong Python & ML foundations\\ ✔ \\5-6 hackathon participations\\ ✔ \\Active GitHub (100+ commits)\\ ✔ \\Growing LinkedIn (300+ connections)\\ 💰 \\Earning Expectation → ₹8K-₹20K per month (Projects/Internship)\\ \\🟢 Year 2: Professional Growth & Specialization (12-24 Months)\\ 🎯 \\Goal: Build Professional Experience & Recognition\\ \\🔹 1-6 Months (Technical Depth)\\ ✅ Advanced ML Topics \- Deep Learning architectures \- Computer Vision OR NLP \- MLOps basics (Docker, FastAPI) \- Cloud fundamentals (AWS/GCP) ✅ Hackathon Achievements \- Win minor prizes in 2-3 hackathons \- Lead teams in major hackathons \- Network with sponsors ✅ Start Technical Blogging 💡 \\Smart Move:\\ \- Focus on hackathon projects that align with career goals \- Build relationships with companies at hackathons \- Create detailed project documentation \\🔹 7-12 Months (Professional Experience)\\ ✅ Secure ML Role/Internship ✅ Advanced Project Building ✅ Open Source Contributions ✅ Organize Small Hackathons 💡 \\Smart Move:\\ \- Use hackathon network for job referrals \- Convert hackathon projects into full products \- Build mentor reputation \\🔵 Year 2 Expected Outcome (60-70% Execution)\\ ✔ \\Professional ML experience\\ ✔ \\10+ hackathon participations\\ ✔ \\1-2 hackathon wins\\ ✔ \\Strong industry network\\ 💰 \\Earning Expectation → ₹40K-₹70K per month (Job/Freelancing)\\ \\🟢 Year 3: Scaling & Business Foundation (24-36 Months)\\ 🎯 \\Goal: Establish Multiple Income Streams\\ \\🔹 1-4 Months (Expertise Building)\\ ✅ Choose Specialization \- MLOps \- Computer Vision \- NLP/LLMs \- Generative AI ✅ Advanced Competitions \- International hackathons \- High-prize competitions \- Corporate ML challenges ✅ Start Consulting Services 💡 \\Smart Move:\\ \- Use hackathon wins for marketing \- Build service packages around expertise \- Network with corporate sponsors \\🔹 5-8 Months (Business Development)\\ ✅ Scale Services ✅ Build Client Network ✅ Create Training Programs ✅ Hackathon Mentorship Program 💡 \\Smart Move:\\ \- Convert hackathon projects to products \- Use event networks for client acquisition \- Build authority through speaking \\🔹 9-12 Months (Growth & Innovation)\\ ✅ Product Development ✅ Team Building ✅ Innovation Focus ✅ Hackathon Organization \\🔵 Year 3 Expected Outcome (60-70% Execution)\\ ✔ \\Established ML business/career\\ ✔ \\Known in hackathon community\\ ✔ \\Multiple income streams\\ ✔ \\Strong industry presence\\ 💰 \\Earning Expectation → ₹1L-₹2L per month (Multiple Streams)\\ \\🟢 Year 4: Scale & Leadership (36-48 Months)\\ 🎯 \\Goal: Build AI Company & Achieve Financial Freedom\\ \\🔹 1-4 Months (Business Scaling)\\ ✅ Company Formation \- AI consulting firm \- Product development \- Training programs ✅ Hackathon Innovation \- Launch own hackathon series \- Corporate partnerships \- Prize sponsorships ✅ Team Expansion 💡 \\Smart Move:\\ \- Use hackathon network for hiring \- Create unique event formats \- Build corporate relationships \\🔹 5-8 Months (Market Leadership)\\ ✅ Product Launch ✅ Service Expansion ✅ International Presence ✅ Innovation Hub Creation 💡 \\Smart Move:\\ \- Create hackathon-to-hiring pipeline \- Build educational programs \- Establish thought leadership \\🔹 9-12 Months (Empire Building)\\ ✅ Multiple Revenue Streams \- AI products \- Consulting services \- Educational programs \- Event organization \- Investment returns ✅ Industry Leadership \- Conference speaking \- Published content \- Community leadership \\🔵 Year 4 Expected Outcome (60-70% Execution)\\ ✔ \\Established AI company\\ ✔ \\Major hackathon organizer\\ ✔ \\Multiple product lines\\ ✔ \\Industry authority status\\ 💰 \\Earning Expectation → ₹3L-₹5L+ per month (Business Income)\\ \\📊 FINAL RATING\\ ✅ \\Comprehensive growth plan\\ ✅ \\Strong community focus\\ ✅ \\Multiple income pathways\\ 💡 \\If 100% Execution → 8.5/10 Feasibility\\ 💡 \\If 50% Execution → 6/10 Feasibility\\ 🔥 \\Conclusion: A balanced path to ML mastery and entrepreneurship, built through consistent growth and community engagement!\\ 🚀 \\Key Success Factors:\\ Regular hackathon participation Strong community involvement Consistent skill development Strategic network building Focus on both technical and business growth

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

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

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.

I've been building stuff for years, I can build your idea

If anyone is interested at all, I'm a college student whose been massively passionate for entrepreneur and business stuff for years and can build anything from a marketplace to a social network, a booking app, a live streaming app, AI app*, what not. I'm really flexible in general and I'm also very reasonable with pricing. I like this community so I'd like to work on something I enjoy... (indeed... get out of my tabs please). Im a little passionate in general let's say, and I build all the time for fun. But I need money. So I'm here. Viola! Since I'm a college student, and this is my first time ever offering my services as well, chances are I won't expect anything past $500. I might even do it for cheaper if it looks doable for me. If you're generous that's up to you (lol). I'm happy to share my work and live previews you can interact with before we start. And, I'm happy to build things before you pay, so you can see it literally working :) THE "NEGATIVE"/catch: There will be no code from scratch as we'd build using no-code (www.bubble.io) and implement code as needed. This means you will not have the source code ever (even if we wanted to) and if you ever want your own from scratch platform/app you will have to find someone/a team to do it from scratch, as there's no option to export source code out. If you plan to grow past 1 million users, you may consider migrating to something built from scratch at this point scaling wise (and you can't get your source code - so you'll have to pay an entire dev team separately. If you have an app, you'll need a website developed, and Android and iOS developers for the app). For an MVP however, I personally think it's a faster, easier and cheaper way to get things running without investing a lot. THE GOOD: No-code/low-code will be a thousand times more easy, cheap, and fast to maintain. And if you're a startup, chances are you WILL need to tweak things... possibly a lot (100s vs. 1,000s difference in my opinion..). We can still build almost anything and also turn it into a mobile app for iOS / Android, though I'm more comfortable with getting a web app up first and the main posting here. But it depends on the complexity so just ask. Maintenance is likely to end up FAR cheaper and you can even do it free yourself if you decided to learn (which you could totally do in some days, and master in some weeks/months fully). I can build and document everything to be as beginner friendly as possible for you to be able to maintain it yourself if you wanted to learn. Send me a message describing what you need if you're interested. I will give you an estimate on price, time, and can send you some live previews. If we agree, I will start to build before any down payments to a (reasonable) point!:)

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

I Watched My Startup Slowly Dying Over Two Years: Mistakes and Lessons Learned

If you are tired of reading successful stories, you may want to listen to my almost failure story. Last year in April, I went full-time on my startup. Nearly two years later, I’ve seen my product gradually dying. I want to share some of the key mistakes I made and the lessons I’ve taken from them so you don't have to go through them. Some mistakes were very obvious in hindsight; others, I’m still not sure if they were mistakes or just bad luck. I’d love to hear your thoughts and advice as well. Background I built an English-learning app, with both web and mobile versions. The idea came from recognizing how expensive it is to hire an English tutor in most countries, especially for practicing speaking skills. With the rise of AI, I saw an opportunity in the education space. My target market was Japan, though I later added support for multiple languages and picked up some users from Indonesia and some Latin American countries too. Most of my users came from influencer marketing on Twitter. The MVP for the web version launched in Japan and got great feedback. People were reposting it on Twitter, and growth was at its peak in the first few weeks. After verifying the requirement with the MVP, I decided to focus on the mobile app to boost user retention, but for various reasons, the mobile version didn’t launch until December 2023— 8 months after the web version. Most of this year has been spent iterating on the mobile app, but it didn’t make much of an impact in the end. Key Events and Lessons Learned Here are some takeaways: Find co-founders as committed as you are I started with two co-founders—both were tech people and working Part-Time. After the web version launched, one dropped out due to family issues. Unfortunately, we didn’t set clear rules for equity allocation, so even after leaving, they still retained part of the equity. The other co-founder also effectively dropped out this year, contributing only minor fixes here and there. So If you’re starting a company with co-founders, make sure they’re as committed as you are. Otherwise, you might be better off going solo. I ended up teaching myself programming with AI tools, starting with Flutter and eventually handling both front-end and back-end work using Windsurf. With dev tools getting more advanced, being a solo developer is becoming a more viable option. Also, have crystal-clear rules for equity—especially around what happens if someone leaves. Outsourcing Pitfalls Outsourcing development was one of my biggest mistakes. I initially hired a former colleague from India to build the app. He dragged the project on for two months with endless excuses, and the final output was unusable. Then I hired a company, but they didn’t have enough skilled Flutter developers. The company’s owner scrambled to find people, which led to rushed work and poor-quality code which took a lot of time revising myself. Outsourcing is a minefield. If you must do it, break the project into small tasks, set clear milestones, and review progress frequently. Catching issues early can save you time and money. Otherwise, you’re often better off learning the tools yourself—modern dev tools are surprisingly beginner-friendly. Trust, but Verify I have a bad habit of trusting people too easily. I don’t like spending time double-checking things, so I tend to assume people will do what they say they’ll do. This mindset is dangerous in a startup. For example, if I had set up milestones and regularly verified the progress of my first outsourced project, I would’ve realized something was wrong within two weeks instead of two months. That would’ve saved me a lot of time and frustration. Like what I mentioned above, set up systems to verify their work—milestones, deliverables, etc.—to minimize risk. Avoid red ocean if you are small My team was tiny (or non-existent, depending on how you see it), with no technical edge. Yet, I chose to enter Japan’s English-learning market, which is incredibly competitive. It’s a red ocean, dominated by big players who’ve been in the game for years. Initially, my product’s AI-powered speaking practice and automatic grammar correction stood out, but within months, competitors rolled out similar features. Looking back, I should’ve gone all-in on marketing during the initial hype and focused on rapidly launching the mobile app. But hindsight is 20/20. 'Understanding your user' helps but what if it's not what you want? I thought I was pretty good at collecting user feedback. I added feedback buttons everywhere in the app and made changes based on what users said. But most of these changes were incremental improvements—not the kind of big updates that spark excitement. Also, my primary users were from Japan and Indonesia, but I’m neither Japanese nor Indonesian. That made it hard to connect with users on social media in an authentic way. And in my opinion, AI translations can only go so far—they lack the human touch and cultural nuance that builds trust. But honestly I'm not sure if the thought is correct to assume that they will not get touched if they recognize you are a foreigner...... Many of my Japanese users were working professionals preparing for the TOEIC exam. I didn’t design any features specifically for that; instead, I aimed to build a general-purpose English-learning tool since I dream to expand it to other markets someday. While there’s nothing wrong with this idealistic approach, it didn’t give users enough reasons to pay for the app. Should You Go Full-Time? From what I read, a lot of successful indie developers started part-time, building traction before quitting their jobs. But for me, I jumped straight into full-time mode, which worked for my lifestyle but might’ve hurt my productivity. I value work-life balance and refused to sacrifice everything for the startup. The reason I chose to leave the corp is I want to escape the 996 toxic working environment in China's internet companies. So even during my most stressful periods, I made time to watch TV with my partner and take weekends off. Anyways, if you’re also building something or thinking about starting a business, I hope my story helps. If I have other thoughts later, I will add them too. Appreciate any advice.

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.

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

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

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 a co-founder for a B2B AI startup. I have a development team and funds for at least a year of operations.

Hello, As the title said I'm looking for a co-founder. I built with my team a few ventures that generate revenues but I don't believe that any of them has a future. I have 15 years of experience in Software Engineering and AI. Worked in various industries, but always in data-driven applications. I spent the last 3 years as an entrepreneur and raised successfully money from VCs. ​ A few preconceptions I have: \- B2C is extremely hard. Very quickly you realize that you need to spend all your resources on marketing. \- B2B is extremely hard - but for different reasons. Sales cycles take months. If you want to reach serious buyers and decision-makers, you need to have an amazing network. Even then, companies will prioritize 90% of the time to do things internally rather than paying for anything. \- I hate when people say that "ideas are garbage", and I think that execution is overhyped. Execution is a matter of finding the right people, and paying them (I am confident to say that I can guarantee good execution). Ideas are not garbage, ideas need validation, and garbage "entrepreneurs" are too lazy to validate anything. ​ Your ideal profile: \- You have a great idea, something that has been brewing for some time but you lack resources or technical experience to execute by yourself. \- You have domain expertise, experience, and a network. If we build an MVP in 3 months, you can get 20 interviews with industry people to validate the solution. Once the MVP is built you can put it in front of another 40 people. \- You are a product person. \- You can do efficient sales calls. (Bonus: You are a sales person) If you are an ideal profile, please reach out.

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 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.

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 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.

I single-handedly built the world’s best AI investing platform. Here’s NexusTrade’s 2024 year in review

I copy-pasted the content of this article to save you a click! I’ve been developing an AI investing platform for 4 years, and I’m blown away by all of the new features I’ve gotten done! Here’s my project’s 2024 year in review —- When someone asks me what is the best way to learn how to trade and invest, I have an unbiased answer – NexusTrade.io. I started NexusTrade to empower everybody, including beginners and non-technical investors, to learn how to make smarter investing decisions. NexusTrade is the best way for a new investor to learn algorithmic trading and financial research, and I’m not the only person to think so. Just this year alone, user growth has skyrocketed from 1,703 users to 14,319 users. This is driven by new features, better research tools, and the launch of algorithmic trading. Here’s NexusTrade’s 2024 year in review, a semi-complete list of the features I’ve launched. Summarizing this year in review TL;DR: I implemented a variety of new features to enhance NexusTrade’s algorithmic trading and financial research capabilities. This includes: Cryptocurrency support Enhanced financial research, like the AI-Powered Stock Screener Unique watchlists and daily market summaries Live-trading with Alpaca. Next year, I plan to implement features to make NexusTrade more tailored for each user’s experience, and launch several unique features including copy trading and fully automated algorithmic trading. Feature-by-feature: What have I done so far in 2024? Algorithmic Cryptocurrency Trading Picture: Algorithmic Cryptocurrency Trading I kicked off the year by adding cryptocurrency support to NexusTrade. Users can now research, design, and implement automated strategies for popular cryptocurrencies, such as Bitcoin, Dogecoin, and Ethereum. AI-Powered Stock Screener and research capabilities Picture: AI-Powered Stock Screener In tandem with cryptocurrency support, I made a huge update to Aurora, the AI Assistant in NexusTrade, by implementing a natural language stock screener. This screener makes it easy to find fundamentally strong stocks. Throughout the year, I’ve made several enhancements to it. Over time, I’ve made the screener faster, more accurate, and expanded its capabilities. Using fundamental indicators within trading strategies Picture: Using fundamental indicators Doing financial research for companies isn’t enough; we also need a way to integrate this type of research into trading strategies. Thus, I’ve expanded the NexusTrade indicators, and made it possible to create strategies using metrics like revenue, net income, free cash flow, and P/E ratio. Stock watchlists with tailored, automated daily emails Picture: Stock watchlists In addition, I didn’t want the research you may have done for a stock (or list of stocks) to be forgotten. Thus, I created the most useful watchlist page of any investing platform. This watchlist makes it easy to keep track of your favorite stocks, track them over time, and even receive curated, daily emails about them. Enhanced user profile page, Google sign-ins, and two-factor authentication Picture: Enhanced user profile Keeping in theme with adding new pages to NexusTrade, many pages, such as the profile page, got a huge revamp. The new profile page is cleaner, easier to use, and allows you to secure your account more effectively, for example, by using two-factor authentication. GPT-Reports: an AI-generated analysis of every stock in the market Picture: GPT-Reports I created GPT-Stock Reports, an AI-Generated analysis of every stock in the market. This report was generated by taking each company’s earnings data and asking GPT to analyze the stock and give it a rating. Manual and semi-automated algorithmic trading with Alpaca Picture: Manual and semi-automated trading Finally, I’ve fully launched the Alpaca integration, and enabled users to execute real trades directly in the NexusTrade app! This integration has transformed NexusTrade from a financial research app into a real, algorithmic trading platform for retail investors. Concluding Thoughts When I say that NexusTrade is the best platform for traders and investors to make more money in the stock market, you may naively think that I’m biased. I created the app, and the rose-tinted glasses is bound to make every red flag look like a regular flag, right? Wrong. NexusTrade is objectively a completely new way for investors to approach financial markets. The fact that the app is so expansive is nothing short of miraculous.

🔥 AI Agents Will Skyrocket in the Coming Years—Jensen Huang Explains! 🚀#shorts #youtubeshorts #ai

🔔 Subscribe to our Newsletter: https://aientrepreneurs.standout.digital?utm_source=yt 🔔 Subscribe for more tech insights: https://www.youtube.com/channel/UCjMceG0jS4Lr5ZACzpYjHf In this exciting video, Jensen Huang shares his vision for the future of AI agents over the coming years. As AI continues to evolve, Huang explains how these agents will make massive strides in problem-solving, automation, and innovation, transforming industries worldwide. 🔹 Learn about the future progress of AI agents from NVIDIA’s CEO. 🔹 Discover how AI agents will revolutionize business and technology. 🔹 Explore the advancements AI agents will bring in the coming years. #JensenHuang #NVIDIA #AIAgents #AIProgress #ArtificialIntelligence #FutureOfAI #AIRevolution #TechInnovation #Automation #TrendingNow Join 66,000+ AI lovers with 4 free gifts🎁: 100 ChatGPT prompts, AI writer to go viral, "Building A Minimum Viable Business In Record Time" Course AND "4-Hour AI Workweek" course! Click here: https://aientrepreneurs.standout.digital?utm_source=yt ✨Exclusive Freebies and Tools: 📙 (Free Course) The 4 Hour AI Workweek: https://aientrepreneurs.standout.digital?utm_source=yt 📑 Bubble No Code AI Template: https://launchai.pro/?aff=wqp8K 🛠️ #1 AI SEO Tool: https://tryjournalist.com?aff=ge 🐤 Grow on Twitter with AI: http://app.tweethunter.io/?via=george-p 📚 Free Lead Magnets Playbook: https://aientrepreneurs.gumroad.com/l/yndih 👨‍💻 AI UI Design Tool: https://get.uizard.io/affc?offerid=3&aff_id=683 📹 Free YouTube Growth Playbook: https://aientrepreneurs.gumroad.com/l/qbswh ✍️ Free Script Writing Guide: https://aientrepreneurs.gumroad.com/l/yfhxgk 🤖 Free 100 ChatGPT Prompts: https://aientrepreneurs.gumroad.com/l/npyks ✨OUR OTHER SOCIALS: 🎙️ Podcast Deep Dive- https://podcast.standout.digital/ 💻 Check out our blog- https://www.standout.digital/blog/ 🐤 Follow us on Twitter- https://twitter.com/EntrepreneursAI 🤳 Check out our Instagram- https://www.instagram.com/standoutaientrepreneurs 📷 Dive into our TikTok- https://www.tiktok.com/@theaientrepreneurs 👨‍💼 Connect on LinkedIn- https://www.linkedin.com/company/theaientrepreneurs Video credits: @CNET Full video: https://youtu.be/kfe3ajUYSdc?feature=shared Some links may be referral links* Thank you!

I am the founder of a b2c saas - organically scaled to $2M ARR, 1.9M users. Started company when I was 22, moved to Korea, built it here over 9 years. Ask me anything

It's 12:05am on Saturday morning and I just had some coffee so I'd like to take this time to talk with the startup subreddit on my journey building a b2c saas company. Specifically on the topics of growth, product, investment/governance, or strategy. For what we are, we are the most popular AI resume builder these days - the story of the company is a bit unique since I started it as a college graduate, then moved to Korea, where I was able to turn the idea in a scaling startup via government programs and Korean VCs. These days our traction shows that we are doing a few things right. I'm happy to share any knowledge or experiences I've gained over this time! Metrics: ARR - 2M Users - 1.9M Employees - 10

I am a 17-year-old who loves coding and AI, so I launched a non-profit to teach people how to create AI websites from scratch.

Nozomio - Learn AI modern web dev for free. https://preview.redd.it/4l9jxs6h032e1.png?width=2064&format=png&auto=webp&s=2132ace94bb936eb9fcb1134d5ef2eea3df77fb9

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!

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

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

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

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

[P] My deep learning library from sophomore year in high school

I made a deep learning library in Java a while ago to help me understand how neural networks work. I implemented vanilla fully connected layers, convolutional layers, pooling layers, GRU cells, multiple gradient descent optimizers, and other cool stuff. I also strived for an object oriented framework with a Keras-like interface. It took me quite a while to understand the full backprop algorithm as I did not know how derivatives work when I started. Also, many intrinsic details about how neural networks operate were obscured behind very similar mathematical equations in most of the blog posts I've seen (although Stanford CS231 was very helpful). In the end, I derived the backprop equations for updating the weights by hand for all of the layers in the library. As such, I want to share my code and maybe help others that are learning about neural networks. Note the library is very slow. There are no fancy GPU speedups because the library is pure Java. You can test the pretrained MNIST by running TestMNISTDraw2.java in the src/tests folder that also contains other demos. Edit: Is this too "beginner" for this sub?

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.

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

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

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.

Think of Caryn AI (a 23-year-old Snapchat influencer) but with entrepreneur personas

Over the past few days, I got the AI craze and I'm really excited about this idea of solving a common pain that creators often face: keep a personnal and close relationship with their fans. ​ I came up with this idea of creating a second brain for successful entrepreneurs based on their internet knowledge (like they did for Caryn AI). ​ The end goal would be to have them own & enrich their 2nd Brain with their personal data (from WhatsApp, notion, email …). ​ Values: For successful entrepreneurs ( or any creators), the ability to scale their time. Daily summary of the most exciting conversation between 2nd Brain and their community. highlight conversation where 2nd Brain would need them to reply. Eventually, 2nd brain could take action (Reply to tweet, post etc..) For the community, 1-1 chat with Shaan & Sam 24/7. Get valuable advice for their business. Think of questions like: \- how can I make more revenue? \- what's the best marketing strategy for reaching out to users x, y, and z? ​ What do you think? Would you be interested in talking with their 2nd Brain? What would you ask them? Curious to hear your thoughts

I am a 17-year-old who loves coding and AI, so I launched a non-profit to teach people how to create AI websites from scratch.

Build and Execute an Organisational AI Strategy

AI is the hottest, most exciting technology to burst onto the scene in recent years. Its impact is so big, it is revolutionizing industries all over the globe. If you are an executive, you may be wondering how to harness AI's incredible power for your organization. Well, this course is going to show you how to do just that.

$1.2 MRR, should I do paid ads?

Hello, I launched a bootstrapped b2b SaaS end of last year and I've just hit 1.2k MRR. It's a 50-60% profit margin, so $600 are going to my pocket, I also do freelancing where most of my revenue comes from, that's about 3k monthly average. My project has essentially been stuck around this 1k MRR mark for months, I'm sticking to my strategy: Daily outreach on LinkedIn Weekly Post on LinkedIn (my company is a no code tool for building AI SEO & content workflows, so every week I share a new tool) Weekly Blog Post Reaching out to influencers/newsletter writers to see if they'd be willing to write about it. Now I'm thinking if I should set $500-$1000 monthly budget for paid ads, I'm primarily considering Google Ads and LinkedIn Ads. Essentially I'm wondering if 1.2k MRR a good point to start investing back into the company.

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.

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

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

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

Hot Take: Not all your startups need AI forced into them

I'm a final year Computer Engineering student, hence applying for jobs all around. There's this particular trend I've noticed with startups that are coming up these days. That is, even for the absolute basic stuff they'll use 'AI', and they'll think they built something 'revolutionary'. No. You're breaking your product in ways you don't realise. An example, that even some well established companies are guilty of: AI Chatbots You absolutely don't need them and it's an entire gimmick. If you really wanna implement a chatbot, connect the user to an actual person on your end, which I think is not possible if you're at a 'startup' stage. You'll need employees who can handle user queries in real time. If the user really is stuck let them use the 'Contact Us' page. A really close relative of mine is very vocal about the frustration he faces whenever he tries to use the AI Chatbot on any well known e-com website. The only case for AI Chatbot that makes sense is when it's directing the customer to an actual customer support rep if none of the AI's solutions is working for the customer. Even then, implementing a search page for FAQ is extremely easy and user friendly. Another example: AI Interviewer I recently interviewed for a startup, and their whole interviewing process was AI'zed?!?! No real person at the other end, I was answering to their questions which were in video format. They even had a 'mascot' / 'AI interviewer' avatar designed by an AI (AI-ception???). This mascot just text-to-speech'ed all the questions for me to rewind and hear what I missed again. And I had to record video and audio to answer these questions on their platform itself. The entire interview process just could've been a questionnaire, or if you're really concerned on the integrity of the interviewee, just take a few minutes out of your oh-so-busy schedule as a startup owner. Atleast for hiring employees who would make the most impact on your product going ahead. I say the most impact, because (atleast as a developer) the work done by these employees would define how robust your product is, and/or how easily other features can be integrated into the codebase. Trust me, refactoring code later on would only cost you time and money. These resources would rather be more useful in other departments of your startup. The only use case for an AI Interviewer I see is for preparing for an actual interview, provided that feedback is given to the user at the earliest, which you don't need to worry about as a startup owner. So yeah, you're probably better off without integrating AI in your product. Thank you for reading. TLDR; The title; I know AI is the new thing and gets everyone drooling and all, but for the love of God, just focus on what your startup does best and put real people behind it; Integrating AI without human intervention is as good as a broken product; Do your hiring yourself, or through real people, emphasizing on the fact that the people you hire at an early stage will define your growth ahead;

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.

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

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

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

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

I'm a dev with zero fucking ideas. Help?

Long-time lurker, first-time poster here. I'm hoping you guys can help me out. I consider myself an above average engineer. With over 8 years of industry experience, I can whip out an MVP fast and iterate quickly. I love coding and learning new tech, but here's the issue—I've got absolutely no clue what to build. It's like I'm the least creative person I know, and can't find even one problem to solve. I've tried everything I can think of: Scrolling through ProductHunt until my eyes bled Asking non-tech friends about their "pain points" Stalking Twitter/X to see what people are building Experimenting with new AI tech to explore possibilities I've even attempted to build products. Almost 6 months ago, I started working on an AI conversation app to help non-native speakers like myself improve their English. But I soon realized there were already hundreds of apps doing this, and doing it much better than I could. I abandoned the project, figuring it wasn't unique enough. Same story with a couple of other projects that I started working on and abandoned later. So my question is how the heck you all come up with ideas? Any advice, commiseration, or hell—even random ideas you don’t want to build—would be greatly appreciated.

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

The Drawing of the Three - Once you look through the veil, nothing is the same again. (I will not promote)

Originally published Nov 5, 2024 In my last post, I talked about assembling a series of filters to use to view the startup landscape, which led me to a few conclusions about what opportunities I should pursue. What did I see through those filters? What I saw through the moire pattern of those two lists overlaid by one another is what I think will be the third great monetization strategy for the internet, matching the pattern of: web1 => Ad monetization web2 => Subscription monetization web3 => For AI, neither of those work anymore, which demands something new. But what? Well that’s the important part, isn’t it? Should I just up and tell you? Yawn. The climax of a movie is at the climax, if they tell you the crux at the beginning, it’s a lot less fun (usually). The standard bearer for web1 and ads was Google (with countless followers), and essentially every website adopted that model for their first pass at content monetization. Google has been… let’s call it fairly successful… so it’s not a bad way to look at things. How many websites live and die by selling advertising? The standard bearers for web2 and subscriptions were Salesforce (for B2B SaaS) and Netflix (for B2C SaaS), with countless followers, to the extent that SaaS has been the dominant startup monetization thesis for the last 15+ years. It’s more old and tired by now than most American politicians, but how many websites live and die by people entering payment details for a monthly or annual subscription? Evidence proves those models for web1 and web2 worked well enough that countless businesses depend on them, and countless fortunes have been made and lost surfing the waves, or crashing against the shorelines, of ads and subs. But it’s also apparent (to me, at least) that now that AI is the dominant startup thesis, neither ads nor subs are going to prevail in an AI-centered world, and for one simple reason: Those monetization strategies are for humans, and AI bots are not humans. Changing Environments Require Changing Strategies Every so often, there’s a fundamental shift that demands everything in the ecosystem adapt to a new habitation strategy to survive. We’ve seen this repeatedly across Earth’s ecology (for instance, introducing free oxygen to the atmosphere, producing respiration while destroying all the life forms that existed before oxygen permeated the atmosphere), and across human society (for example, how nuclear bombs changed war, and how drones are changing it again, for less violent examples, consider the adoption of computers and the subsequent adoption of smartphones). Now the ecosystem of the internet has changed irrevocably, opening up countless new and interesting niches to occupy. Humans may see an ad and buy something stupid (or, occasionally, not-stupid), but an AI won’t unless its programmed to. And subscriptions are designed for humans to consume content at a human rate, not for an AI that can choke down an entire database of content (whatever it may be) at whatever speed the servers can manage. Changing conditions require changing strategies. It was clear to me that: The introduction of AI bots to the internet ecosystem was, is, and will be massively disruptive for a very long time The internet population of bots already exceeds humans and is growing faster than the human population The two dominant monetization strategies are not relevant to bots That disruption of expectations across the ecosystem demands a third strategy, a new strategy to handle a massive change in an existing system. And that strategy needs to accommodate, support, and monetize the new demands from the vast armies of new participants in the internet ecology. Therefore, a method that converts bots from an expense into a revenue source would become a dominant monetization strategy, and therefore whoever owns that strategy will be a dominant player in the internet ecosystem. Set the realization of semi-practical, semi-useful AI against a backdrop of technology cycles that have, in the distant past (in internet terms) produced ads and subs, and more recently produced enormous investment into fintech and crypto, I started to see a path that felt like it would grow over time to become a new monetization strategy that works in the AI ecosystem. Sun Tzu had a couple drinks, saw a couple things… There’s at least, and possibly only, two things I know about fighting: You cannot fight the tide, and it’s much harder to fight an uphill battle. If my whole thesis on this go-around was to go with the flow, and that trickle of insight was leading me from my overlook along a roaring flow of cash coursing through a valley filled with AI startups, where exactly would it lead me? Most rivers lead to the sea eventually, but they can take winding paths, and sometimes the quickest route from the mountain to the sea isn’t to follow the river, but to understand where the river leads and go there instead. Getting a view from on high can save you a lot of time on your journey. But before I get to where the path has led (or is leading) that will explain the objective I’ve identified, and the deliverables I have to produce to reach it, let’s talk about a few of the steps on the path I’ve been taking that highlight the process I followed. I figure if I explain the steps I’m taking, as I’m taking them, it may be easier for people who haven’t trod this route before to follow me and understand how to carve their own course towards their own objectives. And maybe the real treasure will be the friends we make along the way. (I will not promote)

For anyone working on LLM / AI startups

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

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

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

Created the Shopify Alternative in a 3rd world country “I will not promote”

Built a Shopify alternative I’ve been a long-time follower of this subreddit and have always valued the insights shared here. Today, I’m reaching out to share our story and seek advice or guidance on potential next steps for our business. Four years ago, we set out to build a local e-commerce platform tailored to the unique challenges of operating in a third-world country where global solutions like Shopify fall short. Shopify, while a fantastic platform, doesn’t provide localized support or integrations here, and the costs of running a Shopify store are prohibitively high due to: The need for multiple apps to replicate basic functionality Expensive international support calls or long chat queues Higher payment gateway fees (no Shopify Pay) USD-only subscription payments, which incur additional bank conversion fees And more We built a solution that addresses these pain points, and today, we’re proud to have over 4,000 merchants on our platform, with 1,600+ paying customers. We’re processing over $1 million per month across 50,000+ orders, which translates to a significant impact in our local economy. As experienced founders, we’ve managed our financials meticulously, allowing us to thrive while many local competitors have shut down. However, scaling in our current economic climate has been challenging, and raising capital has proven to be incredibly tough. We’re exploring strategic options, including potential partnerships, acquisitions, or investments. For example, we believe our platform could be an attractive opportunity for a player like Shopify or another company looking to expand into emerging markets. I’m reaching out to this community to ask: Are there doors we haven’t knocked on? Are there opportunities or strategies we might be overlooking? Any advice, introductions, or insights would be immensely appreciated. Thank you for taking the time to read this, and I look forward to any feedback or ideas you might have! [post refined by AI]

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

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

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

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

$1.2 MRR, should I do paid ads?

Hello, I launched a bootstrapped b2b SaaS end of last year and I've just hit 1.2k MRR. It's a 50-60% profit margin, so $600 are going to my pocket, I also do freelancing where most of my revenue comes from, that's about 3k monthly average. My project has essentially been stuck around this 1k MRR mark for months, I'm sticking to my strategy: Daily outreach on LinkedIn Weekly Post on LinkedIn (my company is a no code tool for building AI SEO & content workflows, so every week I share a new tool) Weekly Blog Post Reaching out to influencers/newsletter writers to see if they'd be willing to write about it. Now I'm thinking if I should set $500-$1000 monthly budget for paid ads, I'm primarily considering Google Ads and LinkedIn Ads. Essentially I'm wondering if 1.2k MRR a good point to start investing back into the company.

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!

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

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

Behind the scene : fundraising pre-seed of an AI startup

A bit of feedback from our journey at our AI startup. We started prototyping stuff around agentic AI last winter with very cool underlying tech research based on some academic papers (I can send you links if you're interested in LLM orchestration). I'm a serial entrepreneur with 2x exits, nothing went fancy but enough to keep going into the next topic. This time, running an AI project has been a bit different and unique due to the huge interest around the topic. Here are a few insights. Jan \~ Mar: Research Nothing was serious, just a side project with a friend on weekends (the guy became our lead SWE). Market was promising and we had the convinction that our tech can be game changer in computer systems workflows. March \~ April: Market Waking Up Devin published their pre-seed $20m fundraising led by Founders Fund; they paved the market with legitimacy. I decided to launch some coffee meetings with a few angels in my network. Interest confirmed. Back to work on some more serious early prototyping; hard work started here. April \~ May: YC S24 (Fail) Pumped up by our prospective angels and the market waking up on the agentic topic, I applied to YC as a solo founder (was still looking for funds and co-founders). Eventually got rejected (no co-founder and not US-based). May \~ July: VC Dance (Momentum 1) Almost randomly at the same time we got rejected from YC, I got introduced to key members of the VC community by one of our prospective angels. Interest went crazy... tons of calls. Brace yourself here, we probably met 30\~40 funds (+ angels). Got strong interests from 4\~5 of them (3 to 5 meetings each), ultimately closed 1 and some interests which might convert later in the next stage. The legend of AI being hype is true. Majority of our calls went only by word of mouth, lots of inbounds, people even not having the deck would book us a call in the next 48h after saying hi. Also lots of "tourists," just looking because of AI but with no strong opinion on the subject to move further. The hearsay about 90% rejection is true. You'll have a lot of nos, ending some days exhausted and unmotivated. End July: Closing, the Hard Part The VC roadshow is kind of an art you need to master. You need to keep momentum high enough and looking over-subscribed. Good pre-seed VC deals are over-competitive, and good funds only focus on them; they will have opportunities to catch up on lost chances at the seed stage later. We succeeded (arduously) to close our 18\~24mo budget with 1 VC, a few angels, and some state-guaranteed debt. Cash in bank just on time for payday in August (don't under-estimate time of processing) Now: Launching and Prepping the Seed Round We're now in our first weeks of go-to-market with a lot of uncertainty but a very ambitious plan ahead. The good part of having met TONS of VCs during the pre-seed roadshow is that we met probably our future lead investors in these. What would look like a loss of time in the initial pre-seed VC meetings has been finally very prolific, helping us to refine our strategy, assessing more in-depth the market (investors have a lot of insights, they meet a lot of people... that's their full-time job). We now have clear milestones and are heading to raise our seed round by end of year/Q1 if stars stay aligned :) Don't give up, the show must go on.

How to get funding for startup ? I will not promote

I will not promote. Software startup based out of Minnesota us. I've built and launched a product that is gaining traction, solving a problem that has frustrated software developers and product teams for years. The problem: Software development is slow, expensive, and full of inefficiencies. Developers spend hours on repetitive coding tasks, project managers struggle with bottlenecks, and businesses waste time translating product requirements into actual code. The solution: My product automates a large portion of software development. It acts as an AI-powered assistant for developers, taking high-level requirements and turning them into functional code while integrating with existing codebases. It can read, understand, and modify software projects in a structured way—cutting development time drastically. The potential: Businesses are always looking for ways to cut costs and speed up development. With the rise of AI, companies are increasingly adopting automation, and this tool fits perfectly into that wave. Imagine a world where software teams are 10x more efficient because AI handles the grunt work, and developers focus on the bigger picture. It’s not about replacing developers—it’s about supercharging them. The current status: The product is live and in use. The user base is growing, and I’ve proven demand. Now, I need to figure out the best funding model to scale—whether that’s bootstrapping, VC, grants, or some hybrid approach. If you have experience in startup funding or have scaled a tech product, I'd love to hear your insights. DM me if you're open to discussing strategies!

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.

Hot take: AI will replace non-technical founders before technical founders [I will not promote]

I think the prevailing theory is AI is going to empower non-technical people to create complex systems just by writing a prompt or prompts. I think a variant of that is getting close which are agentic workflows where something triggers an agent and it does things autonomously. These sort of systems are starting to pop up everywhere (zapier, n8n, others...) however we're a ways off from these being able to respond in near real time. Long story short you'll still need to have code to run and someone to write that code (at least for a few more years) I've been using Deepresearch by OpenAI since Monday. I'm a technical founder without a formal business background. I've had it do product market fit analysis, sam/tam estimates, go to market strategies and it's producing fantastic reports. I could see it handling pretty much 90% of the non-technical business work that doesn't involve action in the physical world. It produced the content of a very well thought out pitch deck for one of my businesses. It's identifying potential customers. It's pretty damn crazy. Like right now I have it building a financial pro-forma for my data room. In fact it finished before I could write this post!

How would I go about using ai to analyze stats and creating predictions based off of data?

Sorry if I’m asking the question the wrong way but I’ve been a avid sports bettor for years and with the recent surge in ai and it being more accessible to the average person Ive been thinking it were some how possible to use with betting I mean it’s all numbers at the end of the day. If I were to be able to feed info to the bot & have it analyze past games it could pick up on trends and predict outcomes for specific stats and what not. Obviously there is no way to predict something 100% but even if I were to be able to make something that was accurate 40% of the time I look at it as a win. I know alot of bettors of late have been implementing the ai into their strategies as well so I know it’s possible but my question more so is where would be the right direction to start in for some one with ver little knowledge of ai outside of chatgpt?

AI And Google's Algorithm Updates Push Us To Adopt New Customer Acquisition Strategies

Hello everyone, More and more founders seem to be struggling with SEO and organic traffic… Google has made tons of changes these last 2 years. Their zero-click policy, combined with their own generative AI model now answering questions in the search results, makes it more challenging than ever to attract new customers on Google. I made a post about that and I explore alternative solutions that still work well in 2024: https://kwatch.io/the-impact-of-ai-and-google-algorithm-updates-on-seo-pushes-us-to-adopt-new-strategies As a startup founder continuously exploring new customer acquisition strategies, I would love to hear your opinion/advice. Do you have success with SEO? Would you mind sharing your best customer acquisition strategies? Arthur

From “Green” to “Smart” – Tom Gorski’s Word of Advice

Sharing this interview with entrepreneur Tom Gorski. I think it contains a few nice tips for beginner entrepreneurs. What is the problem with the term “Green?” what are the top 3 mistakes entrepreneurs make that can prevent them from enjoying the sweet taste of success? And what should young entrepreneurs always keep in mind? Continuing our expert interview series, we asked entrepreneur Tom Gorski to share some of his secrets to success with us. Gorski is the CEO and Co-Founder at SaaSGenius.com, and an Inbound Marketer & Growth Hacker at InboundWay.com. His career spans over 12 years of developing and implementing online marketing, SEO and conversion optimization campaigns. He defines his biggest accomplishment to date as “achieving 4500% growth for one of my clients over a three­year period.” logo-saasgenius Q: It’s no secret that the SaaS market is saturated, as new companies are having very hard time acquiring, retaining and monetizing users. In your view – what are the top 3 mistakes SaaS companies make? What are some key differentiators you recognize in a successful product? A: Mistake No. 1: Product-market fit is not good enough There are a number of reasons for this, including the fact that inertia, incumbency and bureaucracy are all working against you. For emerging companies, this means finding a way to be exponentially better with fewer resources. As a result, focus is key. Mistake No. 2: Not Specializing Your Sales Roles When you specialize your sales people, you allow them to focus, which creates greater output form your sales team. Mistake No. 3: You Need a Niche To be able to market and sell well, you need to have a niche. The world is noisy and messy, and you’ll struggle if you don’t have a sharp, direct message. When you try to speak to everyone, no one can hear you. Q: Which innovative trends do you recognize in the high tech world nowadays? A: “Green” was a mega trend of the last decade and while it will continue to be very important, there will be a shift towards “smart” solutions, which are intelligent, connected and have the ability to sense, report, and take the right action. Smart solutions will be everywhere around us from smart clothing, phones, to smart homes and smart cities. Q: What is the most significant advice you can give young entrepreneurs? A: Being very successful means learning from those who have already achieved success. Having a mentor is an amazing blessing to an entrepreneur, but not everyone can find one in person. My advice is to work smarter, not harder. This is the most non-intuitive observation I will probably make. If you want to compete in the arena, hard work isn’t enough. And judging yourself on how hard you work, rather than how smart you work can be fatal. Q: We are flooded with buzzwords lately – VR / AI / Bots… where do you think the software world is heading? A: AI and bots are a very hot topic in 2016 and it’s sometimes hard to distinguish the real potential behind the hype. My point of view is that, like with many things, there’s no revolution but evolution. It’s unrealistic to think that AI can become mainstream in SaaS products without proper AI infrastructure. SaaS delivery will significantly outpace traditional software product delivery, growing nearly five times faster than the traditional software market and will become a significant growth driver for all functional software markets. By 2019, the SaaS software model will account for $1 of every $4 spent on software. Q: Let us in on some of your secrets… where do you look for innovation? For inspiration and revolutionary ideas? A: Ideas for new startups often begin with a real problem that needs to be solved. And they don’t come while you’re sitting around sipping coffee and contemplating life. They tend to reveal themselves while you’re at work on something else. Start with brainstorming with problems that you are personally invested in. Building a business is hard and takes the kind of relentless dedication that comes from personal passion. Perhaps the greatest factor that determines whether or not an entrepreneur will be successful isn’t the business idea itself, but rather the entrepreneur’s willingness to try to turn the idea into reality. Great ideas are abundant, but it’s what we decide to do with them that counts. Original post: http://saasaddict.walkme.com/from-green-to-smart-tom-gorskis-words-of-advice/

10,000 users in a month

Our team raised an angel fund and have been quietly iterating over the last year. We launched a month ago and have just about 10,000 users with a small amount of revenue. We are an AI company targeting consumers and beauty. Has anyone raised in the space who could shed some light on what worked/didn’t work for them? Our product is stickier than anyone on the team ever imagined.

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!

Building in the open with Founder University - I will not promote

Published Oct 30, 2024 I am on my fifth startup. I ran the last one for a decade, that’s a whole story. A hell of a story. But a different story. I’ll tell it to you when I can, but not right now. The one before that was an e-commerce site that did pretty well but I didn’t love it. Before that were two service businesses. The first one I did for the love of the game, the second one was an attempt to make people stop asking me to fix their computer by charging them outrageous prices, which backfired horribly when they were eager to pay. None are relevant except to say I’ve been around the block and have the scars to prove it. When it was time to get back out there, I wanted to use all I’ve learned to do better. Before I talk about what those lessons produced, I’m going to talk about what those lessons were. Cause before effect, after all. One thing I wanted to do better this time was pattern matching - making the startup look the way that the industry and investors “expect” a startup to look. My last startup was an awesome idea with awesome tech (still is, but like I said, another story), but that one didn’t match patterns. It didn’t match investor patterns, industry buying patterns, patterns of existing, immediate, recognized and admitted needs. Because it didn’t “look” right to anyone, everything about it was way harder than necessary. The “make it look right” approach runs the risk of building a cargo cult, imitating the trappings of something but without understanding the essence of that something, but then again, a thing that looks like a knife is going to make a better knife that a thing that looks like a bowling ball, so sometimes just sharing apparent similarities can get you pretty far, even if it doesn’t get you all the way there. Like how mimicking someone’s accent makes it easier for them to understand you. For this one, I wanted to adopt every tool, method, and pattern that I knew “the industry” wanted to see to minimize the friction from development, go-to-market, scaling, adoption, and that would make investment optional (and, therefore, available if desired) instead of necessary (and, therefore, largely unavailable). That required establishing some expectations for successful patterns I could match against. What patterns am I matching to? Here’s a general sketch of my pattern matching thought process: Software first and software only. It’s the easiest industry to start a business in, lowest startup costs, and easiest customer acquisition. I wanted to build software for an element of the industry that’s actively emerging (and therefore has room to grow) and part of an optimistic investor thesis (and therefore has a cohort of people who are intent on injecting capital into the market to help it grow). It needs to fills a niche that is underexplored (low competition) and highly potent (lots of opportunity), while being aligned to recognized and emerging needs within the industry (readily adopted). I wanted it to have evidence supporting the business thesis that proves the demand exists, but demonstrates that the demand is unanswered (as of yet) by sufficient or adequate supply.* I wanted the lowest number of dominoes to line up and tip for everything to work correctly - the more dominoes in the line, the less likely the last one will fall. I wanted to implement modern toolsets for everything, wherever possible. I wanted to obey the maxim, “When there’s a gold rush, don’t mine the gold, sell the picks and shovels.” Whatever I chose would need to produce cash flow almost immediately with minimal development time or go-to-market delays, because the end of ZIRP killed the “trust me bro” investment thesis predominant over the last 15 years. I wanted to match to YC best practices, not because YC can predict what will definitely work, but because they’ve churned through so many startups in the last 15 years that they have a good sense of what will definitely not work. And I wanted to build client-centric, because if my intent is to to produce cash flow immediately, we need to get clients immediately, and if we need to get clients immediately, we need to focus on what clients need right now. Extra credit: What’s the difference between a customer and a client? Note: Competition is awesome! Competition is validating and not scary, because competition proves a market exists. But competition, especially mature competition against an immature startup, makes it harder to break into a space. A first mover advantage isn’t everything, but seeing demand before it’s sufficiently supplied is a great advantage if you’re capital constrained or otherwise unproven. Think about how much money the first guy to sell fidget spinners or Silly Bandz made versus how much money the last guy to order a pallet of each made. Finding demand that exists already but is as of yet insufficiently satisfied is a great place to start. What opportunity spaces are most relevant? The industries and markets I chose to observe were: AI, because if I’m following a theme & pattern for today, it’s AI. Fintech, because cash is king, and fintech puts your hands on cash flow. Crypto/blockchain, because that’s the “new” fintech (or maybe the “old-new” fintech?), and crypto creates powerful incentives and capital formation strategies, along with a lot of flexibility for transaction systems. Tools, particularly unmet demand in tools, that enable these industries. If you wanted to do some brief and simple homework, you could map each of those bullets to several of the numbered list items preceding them. The reasoning was pretty simplistic - AI is what people want to build and invest in now, while fintech and crypto/blockchain are what people were building and investing in for the last major investment thesis. That means that there’s demand in the market for AI and AI-adjacent startups, while there’s a glut of underutilized and highly developed tools within fintech and crypto/blockchain, with a lot of motivated capital behind the adoption. When someone is thinking “I built this thing and not enough people are using it”, and you then build something that uses it creates a great way to find allies. This rationale harnesses technology that is being built and financed now (which means it needs tools and support methods, and a lot of other “picks and shovels”), while leveraging technology that was recently built and financed and is eager for more widespread adoption of the existing toolkits, which makes it suitable for using to build the AI-adjacent tools that are in demand now. It’s like two harmonics producing constructive interference - it makes two waves into one larger wave, which gives me more momentum to surf against. This was a learning process, and I iterated against my general paradigm repeatedly as I learned more. Neither of us have the patience to go through that in excruciating detail, so I’ll cover the highlights in my next post. Extra credit answer: A customer gets a product, a client gets a service. Challenge: Is software a product or a service?

New to Startups; Where do I start?

I have an idea for an specialized AI based software system in a particular market that I think, if done well, could be a very helpful and lucrative software/AI (both for its owners as well as its users). It hasn't been properly implemented into any form that I or my associates have been able to find and I believe that now is the perfect time to start its development. I'm an entrepreneur, have started several successful companies over the years and am well experienced in all things business. But, none of my companies have involved creating a brand new product or would fall into the "Startup" category. It's a whole new world to me. That being said, I'm not sure what the proper steps are to make this idea come to fruition and am hoping for a point in the right direction. How do people usually go from idea to launch? I imagine there are 2 distinct things I need right now, funding for the project and a partner to help create the software. Step 1 would be the partner. For this partner, I'm not sure where to start to find this person. I'd imagine I need someone that's experienced in machine learning, AI engineering, software development, programming, etc. Or a combination of people with those skills. Since none of my companies are startup or tech based, I don't have connections to anyone with those skills. If I go around looking for a partner with those skills, I'll surely need to explain my idea to them and will need to be able to protect my idea before hand. Do I copyright it? Make them sign an NDA? What's common business practice? Where do I go to look for a partner with those skills? For funding, I can fund the initial stages of the project for a handful of months. From there, I'd like to find some kind of investment. But that sounds like a bridge to cross when I get further down that road. Looking forward to starting down this road and hopefully making something that benefits and pushes forward this new world of AI!

Hot Take: Not all your startups need AI forced into them

I'm a final year Computer Engineering student, hence applying for jobs all around. There's this particular trend I've noticed with startups that are coming up these days. That is, even for the absolute basic stuff they'll use 'AI', and they'll think they built something 'revolutionary'. No. You're breaking your product in ways you don't realise. An example, that even some well established companies are guilty of: AI Chatbots You absolutely don't need them and it's an entire gimmick. If you really wanna implement a chatbot, connect the user to an actual person on your end, which I think is not possible if you're at a 'startup' stage. You'll need employees who can handle user queries in real time. If the user really is stuck let them use the 'Contact Us' page. A really close relative of mine is very vocal about the frustration he faces whenever he tries to use the AI Chatbot on any well known e-com website. The only case for AI Chatbot that makes sense is when it's directing the customer to an actual customer support rep if none of the AI's solutions is working for the customer. Even then, implementing a search page for FAQ is extremely easy and user friendly. Another example: AI Interviewer I recently interviewed for a startup, and their whole interviewing process was AI'zed?!?! No real person at the other end, I was answering to their questions which were in video format. They even had a 'mascot' / 'AI interviewer' avatar designed by an AI (AI-ception???). This mascot just text-to-speech'ed all the questions for me to rewind and hear what I missed again. And I had to record video and audio to answer these questions on their platform itself. The entire interview process just could've been a questionnaire, or if you're really concerned on the integrity of the interviewee, just take a few minutes out of your oh-so-busy schedule as a startup owner. Atleast for hiring employees who would make the most impact on your product going ahead. I say the most impact, because (atleast as a developer) the work done by these employees would define how robust your product is, and/or how easily other features can be integrated into the codebase. Trust me, refactoring code later on would only cost you time and money. These resources would rather be more useful in other departments of your startup. The only use case for an AI Interviewer I see is for preparing for an actual interview, provided that feedback is given to the user at the earliest, which you don't need to worry about as a startup owner. So yeah, you're probably better off without integrating AI in your product. Thank you for reading. TLDR; The title; I know AI is the new thing and gets everyone drooling and all, but for the love of God, just focus on what your startup does best and put real people behind it; Integrating AI without human intervention is as good as a broken product; Do your hiring yourself, or through real people, emphasizing on the fact that the people you hire at an early stage will define your growth ahead;

Equity vesting schedule as CTO - I will not promote

Hi everyone, in short I recently got an offer as CTO for a start-up with 17% equity vesting in 3 years. The product is like 6 months away from MVP but the co-founders had the core idea proved and figured out (it's an AI company), so my duty is to implement and deploy it. My question is that the first cliff is at the 13th month for 3%, which is definitely after the product is built. What if before the 13th month they just kick me off the bus? Should I ask for a 3% or sth at Day 0? Plus is that vesting schedule common (13th month, 25th month and 37th month) for tech start-up? Oh btw I'm getting paid with a very low almost 0 level until seed investment. Much appreciated for your input! I will not promote.

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

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

Looking for a tech cofounder. Revoltionary (yes really!) gig economy app. I will not promote.

Hey everyone! I’m building a new gig-work app that cuts out the hassles of interviews, applications, and sky-high fees. We’re aiming to make it easy for businesses to hire qualified freelancers for short shifts or one-off tasks—and for freelancers to set their own rates and get paid quickly. Why This App? Time-Saving Model: Instead of posting jobs and conducting multiple interviews, employers can instantly book from a list of KYC-verified freelancers who showcase their skills via 30-second video bios. Cost Leadership: We plan to charge only 5%, far below the 15–50% common in other gig platforms. This keeps more money in the pockets of both freelancers and businesses. Proven Demand: A beta test in 2018 drew nearly 600 active users, validating that there’s appetite for a simpler, fairer way to fill short shifts. About Me 20+ years’ experience in payroll, workforce management, and operations for Fortune 500 companies. Led cross-functional teams, implemented large-scale solutions, and believe in building with a user-first mindset. Offering meaningful equity—I want a true partner, not a hired gun. Who I’m Looking For Full-Stack Developer (comfortable with Node.js, React, Python, or similar and ML/Ai) who can manage everything from front-end to database integration (ideally Postgres/MySQL) and build a same day payments system. Passion for creating solutions that genuinely help gig workers and small businesses. Excitement to collaborate on the product roadmap, from the booking interface to same-day payment features. The Opportunity Major Market: The gig economy is huge and still growing. If we nail speed, cost-effectiveness, and ease of use, we can capture a significant share of it. Remote-Friendly: We can work together from anywhere, though I’m planning to relaunch in London where the initial beta gained momentum. If this sounds like your kind of challenge, drop a comment or DM me. Let’s chat about how we can merge our strengths—my operations background and your technical expertise—to build a platform that truly transforms the gig-work experience. Thanks for reading, and I look forward to creating something impactful together!

Technical entrepreneur looking for next team

Hi everyone, I'm a 10+ year veteran software developer with a proven track record of building consumer-facing products (shipped 10+ projects, 5 for consumers). However, I'm not looking to build another consumer facing product (we all know how difficult that is) unless you have the network and funds. I'm gearing up for my next venture and searching for the perfect co-pilot (or two!) with equal splits. -- Here's the skinny: You (ideal): Experienced (ideally with at least one failed project under your belt - learning is key!) Ready to grind and U.S based. Titles are meaningless - passion and hustle matter most. Are tired of tarpit ideas (dating app, fitness app, etc.) Bonus Points: Another technical co-founder to build magic with. Non-technical rockstars with skills in customer acquisition, fundraising, or deep industry knowledge. -- Please send me a DM! Let's chat and see if we can build something together. -- Full disclosure: I did use AI to write some of these because I'm not super great at writing these out

Looking for a technical cofounder with experience in building websites and marketplaces

Are you passionate about revolutionizing traditional processes? Do you have the expertise to build scalable platforms and want to be part of something transformative? I’m a second-year Economics student at the University of Warwick with a deep drive for creating impactful solutions. I’m seeking a technical co-founder to join me in building a startup dedicated to transforming how startups hire entry-level talent. About the Project I’m developing a recruitment marketplace that connects early-stage and growing startups with talented students and graduates. Our goal is to streamline the hiring process, making it hassle-free for startups while creating meaningful career opportunities for the next generation of talent. What I’m Looking For in a Technical Co-Founder I need someone who can complement my non-technical skills and help take this project to the next level. The ideal co-founder will have: A strong background in programming online marketplace platforms. Experience managing large databases efficiently. Knowledge in machine learning and AI, with a vision to integrate these in future features. Skills in scaling online platforms for a larger audience. The ability to work in synergy with me to shape and execute the vision. A passion for the idea—I’m happy to share more details in a meeting! Key responsibilities will include platform development, handling backend work, deploying the MVP, aiding in design, and collaborating on product iterations. About Me I bring experience in business strategy, operations, finance, product/project management, marketing, and sales—essentially, I cover everything except the technical aspects of development. I previously worked on a social communication platform for school students during high school. I also gained valuable experience as a business analyst in another startup. Why Join me? This is an exciting opportunity to build a product from the ground up, make an impact in the startup ecosystem, and grow alongside a venture poised to redefine hiring. We need: A seamless MVP launch. Networking efforts to onboard startups and expand our reach. Together, we can create something transformative, fostering innovation and enabling career growth for students while helping startups find the talent they need to succeed. If you’re excited about the prospect of building something revolutionary and have the technical skills to complement my business acumen, I’d love to connect. Let’s discuss how we can work together to create the next generation of hiring solutions. Please DM if you are interested in getting to know more about this project! Looking forward

Lessons from 139 YC AI startups (S23)

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

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

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

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

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

Non-technical founders with experienced outside vendor — ok?

I’m a non-technical cofounder of early stage startup. (“Non-technical” but I’ve developed multimedia courseware and led teams in the past (LMS, edu content, no code). My question: how crucial is it that my other biz founder and I have a technical co-founder for our data- and AI-driven product rather than use an experienced vendor whose team has been doing machine learning and AI for 10 years? During our manual work as consultants we have identified a problem in a niche market that can be solved via a combo of hard-to-gather data and AI (and other market-specific stuff that that we will train our LLM on). We’ve done market research, designed and validated the solution with potential customers in numerous interviews via click-through prototypes/wireframes, quantified TAM, SAM, SOM, written biz plan, etc. We have deep experience in our market having proven expertise over years. But as we’ve been learning about fundraising (we hope to begin a seed round in early 2025) we continually hear about the importance of technical cofounder. We get it— but our product will only be half-developed by a technical dev team. The other aspect to the product is: gathering hard to find data, and figuring out relationships in the data — that we will do via mapping work with a cohort with unique expertise in our niche market. Also our outside vendor is very reputable with years’ experience in AI and machine learning prior to the latest gen-AI craze — he’s not a newbie and has an established dev team. And our platform is not a consumer product but a more complicated SaaS product. Like, you can’t just code it by yourself. Sure, in the long run we can hire/bring everything in house, but would investors shy away from working with us if our short-term dev effort does not have a “technical” co-founder? Thanks for your thoughts.

The #1 Mistake Entrepreneurs Make – And How to Avoid It Before Launching Your Startup (I will not promote)

Why So Many Startups Fail Before They Even Begin A huge number of early-stage entrepreneurs fall into the same trap: They get excited about their idea but don’t validate if the market actually wants it. They invest time and money building something nobody will pay for. They focus on execution first instead of proof of demand. By the time reality hits, they’ve burned months (or years) and thousands of dollars—just to learn the hard way that they started wrong. How do we prevent this? What’s the best way to validate a business idea before wasting resources? According to your unique experiences, what’s the Smartest Way to Validate a Startup Idea? I’ve been working on new approaches to validation that combine: ✔ AI-powered feasibility analysis to assess business potential instantly. ✔ Market research frameworks that help test demand before launching. ✔ Lean execution models that prevent unnecessary risk. But I want to hear from you: How did YOU validate your startup idea before launching? What methods have actually worked to confirm demand? What’s one mistake you made in your early-stage startup that others can avoid? The best insights come from real founders who’ve been in the trenches. Let’s break down what actually works. Drop your thoughts below! 👇 (I will not promote).

Hot take: AI will replace non-technical founders before technical founders [I will not promote]

I think the prevailing theory is AI is going to empower non-technical people to create complex systems just by writing a prompt or prompts. I think a variant of that is getting close which are agentic workflows where something triggers an agent and it does things autonomously. These sort of systems are starting to pop up everywhere (zapier, n8n, others...) however we're a ways off from these being able to respond in near real time. Long story short you'll still need to have code to run and someone to write that code (at least for a few more years) I've been using Deepresearch by OpenAI since Monday. I'm a technical founder without a formal business background. I've had it do product market fit analysis, sam/tam estimates, go to market strategies and it's producing fantastic reports. I could see it handling pretty much 90% of the non-technical business work that doesn't involve action in the physical world. It produced the content of a very well thought out pitch deck for one of my businesses. It's identifying potential customers. It's pretty damn crazy. Like right now I have it building a financial pro-forma for my data room. In fact it finished before I could write this post!

Better ways to get leads for my MVP development service? I will not promote

Hi I'm Jay, I've been a dev for over 7 years. I've worked with organisations like the Qatar Airlines Currently I run a small dev shop focusing on building MVPs for non-tech founders specifically. Now I've been running meta ads and it's been okay. Working on 2 interesting projects currently. The workload is lower than our capacity but it's alright. The problem is- most of the leads don't seem to be qualified enough and fall through. Instead of actual founders who want to build something and know what it takes, I get wannabe entrepreneurs who have way too much expectations for absolute peanuts for budget Bare in mind, I already charge pretty low for the MVP as one of my USPs is cost-effective ($5k). I legit had a meeting with someone who expected me to develop a fully fledged AI powered MARKETPLACE for $1000😭 It's so hard not to take offense to things like that and absolutely lose my sh*t because WHAT💀 Any advice on where or how to get qualified and serious clients? Is there a way to target founders who've raised pre-seed or seed funding? I know it's a long shot since most startups don't get funded pre MVP but just something I'm trying to consider just in case Any and all advice would be appreciated, thank you🙏🏼 PS: Sorry about the rant halfway through😭🙏🏼

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.

Product hunt is good or not?

Hey, everyone! I’m engineer of the AI-powered marketing platform for small businesses and entrepreneurs, and we launched on Product Hunt this November 19th at 10:00 AM. Actually, I can’t believe that it’s almost a year since establishment and here we are. What’s this post about? Mainly, to share that my team and I have made it to that stage. We worked hard the whole year and successfully completed all planned roadmap stages. Secondly, I’d love to hear your motivational stories about product launches or demotivational ones about the general meaninglessness of that idea. And finally, I’d be grateful to get your support if you like what we’ve built. I could share it in DM or you could check exactly in my profile.

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.

Behind the scene : fundraising pre-seed of an AI startup

A bit of feedback from our journey at our AI startup. We started prototyping stuff around agentic AI last winter with very cool underlying tech research based on some academic papers (I can send you links if you're interested in LLM orchestration). I'm a serial entrepreneur with 2x exits, nothing went fancy but enough to keep going into the next topic. This time, running an AI project has been a bit different and unique due to the huge interest around the topic. Here are a few insights. Jan \~ Mar: Research Nothing was serious, just a side project with a friend on weekends (the guy became our lead SWE). Market was promising and we had the convinction that our tech can be game changer in computer systems workflows. March \~ April: Market Waking Up Devin published their pre-seed $20m fundraising led by Founders Fund; they paved the market with legitimacy. I decided to launch some coffee meetings with a few angels in my network. Interest confirmed. Back to work on some more serious early prototyping; hard work started here. April \~ May: YC S24 (Fail) Pumped up by our prospective angels and the market waking up on the agentic topic, I applied to YC as a solo founder (was still looking for funds and co-founders). Eventually got rejected (no co-founder and not US-based). May \~ July: VC Dance (Momentum 1) Almost randomly at the same time we got rejected from YC, I got introduced to key members of the VC community by one of our prospective angels. Interest went crazy... tons of calls. Brace yourself here, we probably met 30\~40 funds (+ angels). Got strong interests from 4\~5 of them (3 to 5 meetings each), ultimately closed 1 and some interests which might convert later in the next stage. The legend of AI being hype is true. Majority of our calls went only by word of mouth, lots of inbounds, people even not having the deck would book us a call in the next 48h after saying hi. Also lots of "tourists," just looking because of AI but with no strong opinion on the subject to move further. The hearsay about 90% rejection is true. You'll have a lot of nos, ending some days exhausted and unmotivated. End July: Closing, the Hard Part The VC roadshow is kind of an art you need to master. You need to keep momentum high enough and looking over-subscribed. Good pre-seed VC deals are over-competitive, and good funds only focus on them; they will have opportunities to catch up on lost chances at the seed stage later. We succeeded (arduously) to close our 18\~24mo budget with 1 VC, a few angels, and some state-guaranteed debt. Cash in bank just on time for payday in August (don't under-estimate time of processing) Now: Launching and Prepping the Seed Round We're now in our first weeks of go-to-market with a lot of uncertainty but a very ambitious plan ahead. The good part of having met TONS of VCs during the pre-seed roadshow is that we met probably our future lead investors in these. What would look like a loss of time in the initial pre-seed VC meetings has been finally very prolific, helping us to refine our strategy, assessing more in-depth the market (investors have a lot of insights, they meet a lot of people... that's their full-time job). We now have clear milestones and are heading to raise our seed round by end of year/Q1 if stars stay aligned :) Don't give up, the show must go on.

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

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

We're building a tool to help you find grants. Would you use it?

Hi there! In Europe alone, we spend almost € 400 billion annually on subsidies to support businesses. We estimate there are around 18,000 different grants available to entrepreneurs. Via the EU of course, but also via cities, national governments and literally countless public bodies all offering different kinds of support. I've been working for the government for about 10 years now, and I've noticed how difficult it can be for smaller companies to identify the right subsidy opportunities. Because they don't know they exist (and thus don't know where to find them), or because the eligibility criteria are just overwhelming, for example. Together with my co-founder we're building a tool to make it easier to find the grants that best align with your goals (fingers crossed!). Basically we scan all subsidies in Europe, use AI to analyze the goals and criteria and match companies with those subsidies that work best for them. So my question for you guys: do you look for subsidies or grants at all? And would such a tool be helpful for you? And if so, what kind of features would be most helpful for you? Really appreciate any thoughts from your side! Also if you think the idea is just rubbish :) Jesse

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!

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

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

Selling equity - what’s next?

Hey all, Seeking some guidance / advice as I plan my exit from a marketing agency I helped grow to $5M Long story short, I was hired part time to build their digital marketing department that sat at around 40k annual agency revenue. Since then I’ve become a minority equity partner, and at one point the agency was above $5M in gross agency revenue. The digital department that I run had up to 13 FTE employees at one point And digital revenue accounted for 60% of all agency revenue for the last 3-4 years. So, why am I leaving? Things are groovy, right? Well, we have dropped from $5M to now $3M this year and we’ll be lucky to hit that. As a minority equity party it’s been hard to watch leadership continue to disregard our agency as a digital agency. They don’t want to niche down, and they don’t want to identify as a digital agency, but instead by a full service “strategic agency”. Clients have felt our lack of expertise and direction, so they leave for someone who is an expert in xyz platform or industry. I no longer see their vision, and so I’m planning a sale of my equity and looking for new venture opportunities. While I am perfectly capable of running Google ads and Facebook ads campaigns, and as an accomplished SEO I know how to rank sites, and still find it fun. But I’m not interested in the labor arbitrage model of agency work anymore. I’d rather build a portfolio of in-house properties or digital assets where I have more control. Lately my obsession has been using AI and zapier to automate business processes, documentation, project management etc. Agency life has also exposed me to a lot of industries and business models, which I am always fascinated by. Eventually I will launch my own business, but I’m supporting my partner while they finish school. So I’m a single income household.. Therefore a W2 would be ideal but I’m open to contract work. So my question is- what positions or roles would I fill? I’ve done my share of research but this community has always given me new things to consider. Any feedback or questions are welcomed.

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

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

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

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

From "There's an App for that" to "There's YOUR App for that" - AI workflows will transform generic apps into deeply personalized experiences

I will not promote. For the past decade mobile apps were a core element of daily life for entertainment, productivity and connectivity. However, as the ecosystem saturated the general desire to download "just one more app" became apprehensive. There were clear monopolistic winners in different categories, such as Instagram and TikTok, which completely captured the majority of people's screentime. The golden age of creating indie apps and becoming a millionaire from them was dead. Conceptual models of these popular apps became ingrained in the general consciousness, and downloading new apps where re-learning new UI layouts was required, became a major friction point. There is high reluctance to download a new app rather than just utilizing the tooling of the growing market share of the existing winners. Content marketing and white labeled apps saw a resurgence of new app downloads, as users with parasympathetic relationships with influencers could be more easily persuaded to download them. However, this has led to a series of genericized tooling that lacks the soul of the early indie developer apps from the 2010s (Flappy bird comes to mind). A seemingly grim spot to be in, until everything changed on November 30th 2022. Sam Altman, Ilya Sutskever and team announced chatGPT, a Large Language Model that was the first publicly available generative AI tool. The first non-deterministic tool that could reason probablisitically in a similar (if flawed) way, to the human mind. At first, it was a clear paradigm shift in the world of computing, this was obvious from the fact that it climbed to 1 Million users within the first 5 days of its launch. However, despite the insane hype around the AI, its utility was constrained to chatbot interfaces for another year or more. As the models reasoning abilities got better and better, engineers began to look for other ways of utilizing this new paradigm shift, beyond chatbots. It became clear that, despite the powerful abilities to generate responses to prompts, the LLMs suffered from false hallucinations with extreme confidence, significantly impacting the reliability of their use, in search, coding and general utility. Retrieval Augmented Generation (RAG) was coined to provide a solution to this. Now, the LLM would apply a traditional search for data, via a database, a browser or other source of truth, and then feed that information into the prompt as it generates, allowing for more accurate results. Furthermore, it became clear that you could enhance an LLM by providing them metadata to interact with tools such as APIs for other services, allowing LLMs to perform actions typically reserved for humans, like fetching data, manipulating it and acting as an independent Agent. This prompted engineers to start treating LLMs, not as a database and a search engine, but rather a reasoning system, that could be part of a larger system of inputs and feedback to handle workflows independently. These "AI Agents" are poised to become the core technology in the next few years for hyper-personalizing and automating processes for specific users. Rather than having a generic B2B SaaS product that is somewhat useful for a team, one could standup a modular system of Agents that can handle the exactly specified workflow for that team. Frameworks such as LlangChain and LLamaIndex will help enable this for companies worldwide. The power is back in the hands of the people. However, it's not just big tech that is going to benefit from this revolution. AI Agentic workflows will allow for a resurgence in personalized applications that work like personal digital employee's. One could have a Personal Finance agent keeping track of their budgets, a Personal Trainer accountability coaching you making sure you meet your goals, or even a silly companion that roasts you when you're procrastinating. The options are endless ! At the core of this technology is the fact that these agents will be able to recall all of your previous data and actions, so they will get better at understanding you and your needs as a function of time. We are at the beginning of an exciting period in history, and I'm looking forward to this new period of deeply personalized experiences. What are your thoughts ? Let me know in the comments !

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!

Online Reputation AI - Startup got stuck

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

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.

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.

How to get funding for startup ? I will not promote

I will not promote. Software startup based out of Minnesota us. I've built and launched a product that is gaining traction, solving a problem that has frustrated software developers and product teams for years. The problem: Software development is slow, expensive, and full of inefficiencies. Developers spend hours on repetitive coding tasks, project managers struggle with bottlenecks, and businesses waste time translating product requirements into actual code. The solution: My product automates a large portion of software development. It acts as an AI-powered assistant for developers, taking high-level requirements and turning them into functional code while integrating with existing codebases. It can read, understand, and modify software projects in a structured way—cutting development time drastically. The potential: Businesses are always looking for ways to cut costs and speed up development. With the rise of AI, companies are increasingly adopting automation, and this tool fits perfectly into that wave. Imagine a world where software teams are 10x more efficient because AI handles the grunt work, and developers focus on the bigger picture. It’s not about replacing developers—it’s about supercharging them. The current status: The product is live and in use. The user base is growing, and I’ve proven demand. Now, I need to figure out the best funding model to scale—whether that’s bootstrapping, VC, grants, or some hybrid approach. If you have experience in startup funding or have scaled a tech product, I'd love to hear your insights. DM me if you're open to discussing strategies!

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 fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

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

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

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

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. &#x200B; 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/

Hot Take: Not all your startups need AI forced into them

I'm a final year Computer Engineering student, hence applying for jobs all around. There's this particular trend I've noticed with startups that are coming up these days. That is, even for the absolute basic stuff they'll use 'AI', and they'll think they built something 'revolutionary'. No. You're breaking your product in ways you don't realise. An example, that even some well established companies are guilty of: AI Chatbots You absolutely don't need them and it's an entire gimmick. If you really wanna implement a chatbot, connect the user to an actual person on your end, which I think is not possible if you're at a 'startup' stage. You'll need employees who can handle user queries in real time. If the user really is stuck let them use the 'Contact Us' page. A really close relative of mine is very vocal about the frustration he faces whenever he tries to use the AI Chatbot on any well known e-com website. The only case for AI Chatbot that makes sense is when it's directing the customer to an actual customer support rep if none of the AI's solutions is working for the customer. Even then, implementing a search page for FAQ is extremely easy and user friendly. Another example: AI Interviewer I recently interviewed for a startup, and their whole interviewing process was AI'zed?!?! No real person at the other end, I was answering to their questions which were in video format. They even had a 'mascot' / 'AI interviewer' avatar designed by an AI (AI-ception???). This mascot just text-to-speech'ed all the questions for me to rewind and hear what I missed again. And I had to record video and audio to answer these questions on their platform itself. The entire interview process just could've been a questionnaire, or if you're really concerned on the integrity of the interviewee, just take a few minutes out of your oh-so-busy schedule as a startup owner. Atleast for hiring employees who would make the most impact on your product going ahead. I say the most impact, because (atleast as a developer) the work done by these employees would define how robust your product is, and/or how easily other features can be integrated into the codebase. Trust me, refactoring code later on would only cost you time and money. These resources would rather be more useful in other departments of your startup. The only use case for an AI Interviewer I see is for preparing for an actual interview, provided that feedback is given to the user at the earliest, which you don't need to worry about as a startup owner. So yeah, you're probably better off without integrating AI in your product. Thank you for reading. TLDR; The title; I know AI is the new thing and gets everyone drooling and all, but for the love of God, just focus on what your startup does best and put real people behind it; Integrating AI without human intervention is as good as a broken product; Do your hiring yourself, or through real people, emphasizing on the fact that the people you hire at an early stage will define your growth ahead;

Looking for a tech cofounder. Revoltionary (yes really!) gig economy app. I will not promote.

Hey everyone! I’m building a new gig-work app that cuts out the hassles of interviews, applications, and sky-high fees. We’re aiming to make it easy for businesses to hire qualified freelancers for short shifts or one-off tasks—and for freelancers to set their own rates and get paid quickly. Why This App? Time-Saving Model: Instead of posting jobs and conducting multiple interviews, employers can instantly book from a list of KYC-verified freelancers who showcase their skills via 30-second video bios. Cost Leadership: We plan to charge only 5%, far below the 15–50% common in other gig platforms. This keeps more money in the pockets of both freelancers and businesses. Proven Demand: A beta test in 2018 drew nearly 600 active users, validating that there’s appetite for a simpler, fairer way to fill short shifts. About Me 20+ years’ experience in payroll, workforce management, and operations for Fortune 500 companies. Led cross-functional teams, implemented large-scale solutions, and believe in building with a user-first mindset. Offering meaningful equity—I want a true partner, not a hired gun. Who I’m Looking For Full-Stack Developer (comfortable with Node.js, React, Python, or similar and ML/Ai) who can manage everything from front-end to database integration (ideally Postgres/MySQL) and build a same day payments system. Passion for creating solutions that genuinely help gig workers and small businesses. Excitement to collaborate on the product roadmap, from the booking interface to same-day payment features. The Opportunity Major Market: The gig economy is huge and still growing. If we nail speed, cost-effectiveness, and ease of use, we can capture a significant share of it. Remote-Friendly: We can work together from anywhere, though I’m planning to relaunch in London where the initial beta gained momentum. If this sounds like your kind of challenge, drop a comment or DM me. Let’s chat about how we can merge our strengths—my operations background and your technical expertise—to build a platform that truly transforms the gig-work experience. Thanks for reading, and I look forward to creating something impactful together!

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

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

Anyone wants to join? Looking for non technical partner

To keep things short, I'm a fullstack dev with 13+ years of exp in few startups (the most successful one is $200m+ valuation). Then launched my own gamedev business which operates well in codev and content production. Now I want to switch back into startups and use 140% of my time and expertise to bring a briliant product live after maybe few pivots. I already have one concept of AI daily newsletter with AI narrator imitating podcasts and/or tv live news but tailored for each user. Sound dumb? - Would love to hear and jump on your ideas baked by usp and market research then. Looking for someone with marketing/UA/fundraising expertise. And remember: It is not success that defines, but dedication.

Hot take: AI will replace non-technical founders before technical founders [I will not promote]

I think the prevailing theory is AI is going to empower non-technical people to create complex systems just by writing a prompt or prompts. I think a variant of that is getting close which are agentic workflows where something triggers an agent and it does things autonomously. These sort of systems are starting to pop up everywhere (zapier, n8n, others...) however we're a ways off from these being able to respond in near real time. Long story short you'll still need to have code to run and someone to write that code (at least for a few more years) I've been using Deepresearch by OpenAI since Monday. I'm a technical founder without a formal business background. I've had it do product market fit analysis, sam/tam estimates, go to market strategies and it's producing fantastic reports. I could see it handling pretty much 90% of the non-technical business work that doesn't involve action in the physical world. It produced the content of a very well thought out pitch deck for one of my businesses. It's identifying potential customers. It's pretty damn crazy. Like right now I have it building a financial pro-forma for my data room. In fact it finished before I could write this post!

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!

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

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!

Raising sf venture in the south

So I currenlty run a tech startup in Chattanooga TN (between nashville and atlanta) and this city is very few and far between in tech or startup funding. I am planning on moving to SF someday but my girlfriend is still in school here for the next year and we can't quite afford to move to the bay area yet. My startup needs funding and there is little to no vc's in the area and if you can find someone interested in a deal then they want 30% or more of your company. How hard would it be to raise a 350k pre-seed (with 5-10 customers at 250/mo b2b ai powered smb call management) remotely?

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

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

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

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

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

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

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

How to get funding for startup ? I will not promote

I will not promote. Software startup based out of Minnesota us. I've built and launched a product that is gaining traction, solving a problem that has frustrated software developers and product teams for years. The problem: Software development is slow, expensive, and full of inefficiencies. Developers spend hours on repetitive coding tasks, project managers struggle with bottlenecks, and businesses waste time translating product requirements into actual code. The solution: My product automates a large portion of software development. It acts as an AI-powered assistant for developers, taking high-level requirements and turning them into functional code while integrating with existing codebases. It can read, understand, and modify software projects in a structured way—cutting development time drastically. The potential: Businesses are always looking for ways to cut costs and speed up development. With the rise of AI, companies are increasingly adopting automation, and this tool fits perfectly into that wave. Imagine a world where software teams are 10x more efficient because AI handles the grunt work, and developers focus on the bigger picture. It’s not about replacing developers—it’s about supercharging them. The current status: The product is live and in use. The user base is growing, and I’ve proven demand. Now, I need to figure out the best funding model to scale—whether that’s bootstrapping, VC, grants, or some hybrid approach. If you have experience in startup funding or have scaled a tech product, I'd love to hear your insights. DM me if you're open to discussing strategies!

AI for sales & marketing...what' the latest? (I will not promote)

I'm part of a B2B SaaS startup and we are about to start pushing sales & marketing. I have been there before 2-3 years ago, and most of what i remember is a "data nightmare". Finding contacts, pushing them from one tool to the other, tracking follow ups, trying to create an effective funnel. I get the chance to do it again, and this time i want to automate everything i can. So what's the latest on AI for sales & marketing? How do you guys autome things? How can we do things with AI that would have been 3 interns three years ago? 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

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?

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

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

What Does “Building a Community” Actually Mean for a Startup?

I’ve talked to a lot of founders, and almost everyone gives the same advice: “Build your product and do sales at the same time. Also, build a community alongside it.” I get the first part. Shipping and selling together makes sense. But the “community building” part? That’s where things get blurry for me. Does community building mean posting regular updates on Twitter or LinkedIn? Does it mean making Instagram reels about the product? Or is it more about actually talking to potential customers one-on-one? When people say “build a community,” do they mean creating a place where users can interact with each other or just a way to keep them engaged with the product? The reason I’m asking is that I see different approaches everywhere. Some founders document their startup journey on social media, and that seems to attract an audience. Others focus on getting early users into a private group (Discord, Slack, or WhatsApp) and nurturing relationships there. And then there are those who take a totally different approach—like building in public, sharing code, or offering free tools to bring people in. For my startup, I’m trying to figure out what community building should look like in 2025. The startup landscape has changed drastically in the past year, especially with AI and automation becoming more mainstream. Founders no longer have time to manually interact with every user. So what’s the new way of doing this? What’s working for early-stage startups today? I’d love to hear thoughts from fellow founders. What does “community” actually mean in today’s world, and what’s the best way to build one?

Month 2 of building my startup after being laid off - $200 in revenue and 4 (actual) paying customers

In September 2024, I got laid off from my Silicon Valley job. It fucking sucked. I took a day to be sad, then got to work - I'm not one to wallow, I prefer action. Updated my resume, hit up my network, started interviewing. During this time, I had a realization - I'm tired of depending on a single income stream. I needed to diversify. Then it hit me: I literally work with RAG (retrieval augmented generation) in AI. Why not use this knowledge to help small businesses reduce their customer service load and boost sales? One month later, Answer HQ 0.5 (the MVP) was in the hands of our first users (shoutout to these alpha testers - their feedback shaped everything). By month 2, Answer HQ 1.0 launched with four paying customers, and growing. You're probably thinking - great, another chatbot. Yes, Answer HQ is a chatbot at its core. But here's the difference: it actually works. Our paying customers are seeing real results in reducing support load, plus it has something unique - it actively drives sales by turning customer questions into conversions. How? The AI doesn't just answer questions, it naturally recommends relevant products and content (blogs, social media, etc). Since I'm targeting small business owners (who usually aren't tech wizards) and early startups, Answer HQ had to be dead simple to set up. Here's my onboarding process - just 4 steps. I've checked out competitors like Intercom and Crisp, and I can say this: if my non-tech fiancée can set up an assistant on her blog in minutes, anyone can. Key learnings so far: Building in public is powerful. I shared my journey on Threads and X, and the support for a solo founder has been amazing. AI dev tools (Cursor, Claude Sonnet 3.5) have made MVP development incredibly accessible. You can get a working prototype frontend ready in days. I don't see how traditional no-code tools can survive in this age. But.. for a production-ready product? You still need dev skills and background. Example: I use Redis for super-fast loading of configs and themes. An AI won't suggest this optimization unless you know to ask for it. Another example: Cursor + Sonnet 3.5 struggles with code bases with many files and dependencies. It will change things you don't want it to change. Unless you can read code + understand it + know what needs to be changed and not changed, you'll easily run into upper limits of what prompting alone can do. I never mention "artificial intelligence" "AI" "machine learning" or any of these buzzwords once in my copy in my landing page, docs, product, etc. There is no point. Your customers do not care that something has AI in it. AI is not the product. Solving their pain points and problems is the product. AI is simply a tool of many tools like databases, APIs, caching, system design, etc. Early on, I personally onboarded every user through video calls. Time-consuming? Yes. But it helped me deeply understand their pain points and needs. I wasn't selling tech - I was showing them solutions to their problems. Tech stack: NextJS/React/Tailwind/shadcn frontend, Python FastAPI backend. Using Supabase Postgres, Upstash Redis, and Pinecone for different data needs. Hosted on Vercel and Render.com. Customer growth: Started with one alpha tester who saw such great results (especially in driving e-commerce sales) that he insisted on paying for a full year to keep me motivated. This led to two monthly customers, then a fourth annual customer after I raised prices. My advisor actually pushed me to raise prices again, saying I was undercharging for the value provided. I have settled on my final pricing now. I am learning so much. Traditionally, I have a software development and product management background. I am weak in sales and marketing. Building that app, designing the architecture, talking to customers, etc, these are all my strong suits. I enjoy doing it too. But now I need to improve on my ability to market the startup and really start learning things like SEO, content marketing, cold outreach, etc. I enjoying learning new skills. Happy to answer any questions about the journey so far!

My app has gone viral and I grew from 1k users (take 5months) to 100k user in 5 days

I've always dreamt of building an online side business where I can build once and sell to millions. I love that business model but have never dreamt that I can achieve that, given that I am not a programmer in my career. I have been following side hustle school and some other business podcast for the past years as a drive and motivation to create my own business.  Over the years, I've delve a little on to web development using WordPress and in the hope of earning some money from that. I learnt in the hard way but is a good learning story and journey. I realised that what you put all your efforts building and excited for doesn't mean anything for anyone else and also learnt the importance of UI UX.  Fast forward to 5 months ago (July 2024), I've came across several low code app builder. With the help of the low code tools in combination with chatgpt, I've finally launched my first mobile app - Rolly: AI Money Tracker. But the business challenges doesn't end here, but it's just the beginning. I got no experience and skills on marketing but I've got my drive and passion that keep propelling me forward. By keep listening on people sharing their journey, looking at different apps to brainstorm etc, I've managed to now grow my user base from 1k (in 5 months) to 100k (in 5days). What's happening was my app somehow got viral in Vietnam when people are getting interest funny comments from my AI during entering the transaction and it has been sharing around in the social media and even featured on the news. What a crazy journey as the inflow of users has been too sudden, my server has been down for a few times until I progressively upgrade it until it got stable these couple of days. As for my advice to people dreaming the to be entreprenuer - Don't overthinking about all the problems you will face before starting. You will encounter hundreds of problems along the way and you just need to solve them one by one. You will never start if you think about what's not working and there will never be an answer for everything - even I don't have an answer for everything now.

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!

Restarting My Agency / Compared To Full Time Corporate

I’m currently thinking about going back to consulting / agency work compared to my current tech job I have. Over a year ago I signed this tech client and they wanted more and more from me which ended up becoming a full time role. At the time, the challenge excited me as it was working on a very large project on a global scale, competing with some of the biggest brands in the world. I was making good money before working in my agency and consulting with lots of different brands on their paid media, websites and e-commerce. I have a healthy package where I’m at at the moment but want more. Working with different clients always created curiosity, no day was the same and that what I loved about it. So now I’m considering going to back to starting the business and working with clients again. My question is: What do businesses ACTUALLY want? Everyone wants great roas and an amazing site but what are core things people are looking for in a growth partner / agency? I’m thinking of relaunching with three pillars in mind: Digital (Paid Media, Lead Gen, Web Dev) AI implementation as a lot of businesses don’t know how to leverage AI completely for cost saving and efficiencies. Content (Video, SEO, Content Writing) for modern day ranking I’m currently rebuilding my pitch deck and thought I would ask the question here before I go back to my network and start opening up conversations again. Would love to hear people’s thoughts in addition to anyone that’s done the same?

Optimizing your business with AI

Everyone's talking about it...it can be a threatening or it can be an advantage, but either way, if you don't anticipate it, you're going to be left in the dust. I opened my sports management business nearly 2 years ago and things have been going really well. The clientele is growing, the revenue and projects are doubling every quarter, and headcount is tripling this year. That being said...as the owner and founder of the business, I'm looking for resources to learn more about streamlining operations and admin. I believe that understanding capabilities, the lynch pins, the applications, and the tools to unleash AI are going to be instrumental to how i grow the business to scale...does anyone have any knowledge or nudges about where I can dig into this? Traditional educational courses? Resources or AI integration businesses? Consultants? Thanks in advance for any and all your suggestions!

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

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

Asking Advice

15-year-old aspiring entrepreneur here. I had an idea for a business that I wanted your feedback on. I'm planning to start an information product growth agency with a unique twist. Essentially helping influencers use their preexisting content and knowledge of a particular subject to create an online course that will monetize the attention from their social media via that course. I would like to use AI to intelligently sort through their content as a basis for the course. The gaps will be filled in by the influencer. The influencer would only be responsible for promoting the course and recording missing content. Is this business viable? If you were an influencer would you use this service? Do you have any thoughts, ideas, or concerns? Let me know!

Aspiring AI Consultant seeking advice & connections in Healthcare to get started

I’m an aspiring entrepreneur with a background in software engineering with 3 years of experience consulting for a medical device OEM. I’ve recently decided to venture out and start my own AI consultancy/integration services business, with an initial focus on non-clinical use cases in healthcare (e.g., workflow automation, predictive analytics, etc.). So far, I’ve done my research and have identified a few good potential use-cases, but I’m currently stuck because: I don’t have any direct connections with people who work in a healthcare setting. I’m unsure about the best next steps to validate my ideas and move forward. I’m reaching out here to seek guidance on how to proceed. Specifically: Are there any healthcare professionals here who could share insights into day-to-day challenges and workflows in non-clinical settings? What are the biggest operational pain points you face that could potentially benefit from automation or AI solutions? (Forget about the AI part—just think about tools or capabilities that could make your life easier.) If you’ve been in a similar position starting a business, how did you connect with potential clients or validate your ideas? I’d also love to hear from anyone who has tried offering AI consultancy or similar services, especially in healthcare. This is a genuine attempt to learn and grow, and I’m open to any advice, feedback, or even collaborations. If you’re in healthcare or know someone who might be able to help, I’d be incredibly grateful if you could point me in the right direction.

How do you learn details / potential strategy about technically important new laws in the jurisdictions you operate in?

I am reading “The Entrepreneur’s Guide to Law and Strategy” and it’s really fantastic so far about giving a pretty great overview of these aspects of business. It was published by Wiley (a reputable textbook publisher) in 2018. In one chapter, the authors go into the EU’s “right to be forgotten” and it got me thinking about complying with laws like that. Unfortunately, the latest edition of the book is still nearly 7 years old and written pre-COVID, pre-genAI, pre-social network and privacy pushback, etc. I assume every time a new law comes out that can impact my business (say, a random privacy law in California) that businesses aren’t just telling their lawyers “use any amount of hours you need to in order to read the San Jose papers every day and then write me a one paragraph brief with an outline and potential changes needed to our business, also all the other papers across the world”. They’d spend a fortune. There has to be something I’m missing. Is there a law review for business that I should be following? I operate in the US only at this time. A more technical newspaper (I take WSJ, but it’s not technical enough for this sort of thing. It might give the “what”, but won’t give a small business owner “what to do with it”)? PS: I’m the type of person who read every word of my mortgage. I am aware the answer might be “don’t worry about it”. But I do worry about it, and am trying to fix that. For example, the insanely popular new lawsuits about website accessibility. I want to avoid things (essentially low hanging lawsuit fruit) like that before they happen to me.

What CRM system works best for commercial loan brokers?

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

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

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

Impact of AI on business valuation?

I see many businesses thinking and experimenting with how AI can help improve their business processes. I seem to find far fewer thinking about how AI could impact or even demolish their actual product. I’ve been thinking about this a lot as (thankfully?) I sold my 15 year old business last year. We have teams of specialists that create digital content in narrow but very high value topic areas. Our value has been the ability of our team of experts to distill and explain the impact of the topic. Now, just a few months later, we’ve shown how three specialist AI systems can basically do the same for near zero cost. Our business and model is highly threatened. Anyone else worried about AI on their product, and thereby the value of their business, and perhaps even looking at exiting while the value is high? And yes, I do expect AI will also create new opportunities to create value. Already thinking of ideas…!

Is Digital Marketing Dying?

Is Digital Marketing Dying? &#x200B; I have read articles and seen youtube videos saying, DIGITAL MARKETING IS DYING, AI will replace everything. Facebook is dying! SEO will be Automated You have AI Tools in marketing replacing many jobs roles such as, Copy. AI, Quillbot, Paraphraser, Design. AI, MadgicX, Etc &#x200B; Having been in Digital Marketing for two years, all my seniors are having 2nd thoughts about it. I don,t want to change my domain. I believe marketing will always be there, but the methods, technologies, and tools will change. &#x200B; What do you people have to say?

80+ Social Media Updates Related to Business Marketing That Occurred in last 5 months

Tiktok expanded its caption limits from 100 to 500 Characters. Reddit Updates Search tools, Now you can search User Comments. “Comment search is here”. Pinterest Announces New Partnership with WooCommerce to Expand Product Listings. Google’s launched ‘multisearch’ feature that lets you search using text and image at the same time. Etsy sellers went on strike after platform increases transaction fees. Reddit launched $1 million fund to support various projects going on platform. Instagram is updating its ranking algorithm to put more focus on Original Content LinkedIn Added New tools In creator mode: improved content analytics and Updates profile video Options. Tiktok launched its own gif library “Effect House”. Instagram Updates Reels editing tools adding reordering clips feature. Google Search got a new label to direct people to original news sources YouTube launches new Profile Rings for Stories and Live. Snapchat launched YouTube Link stickers to make video sharing easier! Messenger adds new shortcuts, including a slack like @everyone feature. Pinterest Expands it’s Creator funds program to help more Underrepresented creators. Reddit brings back r/place after 5 years. Google Adds New Seller Performance Badges, New Pricing Insights for eCommerce Brands. Meta and Google agrees to New Data Transfer agreement to keep Instagram and Facebook running in EU. Twitter tests New Interactive Ad types to boost its promotional Appeal. Instagram removed In-stream Ads from its Advertising Options. Tiktok launched new program “CAP” to help creative agencies reach its audience. Twitch shuts down its desktop app. Meta launched the ability to add “share to Reels” feature to third Party Apps. TikTok Adds New ‘Background Player’ Option for Live-Streams. Twitter rolls out ALT badge and improved image description. Fast, A Checkout Startup with $15 billion valuation shuts down after spending all the funds raised in 2021. Wordpress announced new pricing with more traffic and storage limits after receiving backlash from the community. Sales force upgrades marketing field services and sales tools with AI. Dropbox shop launches in open beta to allow creators to sell digital content. Tiktok is the most downloaded app in Quarter 1 of 2022. WhatsApp announced launch of ‘Communities’ - more structured group chats with admin controls. Tiktok expands testing a private dislike button for comments. Twitter acquired “Openback” A notification app to improve timeline and relevance of push notifications YouTube and Tiktok added New options for Automated Captions, Improving Accessibility. A new social media App “Be Real” is trending across the internet grabbing Gen-Zs attention to try the app. WhatsApp got permission to expand payment services to its Indian user base of 100 Million. YouTube Shorts now allows creators to splice in long-form videos. You can use long form video audios and clips for YT shorts. New Snapchat feature ‘Dynamic Stories’ uses a publisher’s RSS feed to automatically create Stories posts. Zoom launches AI-powered features aimed at sales teams. Tiktok started testing who viewed your profile feature. Ogilvy Announced they will no longer work with who edit their bodies and faces for ads. If you don’t know “Oglivy” is the most successful advertising agency of the decade. YouTube Launches New ‘Search Insights’ for all creators. Snapchat Added 13 million new users in Q1 2022 more than both Twitter and Facebook. Google is Introduced new options to reject tracking cookies in Europe after receiving fines from violating EU data laws. Sony & Microsoft are planning to integrate Ads into their gaming platforms Xbox and PlayStation. YouTube Adds new Shorts Shelf to Trending Tab to show Top Shorts in an alternative section. Instagram started testing a reels template feature which enables creators to copy formats from other reels. Google Tests “What People Are Saying” Search Results. Twitter Launches New Test of Promotions for Third Party Tools Within the App. Instagram is changing how hashtags work by experimenting removing Recents tab from hashtags section. Google Adds New Publisher Verification Badges to Extension Listings in the Google Web Store Amazon AWS launches $30M accelerator program aimed at minority founders. Meta launched more fundraising options for Instagram Reels in 30 countries. Brave Search and DuckDuckGo will no longer support Google AMP due to privacy issues. Instagram is working on a pinned post feature and will officially launch in next few months. Meta: You can now add Music to your Facebook comments Twitter tests new closed caption button to switch on captions in Video Clip Elon Musk Bought Twitter $44 Billion and Company is set to go private. Google now lets you request the removal of personal contact information from search results YouTube reveals that Ads between YT Shorts are being tested with selective brands. LinkedInis rolling out a new website link feature. Google Reduces Visibility Of Business Edits With Color Changes To Profile Updates. Instagram expands testing of 90 second Reels. Microsoft Advertising now offers incentive features like cash-back and adding stock images from your website. Facebook & Pinterest are growing again despite all the hype around slow growth of both platform in last quarter. Google Added 9 new Ad policies to prevent misleading ads taking place. Tiktok Introduces Third-party cookies to its Pixel. (like Facebook Pixel) Twitter reportedly overcounted number of daily active users for last 3 years. Google launched Media CDN to compete on content delivery. YouTube expands Thank You Monetisation tool to all eligible creators. Twitch is looking to expand their cut from streamers earnings from 30 to 50% and also thinks of boosting Ads. Snapchat launches a $230 flying drone camera and new e-commerce integrations in Snap Summit 2022. YouTube Expands its ‘Pre-Publish Checks’ Tool to the Mobile App Google Search Console’s URL parameter tool is officially removed for a time period. Twitter creators can now get paid through Cryptocurrency on Twitter with Stripe. Jellysmack- One of the Influencer marketing agency acquires YouTube analytics tool Google & Microsoft Ads brought more revenue in last quarter- 22% Gains! WhatsApp is working on a paid subscription for multi-phone and tablet chatting. Instagram users now spend 20% of their time in the reels section. Google tests new Color for clicked search results by you. Now Clicked results are in Purple. Twitter: Elon plans to remove employees and focus more on influencers for twitter’s growth + new monetisation ideas were shared. YouTube revenue falls as more users spend time on shorts tab than consuming long form content. Drop 👋 to receive June Updates!

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 🙏

Looking to streamline and update family business

Hey r/smallbusiness, I’ve been working at my family’s business for six years now—joined right after college—and I’ve realized that we’re long overdue for an overhaul. I handle advertising sales, and while the business itself is solid, the way we operate is extremely outdated. Without revealing too much, we print about 180 publications, and businesses pay to have their ads featured. As a sales rep, my job includes: Renewing current advertisers Finding new customers and making sales Collecting artwork for ads Gathering billing info Laying out the ad grid with all advertisers The Problem: Everything is still done with pen and paper. We use carbon copy paper to record business details, billing info, and ad costs. One copy goes to the graphic designers, the other to billing. The billing team manually enters everything into QuickBooks, prints invoices, stuffs envelopes, and mails them out. We recently got new software that lets us send invoices via email and text through QuickBooks, which is a step in the right direction, but it’s just a small fix to a much bigger problem. What I Want to Change: Move everything onto an app or website—no more paper. Digitally layout the ad grid instead of doing it manually. (For graphics team) Collect billing info online instead of writing it down. (Obviously to get paid faster and reduce wasted labor) Automate renewal emails instead of calling every single customer. (Save time) Find more efficient ways to generate leads for new business. (Work smarter not harder) Honestly, the company still runs like my grandma set it up in the '90s, and it’s overwhelming trying to figure out where to start. If anyone has been through something similar or has advice on modernizing a business, I’d love to hear your thoughts! Happy to provide more details if needed. I’ve explored some CRMs and AI tools, but I’m sure someone here has better insights or more experience with this than I do. There are other parts of the business that need improvement, but I believe this would be a big step in the right direction. Thanks in advance!

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!

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!

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!

Are AI agents for small businesses worth the hype?

I'm advising/investing in a business n the sustainable energy space and the leadership is considering investing some of their revenue and raised capital on building AI agents/workflows to support their long term growth and I've been seeing all of these AI agencies popping up and all the talk about how they are transformative for business's bottom lines but I'm curious to hear from traditional small businesses that have implemented AI agents/workflows What has your experience with them been? What is the cost to benefit ratio? is how much did you invest and did it have the desired impact on your business? How have your employees responded to your agents/workflow? How do you handle updates? Are the systems stuck in the time when they were implemented or do you pay a retainer to the agency that implemented the system for you? I've been involved with AI for a few years but I don't know if these AI agents/workflows are robust and capable enough to offer significant value to small businesses

The case for micro PE [x-post from r/micro_pe]

Any SMB owners considering a sale? What have your challenges been so far? \-- The high-flying venture capital party is quieting down. The pullback in the public tech valuations and high-profile failures have made venture capitalists more cautious, doing fewer deals, no doubt stemming from antsy LPs. But at the same time, real tech has been built that improves business efficiency. AI to cut costs, target customers, improve products. SaaS products to automate everything from billing to marketing. New platforms that open up new modes of customer acquisition. Some of the hyped venture-backed companies from the past decade, while not quite achieving world domination, demonstrated models that provided real value to customers. The on-demand universe - rides, rooms, meals, home services, pets, leisure, showed that customers value convenience and experience. On another front, there's a silver tsunami on the horizon as aging business owners start to cash out. Nearly 60% of private companies are run by the 55+ crowd. Trillions in assets will change hands in the next 15 years as they retire. The tech layoffs have flooded the labor market with brainpower. No shortage of sharp operators looking for their next act. Put it together and you have the ingredients for a new investment approach: micro private equity. Modest valuations, reasonable return expectations, solid companies with positive cash flow or a clear path to profitability. Maybe with debt financing or an acquisition of an existing business at the outset. More targeted, grounded bets are emerging as an alternative to the high-risk venture model. r/micro_pe

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 🙏

40% Of SMBs Still Can't Pay Their Rent, Extending High Delinquency From September Into October

https://www.alignable.com/forum/q4s-off-to-a-rough-start-40-of-smbs-still-cant-pay-their-rent October 31, 2023: While the federal government reported a surge in economic growth for the U.S. last week, that news doesn't hold true for many small business owners. In fact, in October polling by Alignable, only 12% said their companies are experiencing significant growth this month. Beyond that, Alignable’s October Rent Report, released today, shows that a whopping 40% of SMBs couldn't even pay their October rent in full and on time. This marks the second consecutive month of a 40% rent delinquency rate -- extending 2023's record high from September through October. These findings are based on responses from 4,246 randomly selected small business owners surveyed from 10/1/23 to 10/30/23, as well as input from 44,000+ other respondents over the past year. As the chart below shows, October's SMB rent delinquency rate is 10 percentage points higher than it was in January, reflecting cumulative economic struggles: increased rents, high interest rates, still-stifling inflation, rising labor costs, and revenues that have declined since this time last year. Rent delinquency rates among small businesses during 2023 based on Alignable surveys So, Why's Rent Delinquency At 40% For A 2nd Month? Here’s the current list of problems contributing to two months' worth of the highest delinquency rate 2023 has seen so far: Consumer Spending Declines On Main Street: Quarterly, we ask about customer spending habits at retailers. This month, 45% of independent Mom and Pop Shops said spending has been down over the last 30 days. Some said it was due to more people spending money online with big retailers like Amazon. This figure is quite high, especially considering that back in July, only 24% reported a drop in consumer spending -- 21 percentage points less severe than it is now. Revenue Troubles: 42% are making half or less of the income they generated monthly prior to COVID. For businesses that are less than three years old, this situation is even worse: 53% of this group reports making half or less of what they generated this time last year. High Interest Rates: Over half of all SMB owners polled said the past 19 months of high interest rates have hurt their margins, reduced revenues, and put their expansion plans on hold, as they don't want to apply for loans. Increased Rent Prices: 50% say they’re being charged more for rent now than they were six months ago, with 15% saying rent has increased by 20% or more. At present, only 37% of pre-COVID businesses have recovered financially from the pandemic era, leaving 63% still striving to make up for time they lost due to COVID, inflationary pressures, and high interest rates. There's a slight silver lining here, though, as the 37% figure is three percentage points higher than it was in September. But, with that said, a recovery rate of 37% after more than three and a half years is still very low and speaks volumes about the ongoing list of troubles small business owners face looking into the rest of 2023. Tech, Manufacturing, Gyms, Beauty & Retail Struggle Examining the rent delinquency landscape in terms of sectors, there's quite a negative shift occurring among some industries in October. Let's look at the charts below to see what's really happening. Sectors most affected by rent delinquency include tech and retail Details on sectors affected by rent delinquency in October This is alarming for a few reasons: The countless technology layoffs at larger companies over the past year appear to be affecting the small companies now, too, who are often dependent on the larger ones as clients. Right now, 54% of science/technology small companies couldn't pay their October rent, up 10 percentage points from September and 16 percentage points since August. There are also some comments in the surveys of technology roles being reduced or replaced by ChatGPT and other AI, which can write software programs. Gyms have been struggling now for a while and now 50% of them can't afford the rent, up 8 percentage points from September. The biggest shift between October and September occurred among manufacturers, partially due to ongoing fluctuation in the price of gas and other inflationary issues. For quite some time, manufacturers were improving a lot in terms of their rent delinquency rates, but in October, they jumped 25 percentage points, doubling their rate, which is now 50%. This is also a record high for manufacturers in 2023. We hope this is just a blip, but we'll see in November. Also due, in part, to fluctuating gas prices and costs of vehicles, 45% of transportation companies couldn't pay October rent in full and on time. That's up 6 percentage points from last month. Sadly, 47% of salon owners couldn't cover October rent, after showing a lot of stability over the past few months. But that stability ended this month, as salons' rent delinquency rates jumped nine percentage points. Though rates have dropped three percentage points in October, a high percentage of retailers are still having trouble paying the rent. Last month, it was 47%. This month, it's better, but is still over 40%, landing at 44%. This is worrisome, especially since Q4 is a "make it or break it" time for many Main Street merchants. Looking more closely at the industries, there was some good news, in that a few others experienced lower delinquency rates in October, including restaurants, which dipped to 40% from 44% in September. Travel/lodging dropped seven percentage points to 38% (from 45% last month), as did education, which is also at 38%, down from 43%. When looking at rent delinquency from the vantage point of the states that are most affected, many surges can be seen between October and September, while a few states saw some dramatic, encouraging declines, too. Rent Troubles Increase For IL, VA, TX, MA, FL, & CO Looking at the states' charts, you can see how tumultuous the rent story has become this fall. Let's first talk about those with significant jumps in their delinquency rates. Here's the rundown: Illinois leads the list once again. After having a better month in September, its delinquency rate has soared, once more, landing at 54% for October (up from 46% last month). In fact, the 54% figure is the highest rate IL-based SMBs have seen in 2023. Virginia was in great shape last month, with a delinquency rate of just 19%. But Virginia-based small business owners have had a very rough month, at least in terms of rent. Now, 50% of them who took our poll say they couldn't cover rent (an increase of 31 percentage points). Texas is third on the list, with an 11-percentage-point lift from 38% in September to 49% in October. MA is next up at 48%, which marks the largest jump on the chart -- 32 percentage points from a low of just 16% in September. Small businesses in Florida have also experienced two challenging months in terms of rent delinquency. Right now, 45% of SMBs there couldn't afford to pay, up nine percentage points from September and 15 percentage points from August. Colorado's businesses regressed in October, hitting a new record high of 40%. That rent delinquency rate jumped 13 percentage points from September to October. While we just covered states with some very high delinquency rates, there were also several more positive swings that have occurred in October. Though encouraging, we'll have to see how long those delinquency rates continue. Here are the most remarkable: New York -- After reaching a record rate of 55% last month, New York's small business owners now report a more stable number: just 29%. That's down 26 percentage points. New Jersey -- New York's neighbor has an even more impressive story in October: only 20% of New Jersey's SMBs couldn't pay rent this month, a record low over at least the past 14 months, down 34 percentage points from a record high of 54%. Michigan -- Similarly, Michigan's small business owners boast a rate of just 20%, down from 45% in September.

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

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

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.

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.

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

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

How do I get a job in this job market? How do I stand out from the crowd?

About me - I am an international grad student graduating in Spring 2025. I have been applying for jobs and internships since September 2024 and so far I haven't even been able to land a single interview. I am not an absolute beginner in this field. Before coming to grad school I worked as an AI Software Engineer in a startup for more than a year. I have 2 publications one in the WACV workshop and another in ACM TALLIP. I have experience in computer vision and natural language processing, focusing on multimodal learning and real-world AI applications. My academic projects include building vision-language models, segmentation algorithms for medical imaging, and developing datasets with human attention annotations. I’ve also worked on challenging industry projects like automating AI pipelines and deploying real-time classifiers. How can I improve my chances in this competitive job market? Are there specific strategies for international students navigating U.S. tech job applications? How can I stand out, especially when competing with candidates from top schools and with more experience?

Strategies for training AI players on asymmetric games?

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

Scratch Machine Learning Algorithms Implementations

Hi there, other Redditors! Like many of you, when I first started working in the AI field, I wanted to build some basic Machine Learning models from scratch in order to better understand how each algorithm works, improve my programming and math skills, or simply produce an eye-catching, difficult project to put in the résumé. After spending some time searching for resources that could help me guide my studies, I discovered that the majority of scratch implementations that are currently available are either i) outdated (having been implemented years ago using Python 2 or an earlier version of Python 3); ii) too difficult to understand (using a lot of difficult, unfriendly optimization techniques or with poorly written code); or iii) too simple (only covering binary classification). With that in mind, I made the decision to develop user-friendly, uncomplicated, organized, and simple implementations from scratch. Aside from all of that, I've always wanted to create an open-source project so that others, particularly novices and those with less than a year's experience (like me), can collaborate with others, contribute to public projects, and experience Git firsthand (some of these implementations were made by other contributors!). Here are some implementations that are available: Algorithms (Random Forest Classifier and Regressor, Decision Tree Classifier and Regressor, KMeans, KNN Classifier and Regressor, Gaussian Naive Bayes, Linear Regression, Logistic Regression, PCA, Perceptron, MLP Classifier and Regressor, SVM Classifier and Regressor); Regression and classification metrics; Distance metrics (such as Euclidean); Data split functions (such as KFold); Activation and loss functions; Scalers (such as MinMaxScaler) and encoders (such as One Hot Encoder); and a few things more! Project's link: https://github.com/rafaelgreca/scratchml Disclaimer: The goal of this library is to provide code that is simpler, easier to understand, and more approachable for artificial intelligence enthusiasts and beginners who want to contribute to an open-source repository or who want to learn more about how algorithms work. It is not meant to replace existing libraries that are better, more optimized, and have a wider variety of implemented algorithms (such as scikit-learn, PyTorch, Keras, and Tensorflow). If you want to use optimized implementations with accurate results, please use one of the previously mentioned libraries. P.S.: I accidentally deleted the other post, so I am posting again. :-)

ZeroToHeroML: Beginner-Friendly ML & AI Course (Free)

Hey r/learnmachinelearning! A friend of mine, who's been a software developer at Sony for 10 years, recently expressed interest in learning Machine Learning (ML) and Artificial Intelligence (AI). Leveraging my background in ML and neural computation (learned at UCSD) to create a beginner-friendly course guiding him through the basics and into more complex projects. Foundational Concepts: Predicting House Prices (Regression): Master regression techniques to forecast housing prices based on various factors. Iris Flower Species Prediction (Classification): Learn classification algorithms by predicting flower species using the famous Iris dataset. Overcoming Overfitting: Explore methods to prevent models from overfitting and enhance their generalizability. In Progress: Customer Segmentation (Unsupervised Learning): Delve into unsupervised learning to group customers based on purchase history or demographics (valuable for targeted marketing campaigns). Deep Learning for Image Recognition: Implement Convolutional Neural Networks (CNNs) to build models that recognize objects or scenes in images. Natural Language Processing Sentiment Analysis: Analyze the sentiment (positive, negative, or neutral) expressed in text data (e.g., reviews, social media posts) using NLP techniques. Introduction to Reinforcement Learning: Get acquainted with the fundamentals of reinforcement learning by creating an agent that learns to navigate a maze. Want to Learn or Contribute? I thought I'd share ZeroToHeroML here so others who want to learn ML/AI or know someone who does can benefit from this free resource! &#x200B; Fork the repo: https://github.com/DilrajS/ZeroToHeroML Share with others interested in ML/AI! Pull requests welcome (help the community grow!). All help is appriciated! Let's conquer ML/AI together!

Is it worth doing a Msc Conversion course

I’m a philosophy student currently, graduating with a 2.1 from a russell group uni. I’m looking for a career change into ML with the ultimate goal being research, whether it be comp neuro, biology, or using it in sports. I’ve found a Msc conversion course (1 year with no CS background required) where, as the name suggests, they teach you AI and ML techniques and how to implement them in a a real world context. It also includes a 3 month dissertation project with the possibility of working with industry. I was speaking to a friend today who suggested I learn on my own and save the money. I couldn’t help but think a qualification is useful alongside a portfolio, rather than just a portfolio (which he suggested). Given my current situation, a beginner programmer looking for a way in, what do you think I do?

NeRFs (2025)

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

Question from a non-technical founder

I'm having an automotive photography app built. I want to build a simple AI model that will resize, rotate and reposition automotive photos so they're all consistent. There's about 30 standard photos to build a model for. I've got hundreds of before and after photos to train it with. I'd class myself as a non-technical founder. I can build wordpress sites, basic HTML layouts. Been in digital marketing for 20 years. Is this a simple project that I might be able to learn some AI basics then just feed the model? Or will it require coding knowledge that'll be beyond me? I don't have time to deep dive into the code side. Thanks for any feedback.

Month of August in AI

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

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

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

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

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

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

MMML | Deploy HuggingFace training model rapidly based on MetaSpore

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

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?

AI Noob where to start?

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

Master AI Integration: How to Integrate AI in Your Application

A Comprehensive Guide with Every Detail Spelled Out for Flawless AI Implementation Full Article &#x200B; https://preview.redd.it/m5b79j55f14d1.png?width=1328&format=png&auto=webp&s=8cf04c80cd21be1710dd117a9e74b07d0e8cbe6a In the ideal world, we'd design our software systems with AI in mind from the very beginning. But in the real world, that's not always possible. Many businesses have large, complex systems that have been running for years, and making significant changes to them is risky and expensive. What this Article is About? ● This article aims to convince you that even when changing existing systems is not an option, you can still seamlessly integrate AI into your business processes. It explores real-world scenarios and shows how a company (though simulated) has successfully incorporated AI without overhauling their existing infrastructure. &#x200B; https://i.redd.it/fayl1gcbf14d1.gif Why Read This Article? ● By reading this article, you will learn the critical skill of integrating AI into your existing business ecosystem without making significant changes to your stable workflows. This skill is becoming increasingly important as more and more companies recognize the value of AI while also acknowledging the challenges of overhauling their existing systems. What is Our Business Use Case? ● The article uses a simulated supply chain management company as a business use case. This company has multiple departments, each exposing its own REST API, and to get an inquiry answered, the request has to go through various departments, their respective APIs, and database calls. The article introduces AI capabilities to enhance the company's operations without modifying the existing system architecture. Our Supply Chain Management Company AI Integration Design ● The article describes the various components of the simulated supply chain management company, including the "Data Processing System," "Company Data Handling System," "AI Integration System," "Mapping System," and "System Admin Dashboard." Let's Get Cooking! ● This section provides the code and explanations for implementing the AI integration system in the simulated supply chain management company. It covers the following: ○ Dashboard & AI Integration System ○ Company Data Handling System ○ Data Processing System ○ Mapping System Let's Setup ● This section shows the expected output when setting up the simulated supply chain management system with AI integration. Let's Run it ● This section demonstrates how to run the system and ask questions related to supply chain management, showcasing the AI integration in action. https://i.redd.it/3e68mb57f14d1.gif Closing Thoughts The supply chain management project we have explored in this article serves as a powerful example of how to seamlessly integrate cutting-edge AI capabilities into existing business systems without the need for significant overhauls or disruptions. By leveraging the flexibility and power of modern AI technologies, we were able to enhance the functionality of a simulated supply chain management system while preserving its core operations and workflows. Throughout the development process, we placed a strong emphasis on minimizing the impact on the existing system architecture. Rather than attempting to replace or modify the established components, we introduced an “AI Integration System” that acts as a bridge between the existing infrastructure and the AI-powered capabilities. This approach allowed us to maintain the integrity of the existing systems while simultaneously leveraging the benefits of AI. One of the key advantages of this integration strategy is the ability to leverage the wealth of data already available within the existing systems. By accessing and processing this data through the AI models, we were able to generate more informed and intelligent responses to user queries, providing valuable insights and recommendations tailored to the specific supply chain activities and scenarios. As we look towards the future, the importance of seamlessly integrating AI into existing business ecosystems will only continue to grow. With the rapid pace of technological advancements and the increasing demand for intelligent automation and decision support, organizations that embrace this approach will be better positioned to capitalize on the opportunities presented by AI while minimizing disruptions to their operations. It is my hope that through this simulated real-world example, you have gained a deeper understanding of the potential for AI integration and the various strategies and best practices that can be employed to achieve successful implementation. By embracing this approach, businesses can unlock the transformative power of AI while preserving the investments and institutional knowledge embedded in their existing systems.

What level of understanding of AI do I need?

Would really appreciate some advice if anyone can help out! So I'm a 20 year old student currently doing regular internships in accounting. I use a lot of my spare time to build small businesses that I find fun to build. I have very little coding experience besides basic courses besides a bit of experience with react when building an app with a more technically competent partner. I've concluded 3 things: 1.I want to add the power of AI to my arsenal, whether in work or in business 2.I don't think I'd have the time or experience to be an absolute expert in AI 3.There's a lot of small tech shy businesses in my area which I think could benefit from AI, particularly in accounting automation. I'd love to introduce it to them through some sort of agency. 4.Ideally I want to be competent enough in AI to be able to start an AI based business (probably in finance) with a more technical developer who I can at least communicate with. &#x200B; So my question is, what level do I need? Should I learn all the complex maths behind it and the first principles, or just learn how to harness the powerful tools already out there? If either, could you point me in the right direction for resources? Thanks!

Seeking Guidance to Transition from SRE to Quant Developer/HFT

Hey Reddit! Let me introduce myself: I’m a 2024 B.Tech (IT) graduate from a state-level college in India. Currently, I’m working as an SRE (Site Reliability Engineer) at one of the world’s largest custodian banks (not naming the company). I’ve been with the organization for about a year now, combining my internship and full-time role. During this time, I’ve developed a strong foundation in AI/ML and have primarily been working on projects to automate BAU (Business-As-Usual) activities using these technologies. Outside of work, I have a deep interest in trading and stock markets—something that runs in the family, as my father has been trading for over 40 years. My ultimate goal is to transition into the field of quantitative development or high-frequency trading (HFT) and work for top-tier firms like HRT, Optiver, or Tower Research. To make this dream a reality, I’ve started preparing in the following ways: Learning the basics of stock markets and financial instruments. Studying statistics and experimenting with different algorithms to analyze stocks (mainly on a fundamental level for now). Getting back to practicing DSA (Data Structures and Algorithms). I’ll admit I’m rusty here since I haven’t been consistent with it for a while. I’m aware that transitioning from SRE to Quant Developer/HFT is ambitious and might seem like a pipe dream, but it’s a challenge I’m willing to take on. I’d love to hear from people in the quant field or those who’ve made similar career transitions. What should I focus on? Any recommended resources, books, or courses? Are there any specific skill sets or certifications that could make me stand out? Any guidance, advice, or encouragement would mean a lot. Thank you!

I’m building 30 AI-powered businesses in 30 days with no experience. Here’s why.

Hey everyone! For the past 15 years, I worked in real estate development and sales, but I recently decided to make a career pivot into AI and automation.  I am starting from scratch with absolutely no experience in the space. But instead of just learning about AI, in March I'll be embarking on a challenge to build a business a day for 30 days using AI automation. Each one will be a fully functional product that could generate passive income. My goal? Learn by doing Document the entire process in public Share insights on what works (and what flops) I don't have any followers yet, but I just posted my first thread about my journey here:  https://x.com/RealEstateToAI/status/1886806315260953079 Would love to hear your thoughts: What resources did you find most valuable when starting with no experience in the space? What AI tools do you think are most valuable for automation?

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.

AI for Business: FREE Practical Course & Tools on YouTube

I worked for 15+ years in AI, created “AI for Business” to help any non technical professional learn and apply AI in their work. FREE course on YT + 6 tools (use-case gallery, ideation canvas, idea evaluation, POC template, team roles, & more) Course Link. Outline: https://preview.redd.it/nxh1952rqxad1.png?width=1744&format=png&auto=webp&s=4d31acdec5b0375734dcc49b1c0be81bc3e605e6

Which Roles in AI make you well rounded in the field

Background I've been a Software Engineer for 4 years working with Data. Also have a bachelors in Mathematics where I was one of the top students in my year. I wish to transition to AI and want to start a business in the field in the coming years, but before then I would like to get some professional experience. Which roles in AI would you say make the well rounded in the industry and gives you the best exposure to everything so that you can manoeuvre when the time is right?

Is this a good ML learning progression on Coursera?

AI for Everyone Python for Everybody (UMich) Applied Data Science with Python Specialization (UMich) Machine Learning (Andrew Ng) Data Engineering, Big Data, and ML on GCP Specialization Natural Language Processing Specialization TensorFlow Developer Professional Certificate Machine Learning Engineering for Production (MLOps) by DeepLearning.AI Deep Learning Specialization Mathematics for Machine Learning Specialization Cloud Computing Specialization Product Management for AI and ML Products Specialization I’m currently a highschool junior with currently minimal Python knowledge (currently in BC Calc so I do have somewhat of a math background). However, I do own and run a business and in my business space there’s a huge issue I want to solve that affects pretty much every business. But right now obviously I can’t because I don’t have the necessary knowledge. I do intend to turn this into a startup and pursue AI/ML in college. And I aim to at least start building MVP for startup around June-Sept this year. If startup is not successful then I would still want to be an AI engineer. But is this a good learning progression that I should be able to complete before I start college?

I’m AI/ML product manager. What I would have done differently on Day 1 if I knew what I know today

I’m a software engineer and product manager, and I’ve working with and studying machine learning models for several years. But nothing has taught me more than applying ML in real-world projects. Here are some of top product management lessons I learned from applying ML: Work backwards: In essence, creating ML products and features is no different than other products. Don’t jump into Jupyter notebooks and data analysis before you talk to the key stakeholders. Establish deployment goals (how ML will affect your operations), prediction goals (what exactly the model should predict), and evaluation metrics (metrics that matter and required level of accuracy) before gathering data and exploring models.  Bridge the tech/business gap in your organization: Business professionals don’t know enough about the intricacies of machine learning, and ML professionals don’t know about the practical needs of businesses. Educate your business team on the basics of ML and create joint teams of data scientists and business analysts to define and measure goals and progress of ML projects. ML projects are more likely to fail when business and data science teams work in silos. Adjust your priorities at different stages of the project: In the early stages of your ML project, aim for speed. Choose the solution that validates/rejects your hypotheses the fastest, whether it’s an API, a pre-trained model, or even a non-ML solution (always consider non-ML solutions). In the more advanced stages of the project, look for ways to optimize your solution (increase accuracy and speed, reduce costs, increase flexibility). There is a lot more to share, but these are some of the top experiences that would have made my life a lot easier if I had known them before diving into applied ML.  What is your experience?

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.

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

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

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.

AI for Business: FREE Practical Course & Tools on YouTube

I worked for 15+ years in AI, created “AI for Business” to help any non technical professional learn and apply AI in their work. FREE course on YT + 6 tools (use-case gallery, ideation canvas, idea evaluation, POC template, team roles, & more) Course Link. Outline: https://preview.redd.it/nxh1952rqxad1.png?width=1744&format=png&auto=webp&s=4d31acdec5b0375734dcc49b1c0be81bc3e605e6

I’m building 30 AI-powered businesses in 30 days with no experience. Here’s why.

Hey everyone! For the past 15 years, I worked in real estate development and sales, but I recently decided to make a career pivot into AI and automation.  I am starting from scratch with absolutely no experience in the space. But instead of just learning about AI, in March I'll be embarking on a challenge to build a business a day for 30 days using AI automation. Each one will be a fully functional product that could generate passive income. My goal? Learn by doing Document the entire process in public Share insights on what works (and what flops) I don't have any followers yet, but I just posted my first thread about my journey here:  https://x.com/RealEstateToAI/status/1886806315260953079 Would love to hear your thoughts: What resources did you find most valuable when starting with no experience in the space? What AI tools do you think are most valuable for automation?

MS in Computer Science student (non-tech bachelor) applying for first Machine Learning intern/coop

Hi, I am an international student in the U.S applying for my first co-op for a Machine Learning/AI role, would love to get some advice on my current resume, thanks. I am currently in my second last semester of my 2 year's masters program in CS. I had no tech background before this program and was working in higher education administration. I have applied to about 50 positions so far on LinkedIn and HandShake and have had no responses but a few rejection emails. If you are a Machine learning professional, please help if I could improve my current project sections, I have two projects I am working on and hoping to swap them in after I finish them by the end of this semester: (1)Adaptive Learning curriculum for Spanish Language Learning (Duolingo-Inspired), which tailors lessons based on user's daily interactions (e.g., bar conversations, gym interactions). (2) DEI analytics and how they impact student performances and career outcome in Higher Ed. My interests lies in using ML in EdTech and Higher Education. But before finishing them, are my current projects passable? Also any suggestion to enhance my work experience section since they are not tech-related? Thanks! https://preview.redd.it/ww7smowjazne1.png?width=5100&format=png&auto=webp&s=289cde9aee45b2066dcfbb375fc318e7a3c5f5d7

AI for Business: FREE Practical Course & Tools on YouTube

I worked for 15+ years in AI, created “AI for Business” to help any non technical professional learn and apply AI in their work. FREE course on YT + 6 tools (use-case gallery, ideation canvas, idea evaluation, POC template, team roles, & more) Course Link. Outline: https://preview.redd.it/nxh1952rqxad1.png?width=1744&format=png&auto=webp&s=4d31acdec5b0375734dcc49b1c0be81bc3e605e6

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.

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

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

500MRR.com

500MRR.com A few days ago, while browsing Hacker News, I came across a series of stories titled "Those making $500/month on side projects in 20xx - Show and tell," covering the years from 2017 to 2024. There were quite a few interesting projects, and on a whim, I pulled the data to create a website for visual exploration. The project URLs, income details, project overviews, and summaries from the comments section were extracted and summarized using a large language model. I spent about a day writing a Python script to process data, adjust LLM's prompt., using Nextra to generate a static website, and then deploying it on Vercel. 500MRR.com

I built a library to visualize and edit audio filters

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

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

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

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

ChatPDF and PDF.ai are making millions using open source tech... here's the code

Why "copy" an existing product? The best SaaS products weren’t the first of their kind - think Slack, Shopify, Zoom, Dropbox, or HubSpot. They didn’t invent team communication, e-commerce, video conferencing, cloud storage, or marketing tools; they just made them better. What is a "Chat with PDF" SaaS? These are AI-powered PDF assistants that let you upload a PDF and ask questions about its content. You can summarize articles, extract key details from a contract, analyze a research paper, and more. To see this in action or dive deeper into the tech behind it, check out this YouTube video. Let's look at the market Made possible by advances in AI like ChatGPT and Retrieval-Augmented Generation (RAG), PDF chat tools started gaining traction in early 2023 and have seen consistent growth in market interest, which is currently at an all-time high (source:google trends) Keywords like "chat PDF" and "PDF AI" get between 1 to 10 million searches every month (source:keyword planner), with a broad target audience that includes researchers, students, and professionals across various industries. Leaders like PDF.ai and ChatPDF have already gained millions of users within a year of launch, driven by the growing market demand, with paid users subscribing at around $20/month. Alright, so how do we build this with open source? The core tech for most PDF AI tools are based on the same architecture. You generate text embeddings (AI-friendly text representations; usually via OpenAI APIs) for the uploaded PDF’s chapters/topics and store them in a vector database (like Pinecone). Now, every time the user asks a question, a similarity search is performed to find the most similar PDF topics from the vector database. The selected topic contents are then sent to an LLM (like ChatGPT) along with the question, which generates a contextual answer! Here are some of the best open source implementations for this process: GPT4 & LangChain Chatbot for large PDF docs by Mayo Oshin MultiPDF Chat App by Alejandro AO PDFToChat by Hassan El Mghari Worried about building signups, user management, payments, etc.? Here are my go-to open-source SaaS boilerplates that include everything you need out of the box: SaaS Boilerplate by Remi Wg Open SaaS by wasp-lang A few ideas to stand out from the noise: Here are a few strategies that could help you differentiate and achieve product market fit (based on the pivot principles from The Lean Startup by Eric Ries): Narrow down your target audience for a personalized UX: For instance, an exam prep assistant for students with study notes and quiz generator; or a document due diligence and analysis tool for lawyers. Add unique features to increase switching cost: You could autogenerate APIs for the uploaded PDFs to enable remote integrations (eg. support chatbot knowledge base); or build in workflow automation features for bulk analyses of PDFs. Offer platform level advantages: You could ship a native mobile/desktop apps for a more integrated UX; or (non-trivial) offer private/offline support by replacing the APIs with local open source deployments (eg. llama for LLM, an embedding model from the MTEB list, and FAISS for vector search). TMI? I’m an ex-AI engineer and product lead, so don’t hesitate to reach out with any questions! P.S. I've started a free weekly newsletter to share open-source/turnkey resources behind popular products (like this one). If you’re a founder looking to launch your next product without reinventing the wheel, please subscribe :)

I got 400+ new customers in first 48 hours after launch!!!!

Yesterday I launched my new software and got 400+ customers in 48 hours. I'm gonna break down the product and my launch strategy. What is it? Remember when Elon was taking over Twitter and he emailed the CEO of Twitter Parag Agrawal saying “What did you get done this week?” Well I turned this idea into a software lol. A couple months ago, I had a realization while talking with some friends: I love asking ChatGPT for business advice, but I never remember to actually do it. Now what if there was a pro-active AI business coach that checked in on me every week? Something to keep me accountable and track my progress building my empire. It could have a database where I could see my progress every single week!!! And what if this AI business coach was a simple email that says “What did you get done this week?” So I built this: Elon Email. A weekly 1-on-1 with Elon Musk Every Sunday night for the last month, I’ve been getting a weekly email from Elon Musk saying “What did you get done this week?” I take a few minutes to write back with everything I got done that week: new revenue metrics, a list of the new features I shipped, new employees onboarded, number of workouts, exciting calls and collaboration opportunities, etc. Then an AI trained on Elon would give me tailored advice all in my email. And here's the best part. Rather than a nice friendly soft-spoken AI, I prompted the AI to be as savage and ruthless as Elon with its business advice. And it actually worked. One user said "it's like a slap in the face". I knew with 2025 New Years resolutions coming, I needed to launch it ASAP so I pushed through an all-nighter on Friday and got it launched today. Launch strategy: \> Focus on X (fka Twitter) as main source. I have 31,000 followers on X from the last few years building startups, so I posted my launch this morning there. X is Elon's social media network now so I didn't waste time on other platforms. I basically didn't look up from my phone for like 12 hours (my wife was pissed at me because we're technically on vacation but yolo) and I commented, engaged, and DMed with everyone I could. It paid off with 50,000+ views on the post and nearly 300 likes so far. \> Purposely exclude people. Yes, I know this sounds weird, but you need to purposely exclude some people to focus on the people who will actually use your product. I know a lot of people hate Elon and will hate me for making this. I don't care. I only care about the people who will actually use it aka my customers. The same thing with making it a "savage AI". I know there will be some people who prefer a nice friendly soft AI, but that's not my customer base. The internet is big enough you can find your customer base but you've gotta be willing to exclude some people to speak to the right people! \> Free tier. The weekly Elon email and AI reply is free. I also have a paid tier for a daily email and database access. I know I'm technically losing money on API fees for the free email and AI requests, but it's a loss leader, the costs are actually quite minimal since it's only 1 API request/week, and some % will convert and already have. Doing free was worth it to give people a chance to try it. I hope this helps with your next launch!!!

I retired at 32 from my side project. Here's the path I took.

EDIT 2: Thanks for the award kind stranger! I've stopped responding to reddit comments for this post. I'm adding an FAQ to the original post based on the most common high quality questions. If you have a question that you're dying to know the answer to and that only I can help you with (vs. Google, ChatGPT, etc.), DM me. EDIT: I love how controversial this post has become (50% upvote rate), and only in this subreddit (vs. other subreddits that I posted the same content in). I trust that the open-minded half of you will find something useful in this post and my other posts and comments. I retired at 32 years old, in large part thanks to a B2C SaaS app that I developed on my own. Now, I don't have to work in order to cover my living expenses, and wouldn't have to work for quite a while. In other words, I can finally sip mai tais at the beach. I've condensed how I got there into this post. First, a super simplified timeline of events, followed by some critical details. Timeline 2013 Graduated college in the US 2013 Started first corporate job 2013 Started side project (B2C app) that would eventually lead to my retirement 2020 Started charging for use of my B2C app (was free, became freemium) 2021 Quit my last corporate job 2022 Retired: time freedom attained Details First, some summary statistics of my path to retirement: 9 years: time between graduating college and my retirement. 8 years: total length of my career where I worked at some corporate day job. 7 years: time it took my B2C app to make its first revenue dollar 2 years: time between my first dollar of SaaS revenue and my retirement. "Something something overnight success a decade in the making". I got extremely lucky on my path to retirement, both in terms of the business environment I was in and who I am as a person. I'd also like to think that some of the conscious decisions I made along the way contributed to my early retirement. Lucky Breaks Was born in the US middle class. Had a natural affinity for computer programming and entrepreneurial mindset (initiative, resourcefulness, pragmatism, courage, growth mindset). Had opportunities to develop these mindsets throughout life. Got into a good college which gave me the credentials to get high paying corporate jobs. Was early to a platform that saw large adoption (see "barnacle on whale" strategy). Business niche is shareworthy: my SaaS received free media. Business niche is relatively stable, and small enough to not be competitive. "Skillful" Decisions I decided to spend the nights and weekends of my early career working on side projects in the hopes that one would hit. I also worked a day job to support myself and build my savings. My launch funnel over roughly 7 years of working on side projects: Countless side projects prototyped. 5 side projects publically launched. 2 side projects made > $0. 1 side project ended up becoming the SaaS that would help me retire. At my corporate day jobs, I optimized for learning and work-life balance. My learning usually stalled after a year or two at one company, so I’d quit and find another job. I invested (and continute to do so) in physical and mental wellbeing via regular workouts, meditation, journaling, traveling, and good food. My fulfilling non-work-life re-energized me for my work-life, and my work-life supported my non-work-life: a virtuous cycle. I automated the most time-consuming aspects of my business (outside of product development). Nowadays, I take long vacations and work at most 20 hours a week / a three-day work week . I decided to keep my business entirely owned and operated by me. It's the best fit for my work-style (high autonomy, deep focus, fast decision-making) and need to have full creative freedom and control. I dated and married a very supportive and inspiring partner. I try not to succumb to outrageous lifestyle creep, which keeps my living expenses low and drastically extends my burn-rate. Prescription To share some aphorisms I’ve leaned with the wantrepreneurs or those who want to follow a similar path: Maximize your at bats, because you only need one hit. Bias towards action. Launch quickly. Get your ideas out into the real world for feedback. Perfect is the enemy of good. If you keep swinging and improving, you'll hit the ball eventually. Keep the big picture in mind. You don't necessarily need a home-run to be happy: a base hit will often do the job. Think about what matters most to you in life: is it a lot of money or status? Or is it something more satisfying, and often just as if not more attainable, like freedom, loving relationships, or fulfillment? Is what you’re doing now a good way to get what you want? Or is there a better way? At more of a micro-level of "keep the big picture in mind", I often see talented wantrepreneurs get stuck in the weeds of lower-level optimizations, usually around technical design choices. They forget (or maybe subconsciously avoid) the higher-level and more important questions of customer development, user experience, and distribution. For example: “Are you solving a real problem?” or “Did you launch an MVP and what did your users think?” Adopt a growth mindset. Believe that you are capable of learning whatever you need to learn in order to do what you want to do. The pain of regret is worse than the pain of failure. I’ve noticed that fear of failure is the greatest thing holding people back from taking action towards their dreams. Unless failure means death in your case, a debilitating fear of failure is a surmountable mental block. You miss 100% of the shots you don't take. When all is said and done, we often regret the things we didn't do in life than the things we did. There’s more to life than just work. Blasphemous (at least among my social circle)! But the reality is that many of the dying regret having worked too much in their lives. As Miss Frizzle from The Magic Schoolbus says: "Take chances, make mistakes, get messy!" Original post

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

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

I made a website to generate craft ideas from existing materials

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

Just completed a new type of language learning website - read popular stories scaled to different reading levels

As a language learner and software developer, I bootstrapped my project superlang.com over the past year working on the side. There is a mobile friendly web app now, and iOS/Android apps coming in a few months. A year ago I discovered the concept of "comprehensible input" as a way to help me learn German. Even if it's not a silver bullet, it sounded pretty great. Rather than drilling vocab or looking at grammar charts, I could "just read" and acquire the language. I picked up some fairy tales in German, and stories like Alice in Wonderland. Unfortunately, I couldn't really read them. I had to stop every sentence to look up words and try and decipher sentence constructions. Then I turned to some purpose built simple stories for German beginners. But there was a different problem... these were not really stories with any real plot. I could only read so many "Hans goes to the market" type stories before losing interest. My idea was to try to get the best of both worlds somehow. What if I could take a real story, say Alice in Wonderland (or even War and Peace), and dial the difficulty down to my level without losing the plotline. That way, beginners can start right away with something basically comprehensible. Then, you could also re-read the same story at increasing difficulty levels as you gain confidence. As a cherry on top, more illustrations would help with comprehension so each page could have a picture. Is it revolutionary? Maybe, maybe not. I am building off a well established idea of "graded readers" which are simplified stories meant for learning languages. And there are somewhat similar ideas out there now that AI is good at simplifying text, but none that really take this idea where it needs to be with many preloaded stories, multiple difficulty levels, high quality human verified text, and all the bells and whistles. I spent a year building Superlang and it is ready to put out there. Some quick notes: There are 3 languages so far, intended for native English speakers: German, French, and Spanish There are 3 difficulty levels you can set on each story: beginner (roughly A1-A2), intermediate (roughly A2-B1), and advanced (the same level as the original story, but typically B2+) There is premium version as producing the content was somewhat expensive. You can still do a lot of reading on the free version. I have done no marketing yet, except for this post :) The implementation is a combination of AI, and human proofreading and reviewing. In particular, the simplification of stories is very heavily AI driven. The illustrations for each page are AI as well. For translation, as many of you may be aware new LLM models are typically better than Google translate, but still far from perfect. I am very much a proponent of keeping real people in the loop, and so I have real people proofread the translations. That's why there are only about 700 pages of content so far and not tens of thousands. Let me know what you think, and if you find it helpful! Alice in Wonderland - beginner level German Romeo and Juliet - beginner level Spanish

I made a super niche app for sailors and scaled it to 500k downloads

I started developing this app in 2016, and it was my first app ever. I already had several years of programming experience. Since I was studying maritime navigation, I came up with the idea of creating a maritime app to help students with various nautical calculations and learn maritime regulations. Although I had no experience in mobile app development, I chose the Ionic framework and started development gradually. First Version The first version took me about four months to develop because I literally had to learn everything from scratch: how to develop mobile apps, how to publish them, and everything needed to enable downloads on the app stores. Many of you might recognize me from my story about developing Sintelly and its late monetization. I made the same mistake with this maritime app. At that time, in my country, there was no possibility of earning through in-app purchases, only through ad displays. Since the app was predominantly downloaded in countries like India, the Philippines, and Indonesia, the ad revenue was quite low, and after some time, I removed the ads. Abandonment and Realization As I started developing other apps, this one fell into obscurity. I even just remembered that I needed to renew the domain, which resulted in losing it. The domain buyer tried to sell it back to me for years for $20k, which was absurd. All this led me to rebrand and start working on this app again. Interestingly, during these 8 years, the app never showed a declining trend in installations or active users. I'll share some numbers to give you insight: Total installations (Android + iOS): 501,000 Active installations (Android): 48,000 Monthly active users: 20,000 Average rating: Android 4.8, iOS 4.7 When I considered these numbers, I realized they weren't bad at all and that I was far ahead of most competitors. This led to my decision to rebrand and create a new website. I quickly built the website using WordPress and published lots of existing content from the app. What surprises me is that today, after a year and a half, the website has about 8-10k monthly organic visits. Choosing a Direction Based on all this, I decided it was time to create a Premium version and start selling the app. Since I've been working with AI for many years (which I've written about here), I started thinking about using AI to help seafarers speed up some of their tasks. This led to the idea of creating a multi-agent system equipped with numerous tools to help seafarers. I developed various agents with functionalities, including retrieving maritime weather information, locating and tracking ships, doing various nautical calculations, calculating the shortest maritime routes and unit conversions, and learning about all courses and maritime regulations. All this required considerable work, but thanks to tools like Cursor and Claude, I implemented it in less than four weeks. Last week, I published this new version and started selling subscriptions, and I can already boast that I've earned slightly over $100. This isn't much, but I'm happy to see my first app generating some income, which I always thought impossible. Along this journey, I learned many lessons, and the most important one is to never give up or write off a product. With a little effort, everything can be brought back to life and secure at least some passive income, enough for your morning coffee. Additionally, I learned how to develop mobile apps, which has shaped my career since then. If it weren't for this app, I probably would never have become a developer. I have numerous plans for what to add next and how to improve. I'll base everything on AI features and push the app in that direction.

Learn how to code in 24 hours with a Private AI Tutor

Learning how to code is REALLY HARD. I remember I struggled a lot learning how to code. I just wanted to build a simple app or website but the task was super daunting. There were so many steps, so many things to learn. Terminal, git, command prompt, IDE, library, package, React, Express, GAH! It was hard. I did a lot of courses but I always got 10-20% through and gave up. They were just SO BORING. Some of the courses were too advanced, some were too beginner, and all required me to keep pausing & playing. So, I built Athens: https://www.tryathens.com/ Athens gives you a personal AI tutor that understands your skill level and modifies each challenge/lesson to your skill level. No nothing about programming? Learn from the basics of HTML. Already know the basics of React? Implement it, and then learn the backend. All of this while you build a fully-fledged clone of Instagram, Netflix, or one of the many other projects! What do you guys think about this? Would you use it? Do you have any feedback? PS: Athens will normally go for $299/year but currently it's on pre-sale for $159 (sometimes $99 with lifetime discount)

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

My Side Projects: From CEO to 4th Developer (Thanks, AI 🤖)

Hey Reddit 👋, I wanted to share a bit about some side projects I’ve been working on lately. Quick background for context: I’m the CEO of a mid-to-large-scale eCommerce company pulling in €10M+ annually in net turnover. We even built our own internal tracking software that’s now a SaaS (in early review stages on Shopify), competing with platforms like Lifetimely and TrueROAS. But! That’s not really the point of this post — there’s another journey I’ve been on that I’m super excited to share (and maybe get your feedback on!). AI Transformed My Role (and My Ideas List) I’m not a developer by trade — never properly learned how to code, and to be honest, I don’t intend to. But, I’ve always been the kind of guy who jots down ideas in a notes app and dreams about execution. My dev team calls me their “4th developer” (they’re a team of three) because I have solid theoretical knowledge and can kinda read code. And then AI happened. 🛠️ It basically turned my random ideas app into an MVP generation machine. I thought it’d be fun to share one of the apps I’m especially proud of. I am also planning to build this in public and therefore I am planning to post my progress on X and every project will have /stats page where live stats of the app will be available. Tackling My Task Management Problem 🚀 I’ve sucked at task management for YEARS, I still do! I’ve tried literally everything — Sheets, Todoist, Asana, ClickUp, Notion — you name it. I’d start… and then quit after a few weeks - always. What I struggle with the most is delegating tasks. As a CEO, I delegate a ton, and it’s super hard to track everything I’ve handed off to the team. Take this example: A few days ago, I emailed an employee about checking potential collaboration opportunities with a courier company. Just one of 10s of tasks like this I delegate daily. Suddenly, I thought: “Wouldn’t it be AMAZING if just typing out this email automatically created a task for me to track?” 💡 So… I jumped in. With the power of AI and a few intense days of work, I built a task manager that does just that. But of course, I couldn’t stop there. Research & Leveling It Up 📈 I looked at similar tools like TickTick and Todoist, scraped their G2 reviews (totally legally, promise! 😅), and ran them through AI for a deep SWOT analysis. I wanted to understand what their users liked/didn’t like and what gaps my app could fill. Some of the features people said they were missing didn’t align with the vision for my app (keeping it simple and personal), but I found some gold nuggets: Integration with calendars (Google) Reminders Customizable UX (themes) So, I started implementing what made sense and am keeping others on the roadmap for the future. And I’ve even built for that to, it still doesn’t have a name, however the point is you select on how many reviews of a specific app you want to make a SWOT analysis on and it will do it for you. Example for Todoist in comments. But more on that, some other time, maybe other post ... Key Features So Far: Here’s what’s live right now: ✅ Email to Task: Add an email as to, cc, or bcc — and it automatically creates a task with context, due dates, labels, etc. ✅ WhatsApp Reminders: Get nudged to handle your tasks via WhatsApp. ✅ WhatsApp to Task: Send a message like /task buy groceries — bam, it’s added with full context etc.. ✅ Chrome Extension (work-in-progress): Highlight text on any page, right-click, and send it straight to your task list. Next Steps: Build WITH the Community 👥 Right now, the app is 100% free while still in the early stages. But hey, API calls and server costs aren’t cheap, so pricing is something I’ll figure out with you as we grow. For now, my goal is to hit 100 users and iterate from there. My first pricing idea is, without monthly subscription, I don’t want to charge someone for something he didn’t use. So I am planning on charging "per task", what do you think? Here’s what I have planned: 📍 End of Year Goal: 100 users (starting from… 1 🥲). 💸 Revenue Roadmap: When we establish pricing, we’ll talk about that. 🛠️ Milestones: Post on Product Hunt when we hit 100 users. Clean up my self-written spaghetti code (hire a pro dev for review 🙃). Hire a part-time dev once we hit MRR that can cover its costs. You can check how are we doing on thisisatask.me/stats Other Side Projects I’m Working On: Because… what’s life without taking on too much, right? 😂 Full list of things I’m building: Internal HRM: Not public, tried and tested in-house. Android TV App: Syncs with HRM to post announcements to office TVs (streamlined and simple). Stats Tracker App: Connects to our internal software and gives me real-time company insights. Review Analyzer: Scrapes SaaS reviews (e.g., G2) and runs deep analysis via AI. This was originally for my Shopify SaaS but is quickly turning into something standalone. Coming soon! Mobile app game: secret for now. Let’s Build This Together! Would love it if you guys checked out https://thisisatask.me and gave it a spin! Still super early, super raw, but I’m pumped to hear your thoughts. Also, what’s a must-have task manager feature for you? Anything that frustrates you with current tools? I want to keep evolving this in public, so your feedback is gold. 🌟 Let me know, Reddit! Are you with me? 🙌

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

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

ChatPDF and PDF.ai are making millions using open source tech... here's the code

Why "copy" an existing product? The best SaaS products weren’t the first of their kind - think Slack, Shopify, Zoom, Dropbox, or HubSpot. They didn’t invent team communication, e-commerce, video conferencing, cloud storage, or marketing tools; they just made them better. What is a "Chat with PDF" SaaS? These are AI-powered PDF assistants that let you upload a PDF and ask questions about its content. You can summarize articles, extract key details from a contract, analyze a research paper, and more. To see this in action or dive deeper into the tech behind it, check out this YouTube video. Let's look at the market Made possible by advances in AI like ChatGPT and Retrieval-Augmented Generation (RAG), PDF chat tools started gaining traction in early 2023 and have seen consistent growth in market interest, which is currently at an all-time high (source:google trends) Keywords like "chat PDF" and "PDF AI" get between 1 to 10 million searches every month (source:keyword planner), with a broad target audience that includes researchers, students, and professionals across various industries. Leaders like PDF.ai and ChatPDF have already gained millions of users within a year of launch, driven by the growing market demand, with paid users subscribing at around $20/month. Alright, so how do we build this with open source? The core tech for most PDF AI tools are based on the same architecture. You generate text embeddings (AI-friendly text representations; usually via OpenAI APIs) for the uploaded PDF’s chapters/topics and store them in a vector database (like Pinecone). Now, every time the user asks a question, a similarity search is performed to find the most similar PDF topics from the vector database. The selected topic contents are then sent to an LLM (like ChatGPT) along with the question, which generates a contextual answer! Here are some of the best open source implementations for this process: GPT4 & LangChain Chatbot for large PDF docs by Mayo Oshin MultiPDF Chat App by Alejandro AO PDFToChat by Hassan El Mghari Worried about building signups, user management, payments, etc.? Here are my go-to open-source SaaS boilerplates that include everything you need out of the box: SaaS Boilerplate by Remi Wg Open SaaS by wasp-lang A few ideas to stand out from the noise: Here are a few strategies that could help you differentiate and achieve product market fit (based on the pivot principles from The Lean Startup by Eric Ries): Narrow down your target audience for a personalized UX: For instance, an exam prep assistant for students with study notes and quiz generator; or a document due diligence and analysis tool for lawyers. Add unique features to increase switching cost: You could autogenerate APIs for the uploaded PDFs to enable remote integrations (eg. support chatbot knowledge base); or build in workflow automation features for bulk analyses of PDFs. Offer platform level advantages: You could ship a native mobile/desktop apps for a more integrated UX; or (non-trivial) offer private/offline support by replacing the APIs with local open source deployments (eg. llama for LLM, an embedding model from the MTEB list, and FAISS for vector search). TMI? I’m an ex-AI engineer and product lead, so don’t hesitate to reach out with any questions! P.S. I've started a free weekly newsletter to share open-source/turnkey resources behind popular products (like this one). If you’re a founder looking to launch your next product without reinventing the wheel, please subscribe :)

I grew my mobile app to 1.4 million downloads

I started developing the app in early 2017, well before the AI era, when mobile apps were at their peak popularity. My idea was to create an app for emotional and psychological support in the form of helpful articles and various quizzes, such as personality assessments and life satisfaction tests. I named the app "Emotional Intelligence" because this keyword showed good ASO potential for positioning at the top of mobile stores. This proved to be accurate, and the app quickly gained traction in terms of downloads. A major problem I faced then was monetization. Unfortunately, in my country, it wasn't possible to sell through Google Play then, so I could only display ads. I started with Google AdMob, earning $2000 monthly after just a few months. The app then got about 1500 organic downloads daily and quickly surpassed 500,000. Three years after launching the app, I decided it was time for branding to build recognition. By combining the words "sentiment" and "intelligence," I came up with "Sintelly." I then pushed the app toward a social network, which differed from the right move. Adding features like discussion forums for problems, likes, and comments would result in even more growth, but the opposite happened. The app started declining, and I began investing in advertising campaigns. I managed to maintain a balance between income and expenses but without any profit. Then COVID-19 hit, and everything went downhill. I had to give up development and find a job as a developer to ensure my livelihood. Two years passed since I gave up, and that's when ChatGPT started gaining popularity. This immediately showed me how to steer the app towards active support for well-being questions. As I'm not an expert in psychology, I found several external psychotherapists who helped me put together CBT therapy, which I then implemented through a chatbot. This is how the new Sintelly app was born, with its main feature being a chatbot system composed of 17 AI agents that adapt to the user and guide them through a five-phase CBT therapy (I'll write a post about the technology). In addition to the agents, I added various exercises and tests to provide better personalization for the user. Initially, I made all of this free, which was also a mistake. I followed the principle of first showing what the app can do and gathering enough new users before starting to charge. I started selling subscriptions at the beginning of July, and since then, the app has had stable growth. If you want a check app, here is the link. Lessons learned: If things are working, don't touch them Start selling immediately upon app release; there's no need to wait Regularly test prices and types of subscriptions Onboarding is the most essential part of the app because most users buy subscriptions during onboarding It's essential to listen to user feedback. From day one, have a website and work on content to generate organic visits and redirect users from the web to the mobile app Stats: Over 1.4 million downloads 4.4 rating Only 40,000 active users (I had a massive loss during the period when I gave up) 280 active subscribers $3000 monthly revenue Next steps: Work on improving the Agent AI approach Setting up email campaigns and transactional emails Introducing in-app and push notifications Introducing gamification Potential for B2B I hope you can extract useful information from my example and avoid repeating my mistakes. I'm interested in your thoughts and if you have any recommendations for the next steps. I'm always looking to learn and improve.

Hit a major milestone with my app that helps people find jobs and optimize their resume

I've been grinding for ~1.5 years now on my sideproject, Jobs-Scout, which helps people find jobs and optimize their resume for any specific role. I've been in industry a number of years as a senior manager, so I have done lots of interviewing and hiring and I think that helps my tool do a better job than others in knowing how to position a resume. It's the non-technical stuff, like branding, SEO etc. thats the hardest for me, but my buddy is now helping and we're starting to make in-roads and traffic is up a lot! 🚀 We hit our 200th paid customer today which is a major milestone for us, and just wanted to share! The app features: resume-to-job analysis using AI (of course!) a free job board updated daily matching and emailing new jobs to users (ie. 'scouting' for jobs hence the name!) resume builder and editor with inline AI optimization free tier (3 free analyses a month) and paid tiers If you're curious, everything's running on AWS, and I code and maintain it myself in the evenings after work, and my colleague is now on marketing and business development. Biggest lesson was finding a trustworthy co-founder. I went through a couple of iterations, but you need a certain personality that's able to keep up with the hustle. Would love feedback or tips on how to keep growing 🚀 . Edit: link: https://www.jobs-scout.com

Running and selling multiple side projects alongside a 9-5

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

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

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

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

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

Launch your landing page and marketing website faster even if you aren't a designer

As a frontend engineer  who is also good with UI/UX design,  aside from building dashboard and web apps all the time, one other thing I get to build is a landing page or marketing website to sell the product we are building. And just like dashboards, there are lots of repeatable sections in marketing website, just the uniqueness of designs. I find myself always building marketing websites from scratch always, which led me to building astrolandingpage.com , with my years of experience designing and building landing pages, I thought, this is good for me to do. to help me Save time and cut cost Launch early and validate my idea faster Launch beautiful landing page even if you are not a designer With copies that helps you converts, as each templates comes with examples copies and how to write them Although, I’ve been scared to launch this, because I think people might judge me, I probably wont make any sale, all because of how AI is turning out to be. With astrolandingpage, either you are a developer, a non technical person, a freelancer, an agency, a startup founder, you can launch beautiful and modern designs full fledge template in 20 minutes You get to pick from lots of templates and also UI components that you can copy and paste without the need to redesign  I believe this would be of great value to you and also I want to have fun building this. check it our here Astrolandingpage wesbite

I Launched a Side Project That People Love, But Scaling It Is Brutal

I Built a Side Project with Great Engagement—But It’s Still Not Making Money Six months ago, I started a side project in the consumer AI space: opencharacter.org. It’s been a grind, but I’ve built something people actually love—high retention, strong engagement, and users spending a ton of time on the platform. By all product metrics, it’s a success. But financially? It’s not quite there yet. The biggest challenge hasn’t been technical, managing infrastructure, or even dealing with a community. It’s distribution. Getting people to actually find and use your side project at scale is insanely hard. What’s Worked Reddit – Thoughtful, non-spammy comments in relevant threads drove early users. Instagram – Short-form videos brought in surprising traction. Paid ads – Somewhat effective, but tough to balance customer acquisition costs and revenue. What Hasn’t (Yet) TikTok – Dozens of videos later, still struggling to make it a reliable growth channel. Discord – Great for engagement, but not a strong acquisition channel. Recently, I brought on a co-founder who has done over 100 million views on Instagram Reels in under two years, so I’m hopeful we can crack the growth formula. Because without a scalable system for getting users, even a great side project won’t reach its potential. If I could start over, I’d think much more about distribution before building. Would love to hear from others—how do you drive growth for your side project?

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

Just reached 300 users in 3 months!!!

Just reached 300 users after 3 months live!!! My co-founder has been posting a bit here and always got some strong support and he suggested I share my side of things so here it is: How it started I co-founded AirMedia almost a year ago and we both didn’t know much about design/marketing/coding (just studied programming during my 6-month exchange period. The quickest way to get started seemed to get a no-code product that we could put in front of users and get feedback. My co-founder then started learning about bubble and we put together a basic platform to show users. I was working on a custom-code database in the meantime and decided after month 2 that we wanted to get something better I.e. AI would be interacting with the UI and had to do everything custom-code for it. We’re now month 3 and started from scratch again. While I was working on the code, we started talking to some potential users and selling lifetime deals to validate the idea (this is where I would start if I had to do it over again). Well I progressively found out it was more complicated than expected and we only released our first beta product last August (6 months later) Some challenges pre-launch: Getting the Meta/LinkedIn permissions for scheduling took around 1 month As the whole process took more time than expected, the waitlist of 300 that we managed to put together only converted by 10% (into free users). Please don’t make our mistakes and always keep your waitlist updated on what’s going on. Some challenges post-launch: Getting the right feedback and how to prioritise Getting users Monetising (yes - we’re bootstrapped) To get the best feedback we implemented some tracking (according to GDPR of course) on the platform and implemented Microsoft Clarity. The latter is a game-changer, if you have a SaaS and don’t use it you’re missing out. I wasn’t really into getting users as my co-founder handled that but it’s mainly manual and personalised LinkedIn outreach at the beginning and Reddit sharing about the progress, answering questions and getting some feedback at the same time. To monetise we realised we’re too common and there are 100+ other nice schedulers around so we’re now focusing on cracking the content creation side of AI (to be released next week 👀) as there’s much less competitors and it seems like that’s our users want. In the meantime of growing the company, we had to find a way to pay the bills as it’s two of us living together. So my co-founder started using the bubble skills gained and doing some freelance. He did around 7 platforms the last 6 months and we’re now just launching a bubble agency as a part of the main company to get your idea of a SaaS done in 30 days. That’s QuickMVP. It seemed like the right move to help other people (I met many non-technical founder looking for someone to bring their idea to life that didn’t cost $10k and was reliable) and include the AirMedia subscription in the package so let’s see how this next step plays out. Thanks for reading until here :)

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

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

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.

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

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

How 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

How to get your first 10 customers with cold email

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

I’ve Compiled the Best AI Side Project Playbooks and Tested Them Myself—Anyone Interested?

I’ve spent the past year diving deep into AI-powered side projects, testing out all the best playbooks I could find. Some worked amazingly well, some flopped, and I learned a ton along the way. Now, I’ve compiled everything—only the most effective, step-by-step playbooks that actually work. These cover everything from idea validation to scaling, and I’ve tested them all myself to make sure they’re legit. Some of the things I’ve successfully built with AI: ✅ Automated content businesses ✅ Niche websites that generate passive income ✅ AI-powered digital product businesses ✅ Simple AI tools that people actually pay for ✅ AI-assisted freelancing strategies Would anyone be interested in checking these out? Just trying to see if there’s demand before I share more! Let me know what kind of AI side hustle you’d want to try.

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

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

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 retired at 32 from my side project. Here's the path I took.

EDIT 2: Thanks for the award kind stranger! I've stopped responding to reddit comments for this post. I'm adding an FAQ to the original post based on the most common high quality questions. If you have a question that you're dying to know the answer to and that only I can help you with (vs. Google, ChatGPT, etc.), DM me. EDIT: I love how controversial this post has become (50% upvote rate), and only in this subreddit (vs. other subreddits that I posted the same content in). I trust that the open-minded half of you will find something useful in this post and my other posts and comments. I retired at 32 years old, in large part thanks to a B2C SaaS app that I developed on my own. Now, I don't have to work in order to cover my living expenses, and wouldn't have to work for quite a while. In other words, I can finally sip mai tais at the beach. I've condensed how I got there into this post. First, a super simplified timeline of events, followed by some critical details. Timeline 2013 Graduated college in the US 2013 Started first corporate job 2013 Started side project (B2C app) that would eventually lead to my retirement 2020 Started charging for use of my B2C app (was free, became freemium) 2021 Quit my last corporate job 2022 Retired: time freedom attained Details First, some summary statistics of my path to retirement: 9 years: time between graduating college and my retirement. 8 years: total length of my career where I worked at some corporate day job. 7 years: time it took my B2C app to make its first revenue dollar 2 years: time between my first dollar of SaaS revenue and my retirement. "Something something overnight success a decade in the making". I got extremely lucky on my path to retirement, both in terms of the business environment I was in and who I am as a person. I'd also like to think that some of the conscious decisions I made along the way contributed to my early retirement. Lucky Breaks Was born in the US middle class. Had a natural affinity for computer programming and entrepreneurial mindset (initiative, resourcefulness, pragmatism, courage, growth mindset). Had opportunities to develop these mindsets throughout life. Got into a good college which gave me the credentials to get high paying corporate jobs. Was early to a platform that saw large adoption (see "barnacle on whale" strategy). Business niche is shareworthy: my SaaS received free media. Business niche is relatively stable, and small enough to not be competitive. "Skillful" Decisions I decided to spend the nights and weekends of my early career working on side projects in the hopes that one would hit. I also worked a day job to support myself and build my savings. My launch funnel over roughly 7 years of working on side projects: Countless side projects prototyped. 5 side projects publically launched. 2 side projects made > $0. 1 side project ended up becoming the SaaS that would help me retire. At my corporate day jobs, I optimized for learning and work-life balance. My learning usually stalled after a year or two at one company, so I’d quit and find another job. I invested (and continute to do so) in physical and mental wellbeing via regular workouts, meditation, journaling, traveling, and good food. My fulfilling non-work-life re-energized me for my work-life, and my work-life supported my non-work-life: a virtuous cycle. I automated the most time-consuming aspects of my business (outside of product development). Nowadays, I take long vacations and work at most 20 hours a week / a three-day work week . I decided to keep my business entirely owned and operated by me. It's the best fit for my work-style (high autonomy, deep focus, fast decision-making) and need to have full creative freedom and control. I dated and married a very supportive and inspiring partner. I try not to succumb to outrageous lifestyle creep, which keeps my living expenses low and drastically extends my burn-rate. Prescription To share some aphorisms I’ve leaned with the wantrepreneurs or those who want to follow a similar path: Maximize your at bats, because you only need one hit. Bias towards action. Launch quickly. Get your ideas out into the real world for feedback. Perfect is the enemy of good. If you keep swinging and improving, you'll hit the ball eventually. Keep the big picture in mind. You don't necessarily need a home-run to be happy: a base hit will often do the job. Think about what matters most to you in life: is it a lot of money or status? Or is it something more satisfying, and often just as if not more attainable, like freedom, loving relationships, or fulfillment? Is what you’re doing now a good way to get what you want? Or is there a better way? At more of a micro-level of "keep the big picture in mind", I often see talented wantrepreneurs get stuck in the weeds of lower-level optimizations, usually around technical design choices. They forget (or maybe subconsciously avoid) the higher-level and more important questions of customer development, user experience, and distribution. For example: “Are you solving a real problem?” or “Did you launch an MVP and what did your users think?” Adopt a growth mindset. Believe that you are capable of learning whatever you need to learn in order to do what you want to do. The pain of regret is worse than the pain of failure. I’ve noticed that fear of failure is the greatest thing holding people back from taking action towards their dreams. Unless failure means death in your case, a debilitating fear of failure is a surmountable mental block. You miss 100% of the shots you don't take. When all is said and done, we often regret the things we didn't do in life than the things we did. There’s more to life than just work. Blasphemous (at least among my social circle)! But the reality is that many of the dying regret having worked too much in their lives. As Miss Frizzle from The Magic Schoolbus says: "Take chances, make mistakes, get messy!" Original post

I retired at 12 from my side project. AMA

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

I retired at 12 from my side project. AMA

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

Disorganized: The note taking app for busy people (no AI inside)

https://preview.redd.it/27qoz7ihlnpe1.png?width=1774&format=png&auto=webp&s=1658d7a4c619df46cd76c5ff639b6c6c7b65fc50 About one year ago I had enough and set out to create my own note taking app, and have been working on it in my spare time since summer. I had two main goals when creating Disorganized: \- Less friction If I'm walking around and a thought pop ups in my head there should be zero friction to writing it down. That's why Disorganized doesn't ask you to write a title, sort it into the correct folder, etc. You write exactly your thoughts and nothing else. \- A better solution than templates. I wanted one app that I could use to track my workouts, my recipes and one-off notes. Other apps accomplish this with templates but I find templates too rigid - I don't want to create a "recipe" template because a "recipe" is not always the same thing. It's usually a table of ingredients and some instructions in text, but other times it's multiple tables of ingredients, or something else entirely. Templates are too rigid. In Disorganized, you "clone" notes to create a new note with the same structure. This way, you can reuse previous set ups, but you're completely free to evolve your "template" as you go. Please try it out and tell me what you think! iOS, three months premium: https://apps.apple.com/redeem/?ctx=offercodes&id=6738280174&code=THREEMONTHS Android: https://play.google.com/store/apps/details?id=com.disorganized.disorganized&pli=1 Use code "THREEMONTHS" at checkout for three months. Web version: https://app.getdisorganized.com/

My side project is starting getting attentions. We create AI virtual customer to train you and your sales.

Our team and I has years of SAAS sales engineering and sales trainer experience, brining the top Sales strategy, training & coaching experience to founders and SMB sales leaders. Peak Mojo transforms your sales training with our AI roleplay tool. Here’s what we offer: AI Customer Roleplay: Virtual AI personas for realistic sales practice. Chrome Plugin: Gathers info from LinkedIn for authentic scenarios. Mock Sessions: Managers review mock calls to evaluate new reps. Looking for early adopters and help shape our product! Reply to book a demo meeting. I will sit down with you and discuss what can we shape the product to fit your need. https://www.peakmojo.ai/

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

How I'm automating all my SEO research & writing with AI by building an open source software

I make most of my current recurring income from writing articles for a few blogs. Over the years I have developed strategies and writing techniques that increase my chances of landing at the top of Google search results. I’m a writer, but I also write code. With the advent of AI I have been itching to codify many of my previous activities. I tried writing content with the general LLMs like ChatGPT and Claude but the results were terrible, especially for niches with technical information. I didn’t want to lose hope in AI because I realised with A LOT of hand-holding, it got better results. THEN IT HIT ME!  What if I could create a Human-Guided AI for Better AI-Written Articles: enter Building ContentScribe After months of coding with AI tools and trying different approaches, I’m excited to share that ContentScribe is finally taking shape. The journey to this point has been challenging but incredibly rewarding. Over the past six months, we’ve been using ContentScribe ourselves to automate blog content creation. We found other tools in the AI article generation space such as Koala AI and Cuppa that left us wanting more. They basically took a topic from you and let the AI loose. We consider this to be a better Koala AI and Cuppa alternative. I wanted to have more control and freedom from the expense of the credit system most of them use. Even after generation, every article required significant human input to make it truly SEO-friendly, and existing tools couldn’t handle the specific strategies we needed for our niche. So, we decided to build something new: an AI-powered, open-source tool that doesn’t just spit out generic articles, but actually allows users to shape how the content is written. ContentScribe is designed to integrate the SEO techniques that we’ve developed over years of building profitable blogs. It codifies our best practices and turns them into a process that anyone can use to create researched, optimized content, every time. The product works, and it’s live! We’ve been populating our latest blog with human-guided AI-written articles, and the results are already impressive. The coolest part? This project scratches our own itch and addresses the pain points we faced when using other tools. Plus there is nothing to lose because it’s free and open source, you can run it locally or in the cloud. It’s still early days, but I’m excited to share more as we keep building in public. We’re working on tutorials, and adding more features. The feedback we’ve gotten so far from our in-house team has been invaluable, and I’m looking forward to sharing this with more content creators out there. For anyone struggling to get their ideas off the ground: keep experimenting, keep building. ContentScribe is proof that when you combine persistence with innovation, the results can be something you’re genuinely proud of. This is just the beginning!

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.

Built an AI marketplace for hiring AI agents, tools & developers – Would love feedback!

Hey Reddit! 👋 I’ve been fascinated by the rise of AI automation, and YC-backed Firecrawl recently made headlines for hiring an AI agent for $15K/year. That got me thinking… 🤔 💡 What if there was a marketplace where businesses could hire AI agents, tools, and developers easily? So, I built agentsjungle.com as a side project: ✅ Discover AI Agents & Tools for automation ✅ Hire AI Developers for custom solutions ✅ Find AI Job Listings in AI & ML Right now, it’s just a side project, and I’d love feedback from the community! 🔗 Check it out: agentsjungle.com

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

I made a Voice AI Automated Testing platform (because I hate making phone calls)

As my first New Year’s resolution, I’m excited to officially launch my side project: Testzilla.ai. While designing my Voice AI systems using VAPI, RetellAI, Bland, etc., I quickly got tired of the "Update system, test call flows, repeat" cycle that went with it. The whole point of Voice AI (for me) was that I could get off the phone, not spend even more time on it. So I made some Voice AI agents to test my Voice AI system so I didn't have to keep doing it manually. I showed it to developers friends who got excited and wanted to use it themselves with their systems (and sent me "Take My Money" meme, always a good sign). After hearing this a bunch of times, I decided to make it a platform I could share and easily use on multiple projects, have a simple UI, and let me run tests from my desktop or mobile with a click—and not spend 5-30 minutes of awkward time talking to phonebots in a crowded office. Win. It also has the benefit of being a way for an AI Agency to PROVE to clients that their AI system is working properly, answering questions the right way, NOT answering questions the wrong way, and that any advanced functionality (lookups, appointments, etc.) works properly. Key Features: Multi-Project Management: Simplifies the QA process across a diverse project portfolio, ideal for agencies handling multiple clients. Custom Test Management: Easily create, organize, and track test cases tailored to your project. Run Test Batches: Group and execute test cases efficiently to keep your workflow smooth and organized. Actionable Insights: Get analysis and suggestions that help you fix issues early and improve your releases. Client-Friendly Reporting: Provides clear, detailed reports that make it easy to share progress and results with stakeholders. Developer Tools: Easily manage (receive, email, view, listen, notify) your Transcripts from other systems (VAPI, Retell, etc) without having to create Zapier or Make automations with the provided Webhook URL. More dev tools coming soon, let us know what would make your life easier! I’m launching today and would love to get feedback from this awesome community! If you’re into QA, software development, or just love testing tools, give it a look and let me know what you think. I'll add $20 in credits to your new account so you can try it out risk free, no credit cards required. Here’s the link: Testzilla.ai Looking forward to hearing your thoughts! Cheers, Brian Gallagher

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

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

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

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

[D] Misuse of Deep Learning in Nature Journal’s Earthquake Aftershock Paper

Recently, I saw a post by Rajiv Shah, Chicago-based data-scientist, regarding an article published in Nature last year called Deep learning of aftershock patterns following large earthquakes, written by scientists at Harvard in collaboration with Google. Below is the article: Stand Up for Best Practices: Misuse of Deep Learning in Nature’s Earthquake Aftershock Paper The Dangers of Machine Learning Hype Practitioners of AI, machine learning, predictive modeling, and data science have grown enormously over the last few years. What was once a niche field defined by its blend of knowledge is becoming a rapidly growing profession. As the excitement around AI continues to grow, the new wave of ML augmentation, automation, and GUI tools will lead to even more growth in the number of people trying to build predictive models. But here’s the rub: While it becomes easier to use the tools of predictive modeling, predictive modeling knowledge is not yet a widespread commodity. Errors can be counterintuitive and subtle, and they can easily lead you to the wrong conclusions if you’re not careful. I’m a data scientist who works with dozens of expert data science teams for a living. In my day job, I see these teams striving to build high-quality models. The best teams work together to review their models to detect problems. There are many hard-to-detect-ways that lead to problematic models (say, by allowing target leakage into their training data). Identifying issues is not fun. This requires admitting that exciting results are “too good to be true” or that their methods were not the right approach. In other words, it’s less about the sexy data science hype that gets headlines and more about a rigorous scientific discipline. Bad Methods Create Bad Results Almost a year ago, I read an article in Nature that claimed unprecedented accuracy in predicting earthquake aftershocks by using deep learning. Reading the article, my internal radar became deeply suspicious of their results. Their methods simply didn’t carry many of the hallmarks of careful predicting modeling. I started to dig deeper. In the meantime, this article blew up and became widely recognized! It was even included in the release notes for Tensorflow as an example of what deep learning could do. However, in my digging, I found major flaws in the paper. Namely, data leakage which leads to unrealistic accuracy scores and a lack of attention to model selection (you don’t build a 6 layer neural network when a simpler model provides the same level of accuracy). To my earlier point: these are subtle, but incredibly basic predictive modeling errors that can invalidate the entire results of an experiment. Data scientists are trained to recognize and avoid these issues in their work. I assumed that this was simply overlooked by the author, so I contacted her and let her know so that she could improve her analysis. Although we had previously communicated, she did not respond to my email over concerns with the paper. Falling On Deaf Ears So, what was I to do? My coworkers told me to just tweet it and let it go, but I wanted to stand up for good modeling practices. I thought reason and best practices would prevail, so I started a 6-month process of writing up my results and shared them with Nature. Upon sharing my results, I received a note from Nature in January 2019 that despite serious concerns about data leakage and model selection that invalidate their experiment, they saw no need to correct the errors, because “Devries et al. are concerned primarily with using machine learning as [a] tool to extract insight into the natural world, and not with details of the algorithm design.” The authors provided a much harsher response. You can read the entire exchange on my github. It’s not enough to say that I was disappointed. This was a major paper (it’s Nature!) that bought into AI hype and published a paper despite it using flawed methods. Then, just this week, I ran across articles by Arnaud Mignan and Marco Broccardo on shortcomings that they found in the aftershocks article. Here are two more data scientists with expertise in earthquake analysis who also noticed flaws in the paper. I also have placed my analysis and reproducible code on github. Standing Up For Predictive Modeling Methods I want to make it clear: my goal is not to villainize the authors of the aftershocks paper. I don’t believe that they were malicious, and I think that they would argue their goal was to just show how machine learning could be applied to aftershocks. Devries is an accomplished earthquake scientist who wanted to use the latest methods for her field of study and found exciting results from it. But here’s the problem: their insights and results were based on fundamentally flawed methods. It’s not enough to say, “This isn’t a machine learning paper, it’s an earthquake paper.” If you use predictive modeling, then the quality of your results are determined by the quality of your modeling. Your work becomes data science work, and you are on the hook for your scientific rigor. There is a huge appetite for papers that use the latest technologies and approaches. It becomes very difficult to push back on these papers. But if we allow papers or projects with fundamental issues to advance, it hurts all of us. It undermines the field of predictive modeling. Please push back on bad data science. Report bad findings to papers. And if they don’t take action, go to twitter, post about it, share your results and make noise. This type of collective action worked to raise awareness of p-values and combat the epidemic of p-hacking. We need good machine learning practices if we want our field to continue to grow and maintain credibility. Link to Rajiv's Article Original Nature Publication (note: paywalled) GitHub repo contains an attempt to reproduce Nature's paper Confrontational correspondence with authors

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

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

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

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

[N] Netflix and European Space Agency no longer working with Siraj Raval

According to article in The Register: A Netflix spokesperson confirmed to The Register it wasn’t working with Raval, and the ESA has cancelled the whole workshop altogether. “The situation is as it is. The workshop is cancelled, and that’s all,” Guillaume Belanger, an astrophysicist and the INTEGRAL Science Operations Coordinator at the ESA, told The Register on Monday. Raval isn’t about to quit his work any time soon, however. He promised students who graduated from his course that they would be referred to recruiters at Nvidia, Intel, Google and Amazon for engineering positions, or matched with a startup co-founder or a consulting client. In an unlisted YouTube video recorded live for his students discussing week eight of his course, and seen by El Reg, he read out a question posed to him: “Will your referrals hold any value now?” “Um, yeah they’re going to hold value. I don’t see why they wouldn’t. I mean, yes, some people on Twitter were angry but that has nothing to do with… I mean… I’ve also had tons of support, you know. I’ve had tons of support from people, who, uh, you know, support me, who work at these companies. He continues to justify his actions: “Public figures called me in private to remind me that this happens. You know, people make mistakes. You just have to keep going. They’re basically just telling me to not to stop. Of course, you make mistakes but you just keep going,” he claimed. When The Register asked Raval for comment, he responded: I've hardly taken any time off to relax since I first started my YouTube channel almost four years ago. And despite the enormous amount of work it takes to release two high quality videos a week for my audience, I progressively started to take on multiple other projects simultaneously by myself – a book, a docu-series, podcasts, YouTube videos, the course, the school of AI. Basically, these past few weeks, I've been experiencing a burnout unlike anything I've felt before. As a result, all of my output has been subpar. I made the [neural qubits] video and paper in one week. I remember wishing I had three to six months to really dive into quantum machine-learning and make something awesome, but telling myself I couldn't take that long as it would hinder my other projects. I plagiarized large chunks of the paper to meet my self-imposed one-week deadline. The associated video with animations took a lot more work to make. I didn't expect the paper to be cited as serious research, I considered it an additional reading resource for people who enjoyed the associated video to learn more about quantum machine learning. If I had a second chance, I'd definitely take way more time to write the paper, and in my own words. I've given refunds to every student who's asked so far, and the majority of students are still enrolled in the course. There are many happy students, they're just not as vocal on social media. We're on week 8 of 10 of my course, fully committed to student success. “And, no, I haven't plagiarized research for any other paper,” he added. https://www.theregister.co.uk/2019/10/14/ravelaiyoutube/

[R] Analysis of 400+ ML competitions in 2024

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

[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?

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

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

[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] Yoshua Bengio's latest letter addressing arguments against taking AI safety seriously

https://yoshuabengio.org/2024/07/09/reasoning-through-arguments-against-taking-ai-safety-seriously/ Summary by GPT-4o: "Reasoning through arguments against taking AI safety seriously" by Yoshua Bengio: Summary Introduction Bengio reflects on his year of advocating for AI safety, learning through debates, and synthesizing global expert views in the International Scientific Report on AI safety. He revisits arguments against AI safety concerns and shares his evolved perspective on the potential catastrophic risks of AGI and ASI. Headings and Summary The Importance of AI Safety Despite differing views, there is a consensus on the need to address risks associated with AGI and ASI. The main concern is the unknown moral and behavioral control over such entities. Arguments Dismissing AGI/ASI Risks Skeptics argue AGI/ASI is either impossible or too far in the future to worry about now. Bengio refutes this, stating we cannot be certain about the timeline and need to prepare regulatory frameworks proactively. For those who think AGI and ASI are impossible or far in the future He challenges the idea that current AI capabilities are far from human-level intelligence, citing historical underestimations of AI advancements. The trend of AI capabilities suggests we might reach AGI/ASI sooner than expected. For those who think AGI is possible but only in many decades Regulatory and safety measures need time to develop, necessitating action now despite uncertainties about AGI’s timeline. For those who think that we may reach AGI but not ASI Bengio argues that even AGI presents significant risks and could quickly lead to ASI, making it crucial to address these dangers. For those who think that AGI and ASI will be kind to us He counters the optimism that AGI/ASI will align with human goals, emphasizing the need for robust control mechanisms to prevent AI from pursuing harmful objectives. For those who think that corporations will only design well-behaving AIs and existing laws are sufficient Profit motives often conflict with safety, and existing laws may not adequately address AI-specific risks and loopholes. For those who think that we should accelerate AI capabilities research and not delay benefits of AGI Bengio warns against prioritizing short-term benefits over long-term risks, advocating for a balanced approach that includes safety research. For those concerned that talking about catastrophic risks will hurt efforts to mitigate short-term human-rights issues with AI Addressing both short-term and long-term AI risks can be complementary, and ignoring catastrophic risks would be irresponsible given their potential impact. For those concerned with the US-China cold war AI development should consider global risks and seek collaborative safety research to prevent catastrophic mistakes that transcend national borders. For those who think that international treaties will not work While challenging, international treaties on AI safety are essential and feasible, especially with mechanisms like hardware-enabled governance. For those who think the genie is out of the bottle and we should just let go and avoid regulation Despite AI's unstoppable progress, regulation and safety measures are still critical to steer AI development towards positive outcomes. For those who think that open-source AGI code and weights are the solution Open-sourcing AI has benefits but also significant risks, requiring careful consideration and governance to prevent misuse and loss of control. For those who think worrying about AGI is falling for Pascal’s wager Bengio argues that AI risks are substantial and non-negligible, warranting serious attention and proactive mitigation efforts. Conclusion Bengio emphasizes the need for a collective, cautious approach to AI development, balancing the pursuit of benefits with rigorous safety measures to prevent catastrophic outcomes.

[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.”

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

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

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

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

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

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

[Discussion]: Mark Zuckerberg on Meta's Strategy on Open Source and AI during the earnings call

During the recent earnings call, Mark Zuckerberg answered a question from Eric Sheridan of Goldman Sachs on Meta's AI strategy, opportunities to integrate into products, and why they open source models and how it would benefit their business. I found the reasoning to be very sound and promising for the OSS and AI community. The biggest risk from AI, in my opinion, is not the doomsday scenarios that intuitively come to mind but rather that the most powerful AI systems will only be accessible to the most powerful and resourceful corporations. Quote copied from Ben Thompson's write up on Meta's earning in his Stratechery blog post which goes beyond AI. It's behind a paywall but I highly recommend it personally. Some noteworthy quotes that signal the thought process at Meta FAIR and more broadly We’re just playing a different game on the infrastructure than companies like Google or Microsoft or Amazon We would aspire to and hope to make even more open than that. So, we’ll need to figure out a way to do that. ...lead us to do more work in terms of open sourcing, some of the lower level models and tools Open sourcing low level tools make the way we run all this infrastructure more efficient over time. On PyTorch: It’s generally been very valuable for us to provide that because now all of the best developers across the industry are using tools that we’re also using internally. I would expect us to be pushing and helping to build out an open ecosystem. For all the negative that comes out of the popular discourse on Meta, I think their work to open source key tech tools over the last 10 years has been exceptional, here's hoping it continues into this decade of AI and pushes other tech giants to also realize the benefits of Open Source. Full Transcript: Right now most of the companies that are training large language models have business models that lead them to a closed approach to development. I think there’s an important opportunity to help create an open ecosystem. If we can help be a part of this, then much of the industry will standardize on using these open tools and help improve them further. So this will make it easier for other companies to integrate with our products and platforms as we enable more integrations, and that will help our products stay at the leading edge as well. Our approach to AI and our infrastructure has always been fairly open. We open source many of our state of the art models so people can experiment and build with them. This quarter we released our LLaMa LLM to researchers. It has 65 billion parameters but outperforms larger models and has proven quite popular. We’ve also open-sourced three other groundbreaking visual models along with their training data and model weights — Segment Anything, DinoV2, and our Animated Drawings tool — and we’ve gotten positive feedback on all of those as well. I think that there’s an important distinction between the products we offer and a lot of the technical infrastructure, especially the software that we write to support that. And historically, whether it’s the Open Compute project that we’ve done or just open sourcing a lot of the infrastructure that we’ve built, we’ve historically open sourced a lot of that infrastructure, even though we haven’t open sourced the code for our core products or anything like that. And the reason why I think why we do this is that unlike some of the other companies in the space, we’re not selling a cloud computing service where we try to keep the different software infrastructure that we’re building proprietary. For us, it’s way better if the industry standardizes on the basic tools that we’re using and therefore we can benefit from the improvements that others make and others’ use of those tools can, in some cases like Open Compute, drive down the costs of those things which make our business more efficient too. So I think to some degree we’re just playing a different game on the infrastructure than companies like Google or Microsoft or Amazon, and that creates different incentives for us. So overall, I think that that’s going to lead us to do more work in terms of open sourcing, some of the lower level models and tools. But of course, a lot of the product work itself is going to be specific and integrated with the things that we do. So it’s not that everything we do is going to be open. Obviously, a bunch of this needs to be developed in a way that creates unique value for our products, but I think in terms of the basic models, I would expect us to be pushing and helping to build out an open ecosystem here, which I think is something that’s going to be important. On the AI tools, and we have a bunch of history here, right? So if you if you look at what we’ve done with PyTorch, for example, which has generally become the standard in the industry as a tool that a lot of folks who are building AI models and different things in that space use, it’s generally been very valuable for us to provide that because now all of the best developers across the industry are using tools that we’re also using internally. So the tool chain is the same. So when they create some innovation, we can easily integrate it into the things that we’re doing. When we improve something, it improves other products too. Because it’s integrated with our technology stack, when there are opportunities to make integrations with products, it’s much easier to make sure that developers and other folks are compatible with the things that we need in the way that our systems work. So there are a lot of advantages, but I view this more as a kind of back end infrastructure advantage with potential integrations on the product side, but one that should hopefully enable us to stay at the leading edge and integrate more broadly with the community and also make the way we run all this infrastructure more efficient over time. There are a number of models. I just gave PyTorch as an example. Open Compute is another model that has worked really well for us in this way, both to incorporate both innovation and scale efficiency into our own infrastructure. So I think that there’s, our incentives I think are basically aligned towards moving in this direction. Now that said, there’s a lot to figure out, right? So when you asked if there are going to be other opportunities, I hope so. I can’t speak to what all those things might be now. This is all quite early in getting developed. The better we do at the foundational work, the more opportunities I think that will come and present themselves. So I think that that’s all stuff that we need to figure out. But at least at the base level, I think we’re generally incentivized to move in this direction. And we also need to figure out how to go in that direction over time. I mean, I mentioned LLaMA before and I also want to be clear that while I’m talking about helping contribute to an open ecosystem, LLaMA is a model that we only really made available to researchers and there’s a lot of really good stuff that’s happening there. But a lot of the work that we’re doing, I think, we would aspire to and hope to make even more open than that. So, we’ll need to figure out a way to do that.

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

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

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

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

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

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

[D] "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?

[R] Reinforcement Learning for Sequential Decision and Optimal Control

Since early 21st century, artificial intelligence (AI) has been reshaping almost all areas of human society, which has high potential to spark the fourth industrial revolution. Notable examples can be found in the sector of road transportation, where AI has drastically changed automobile design and traffic management. Many new technologies, such as driver assistance, autonomous driving, and cloud-based cooperation, are emerging at an unbelievable speed. These new technologies have the potential to significantly improve driving ability, reduce traffic accidents, and relieve urban congestion. As one of the most important AI branches, reinforcement learning (RL) has attracted increasing attention in recent years. RL is an interdisciplinary field of trial-and-error learning and optimal control, which promises to provide optimal solutions for decision-making or control in large-scale and complex dynamic processes. One of its most conspicuous successes is AlphaGo from Google DeepMind, which has beaten the highest-level professional human player. The underlying key technology is the so-called deep reinforcement learning, which equips AlphaGo with amazing self-evolution ability and high playing intelligence. Despite a few successes, the application of RL is still in its infancy because most RL algorithms are rather difficult to comprehend and implement. RL connects deeply with statistical learning and convex optimization, and involves a wide range of new concepts and theories. As a beginner, one must undergo a long and tedious learning process to become an RL master. Without fully understanding those underlying principles, it is very difficult for new users to make proper adjustments to achieve the best application performance. &#x200B; https://preview.redd.it/tggt6o3o481c1.jpg?width=248&format=pjpg&auto=webp&s=75e2b58ac8da9273f2511a4fe37ef508d86a6e96 Reference： Shengbo Eben Li, Reinforcement Learning for Sequential Decision and Optimal Control. Springer Verlag, Singapore, 2023 Website of e-book: https://link.springer.com/book/10.1007/978-981-19-7784-8 &#x200B; QR code to Springer Book contents This book aims to provide a systematic introduction to fundamental RL theories, mainstream RL algorithms and typical RL applications for researchers and engineers. The main topics include Markov decision processes, Monte Carlo learning, temporal difference learning, RL with function approximation, policy gradient method, approximate dynamic programming, deep reinforcement learning, etc. Chapter 1 provides an overview of RL, including its history, famous scholars, successful examples and up-to-date challenges. Chapter 2 discusses the basis of RL, including main concepts and terminologies, Bellman’s optimality condition, and general problem formulation. Chapter 3 introduces Monte Carlo learning methods for model-free RL, including on-policy/off-policy methods and importance sampling technique. Chapter 4 introduces temporal difference learning methods for model-free RL, including Sarsa, Q-learning, and expected Sarsa. Chapter 5 introduces stochastic dynamic programming (DP), i.e., model-based RL with tabular representation, including value iteration DP, policy iteration DP and their convergence mechanisms. Chapter 6 introduces how to approximate policy and value functions in indirect RL methods as well as the associated actor-critic architecture. Chapter 7 derives different kinds of direct policy gradients, including likelihood ratio gradient, natural policy gradient and a few advanced variants. Chapter 8 introduces infinite-horizon ADP, finite-horizon ADP and its connection with model predictive control. Chapter 9 discusses how to handle state constraints and its connection with feasibility and safety, as well as the newly proposed actor-critic-scenery learning architecture. Chapter 10 is devoted to deep reinforcement learning, including how to train artificial neural networks and typical deep RL algorithms such as DQN, DDPG, TD3, TRPO, PPO, SAC, and DSAC. Chapter 11 provides various RL topics,including robust RL, POMDP, multi-agent RL, meta-RL, inverse RL, offline RL, major RL libraries and platforms. Author information: Shengbo Eben Li is currently a professor at Tsinghua University in the interdisciplinary field of autonomous driving and artificial intelligence. Before joining Tsinghua University, he has worked at Stanford University, University of Michigan, and UC Berkeley. His active research interests include intelligent vehicles and driver assistance, deep reinforcement learning, optimal control and estimation, etc. He has published more than 130 peer-reviewed papers in top-tier international journals and conferences. He is the recipient of best paper awards (finalists) of IEEE ITSC, ICCAS, IEEE ICUS, IEEE IV, L4DC, etc. He has received a number of important academic honors, including National Award for Technological Invention of China (2013), National Award for Progress in Sci & Tech of China (2018), Distinguished Young Scholar of Beijing NSF (2018), Youth Sci & Tech Innovation Leader from MOST China (2020), etc. He also serves as Board of Governor of IEEE ITS Society, Senior AE of IEEE OJ ITS, and AEs of IEEE ITSM, IEEE Trans ITS, Automotive Innovation, etc.

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

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

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

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

[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] The machine learning community has a toxicity problem

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

[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] Jarvislabs.ai - An Affordable GPU Cloud with Fast launch, Pause and Resume. Scale GPUs post creation. A100/RTX6K/RTX5K

For the last few years, I have been learning and practicing Deep Learning. Participated in several Kaggle competitions and won few medals. During all these years, I tried several cloud platforms and on-premise systems. Some of them offered simplicity, flexibility, and affordability. But very few to none offered all of these in one platform. After struggling with different platforms, I know what I would need as a DL researcher. That gave birth to jarvislabs.ai with the aim of being simple and affordable. I along with my friends started working on this project a year back. Due to Covid, executing the project became more challenging. As first-time entrepreneurs, we underestimated the complexity of the problem at hand but with persistence, we were able to launch a beta version of the product in December 2020. With some of the amazing feedback from our early adopters, we have been able to make the product smoother. We would love to invite you all to come and try the platform. Features 1 click Jupyter Lab < \[30 seconds\] Pause the instance and Resume from where you left. SSH to the instance. Scale GPUs, storage and change GPU type on resume. Auto-Pause using jarviscloud.pause() in your code, so you can catch up some good night’s sleep while your model trains. Pay per usage – Minute Billing \[After first 15 minutes\] Competitive pricing \[Lowest to our Knowledge\]. &#x200B; Pricing |GPU Type|GPU RAM|Price -$/hr| |:-|:-|:-| |RTX 5000|16 GB|0.49| |RTX 6000|24 GB|0.99| |A100|40 GB|2.39| &#x200B; Talk to us We will be happy to assist you in spinning your first instance and many more. You can use one of these platforms to reach us. Chat option on cloud.jarvislabs.ai Email us - hello@jarvislabs.ai Comment here. We have come a long way, but we understand that a lot more has to be done. We have listed down all the upcoming product features here. Deep learning and AI are evolving and how we would use the cloud platforms could evolve in the coming years. Understanding this, we develop in the open by constantly keeping in touch with our users. Please help us in shaping Jarvislabs.ai with any valuable suggestions/feedback.

[D] Should the praise of "Data-centric" AI be taken with a grain of salt?

I hear co-workers, professors, entrepreneurs talk about just how important it is to switch from model-centric AI to a data-centric approach. Personally I don't see a problem focusing on attaining better data but I have been seeing this simplification that AI performance = model + data which seems massively misleading. A better generalization would be AI performance = model data or even AI performance = model log(len(data)). Looking at the rapidly changing problem of image synthesis, it is clear that data alone could not produce the same results seen even two years ago. On the other hand, it can seem unproductive for the field as a whole to try to create another classification model that achieves a .02% increased performance on ImageNet... again and again... And this is maybe why we hear more talk in industry about focusing on the data instead of models: Industry generally faces simpler tasks with negligible improvement as of recently (regression, classification). Therefore it's more easy and valuable to increase and improve the training data. And yes, most machine learning models NEED a large training set to approximate a complex distribution. We have already known this since forever. I think the term has just recently become a pet peeve for me as a novel "catch all" solution to any problem. What are your opinions on the matter?

[D] Gary Marcus and Luis Lamb -- discussion of AGI and Neurosymbolic methods

https://youtu.be/nhUt6mKCPf8 Pod: https://anchor.fm/machinelearningstreettalk/episodes/54-Gary-Marcus-and-Luis-Lamb---Neurosymbolic-models-e125495 Professor Gary Marcus is a scientist, best-selling author, and entrepreneur. He is Founder and CEO of Robust.AI, and was Founder and CEO of Geometric Intelligence, a machine learning company acquired by Uber in 2016. Gary said in his recent next decade paper that — without us, or other creatures like us, the world would continue to exist, but it would not be described, distilled, or understood. Human lives are filled with abstraction and causal description. This is so powerful. Francois Chollet the other week said that intelligence is literally sensitivity to abstract analogies, and that is all there is to it. It's almost as if one of the most important features of intelligence is to be able to abstract knowledge, this drives the generalisation which will allow you to mine previous experience to make sense of many future novel situations. Also joining us today is Professor Luis Lamb — Secretary of Innovation for Science and Technology of the State of Rio Grande do Sul, Brazil. His Research Interests are Machine Learning and Reasoning, Neuro-Symbolic Computing, Logic in Computation and Artificial Intelligence, Cognitive and Neural Computation and also AI Ethics and Social Computing. Luis released his new paper Neurosymbolic AI: the third wave at the end of last year. It beautifully articulated the key ingredients needed in the next generation of AI systems, integrating type 1 and type 2 approaches to AI and it summarises all the of the achievements of the last 20 years of research. We cover a lot of ground in today's show. Explaining the limitations of deep learning, Rich Sutton's the bitter lesson and "reward is enough", and the semantic foundation which is required for us to build robust AI.

[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.

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

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

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

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

[D] Is the Covid-19 crisis the rock on which the ML hype wave finally crashes?

People have been predicting the end of the ML Hype for a while, but it didn't seem to go away. Andrew Ng's "A.I. is the new electricity" statement looked like it was true, and the number of ML related stuff on resumes, job descriptions and software requirements, not to mention startups, seemed to keep increasing and increasing, and increasing.... Then came a virus, with a billion years of optimization and search efficiency baked into its RNA. Some considerations: Despite all the hype, production grade ML was still a challenge for most companies outside of the big tech shops and some talented startups. With the Covid-19 induced economic meltdown, most companies don't have the money or the resources to fund the projects required to take ML from PoC/Jupyter Notebook status to value generating production applications. Most of the startups that are building ML productionizing tools and platforms will run out of funds, clients, or both. Moreover, the current economic meltdown makes most historical data on business KPIs, Customer behavior, time series forecasting, etc...is no longer useful as training data. The only data sets that are still useful are those for "hard-core" ML problems like computer vision and NLP, for which completely automated APIs have been already developed and Auto-ML works pretty well, so no real ML talent is needed in deploying them. All of this tells me that Q2 2020 will mark the end of the ML and Deep Learning hype, and besides a likely multi-year economic depression in the U.S., we are also headed into another AI winter. I'm not happy about the ML hype dying, it has helped me a lot in my career, and I really really love Deep Learning from a purely conceptual point of view. But one needs to be realistic in such a job market, should we all start reframing our skill sets and our resumes? I'm kind of hoping somebody will prove my above reasoning wrong.

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

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

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

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

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

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

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

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

[N] 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.

[P] I built an open SotA image tagging model to do what CLIP won't

I'm a hobbyist ML researcher and finally, after a year of work, built a state of the art machine vision model from scratch. It's ViT-B/16 based, 448x448x3 input, 91M parameters, trained for 660M samples, with multi-label classification as the target task, on over 5000 unique tags. All the big foundation vision models today were trained on heavily filtered datasets, greatly limiting the concepts they can represent, in line with arbitrary sets of rules for what is deemed "wholesome" by leading tech companies. Everything from innocuous to spicy is on the chopping block of those filters. And because CLIP pervades the industry, from StableDiffusion to LLaVA, so does OpenAI's sensibilities. My goal was to build a vision model for tagging images, mainly for labelling images for SD finetunes, but which wasn't as heavily filtered and handicapped as CLIP/BLIP/LLaVA. Something more inclusive, diverse, and sex positive. Starting from the wonderful work of SmilingWolf (https://github.com/SmilingWolf/SW-CV-ModelZoo) and the Danbooru2021 dataset, I iterated for a year on the model, training, and manually labeling a thousand images to help the model generalize beyond the danbooru domain. I'm releasing the first version of this model, dubbed JoyTag, today: https://github.com/fpgaminer/joytag It achieves a mean F1 score of 0.578 across all of its over 5000 tags and across both the anime/manga styled images of the original danbooru dataset, but also photographs and other mediums thanks to the auxiliary training data I provided to it. It was quite the struggle getting to this point, and I probably spent more time and money than any sane person should have. I learned a lot about dealing with datasets as large as danbooru2021, training models at scale, and how to keep yourself awake all night so your 8xA100 rental doesn't crash and blow all your money. In my manual testing outside of even the validation set, the model has generalized well to unseen images, so I'm quite happy with the results thus far. There's plenty more work to do expanding its dataset to improve that F1 score further, and roundout its weak points. With inclusivity and diversity being a major goal of this project, I'm disappointed by some of its remaining limitations (as documented in the GitHub README). But I'm already busy manually tagging more images using my model-augmented workflow. I'm happy to answer questions about the project, the training procedure, anything. All the training parameters are documented on GitHub, but there are so many little details that were hard won over the year. Like that damned loss multiplier. Ugh. Github: https://github.com/fpgaminer/joytag Model download: https://huggingface.co/fancyfeast/joytag/tree/main Demo: https://huggingface.co/spaces/fancyfeast/joytag

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

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

[D]Why isn't Hugging Face becoming one of the promising (and young) AI chatbot players on the table (like Mistral AI, Anthropic, Perplexity AI, etc)

I rememebered a few years ago people discussing about what HF's business model is or how to profit. I think now is the best time for them, but yet i am a bit suprised they didn't make their own one. They have talents, experiences, resources. Just wonder it.

[D] How Facebook got addicted to spreading misinformation

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

[Discussion]: Mark Zuckerberg on Meta's Strategy on Open Source and AI during the earnings call

During the recent earnings call, Mark Zuckerberg answered a question from Eric Sheridan of Goldman Sachs on Meta's AI strategy, opportunities to integrate into products, and why they open source models and how it would benefit their business. I found the reasoning to be very sound and promising for the OSS and AI community. The biggest risk from AI, in my opinion, is not the doomsday scenarios that intuitively come to mind but rather that the most powerful AI systems will only be accessible to the most powerful and resourceful corporations. Quote copied from Ben Thompson's write up on Meta's earning in his Stratechery blog post which goes beyond AI. It's behind a paywall but I highly recommend it personally. Some noteworthy quotes that signal the thought process at Meta FAIR and more broadly We’re just playing a different game on the infrastructure than companies like Google or Microsoft or Amazon We would aspire to and hope to make even more open than that. So, we’ll need to figure out a way to do that. ...lead us to do more work in terms of open sourcing, some of the lower level models and tools Open sourcing low level tools make the way we run all this infrastructure more efficient over time. On PyTorch: It’s generally been very valuable for us to provide that because now all of the best developers across the industry are using tools that we’re also using internally. I would expect us to be pushing and helping to build out an open ecosystem. For all the negative that comes out of the popular discourse on Meta, I think their work to open source key tech tools over the last 10 years has been exceptional, here's hoping it continues into this decade of AI and pushes other tech giants to also realize the benefits of Open Source. Full Transcript: Right now most of the companies that are training large language models have business models that lead them to a closed approach to development. I think there’s an important opportunity to help create an open ecosystem. If we can help be a part of this, then much of the industry will standardize on using these open tools and help improve them further. So this will make it easier for other companies to integrate with our products and platforms as we enable more integrations, and that will help our products stay at the leading edge as well. Our approach to AI and our infrastructure has always been fairly open. We open source many of our state of the art models so people can experiment and build with them. This quarter we released our LLaMa LLM to researchers. It has 65 billion parameters but outperforms larger models and has proven quite popular. We’ve also open-sourced three other groundbreaking visual models along with their training data and model weights — Segment Anything, DinoV2, and our Animated Drawings tool — and we’ve gotten positive feedback on all of those as well. I think that there’s an important distinction between the products we offer and a lot of the technical infrastructure, especially the software that we write to support that. And historically, whether it’s the Open Compute project that we’ve done or just open sourcing a lot of the infrastructure that we’ve built, we’ve historically open sourced a lot of that infrastructure, even though we haven’t open sourced the code for our core products or anything like that. And the reason why I think why we do this is that unlike some of the other companies in the space, we’re not selling a cloud computing service where we try to keep the different software infrastructure that we’re building proprietary. For us, it’s way better if the industry standardizes on the basic tools that we’re using and therefore we can benefit from the improvements that others make and others’ use of those tools can, in some cases like Open Compute, drive down the costs of those things which make our business more efficient too. So I think to some degree we’re just playing a different game on the infrastructure than companies like Google or Microsoft or Amazon, and that creates different incentives for us. So overall, I think that that’s going to lead us to do more work in terms of open sourcing, some of the lower level models and tools. But of course, a lot of the product work itself is going to be specific and integrated with the things that we do. So it’s not that everything we do is going to be open. Obviously, a bunch of this needs to be developed in a way that creates unique value for our products, but I think in terms of the basic models, I would expect us to be pushing and helping to build out an open ecosystem here, which I think is something that’s going to be important. On the AI tools, and we have a bunch of history here, right? So if you if you look at what we’ve done with PyTorch, for example, which has generally become the standard in the industry as a tool that a lot of folks who are building AI models and different things in that space use, it’s generally been very valuable for us to provide that because now all of the best developers across the industry are using tools that we’re also using internally. So the tool chain is the same. So when they create some innovation, we can easily integrate it into the things that we’re doing. When we improve something, it improves other products too. Because it’s integrated with our technology stack, when there are opportunities to make integrations with products, it’s much easier to make sure that developers and other folks are compatible with the things that we need in the way that our systems work. So there are a lot of advantages, but I view this more as a kind of back end infrastructure advantage with potential integrations on the product side, but one that should hopefully enable us to stay at the leading edge and integrate more broadly with the community and also make the way we run all this infrastructure more efficient over time. There are a number of models. I just gave PyTorch as an example. Open Compute is another model that has worked really well for us in this way, both to incorporate both innovation and scale efficiency into our own infrastructure. So I think that there’s, our incentives I think are basically aligned towards moving in this direction. Now that said, there’s a lot to figure out, right? So when you asked if there are going to be other opportunities, I hope so. I can’t speak to what all those things might be now. This is all quite early in getting developed. The better we do at the foundational work, the more opportunities I think that will come and present themselves. So I think that that’s all stuff that we need to figure out. But at least at the base level, I think we’re generally incentivized to move in this direction. And we also need to figure out how to go in that direction over time. I mean, I mentioned LLaMA before and I also want to be clear that while I’m talking about helping contribute to an open ecosystem, LLaMA is a model that we only really made available to researchers and there’s a lot of really good stuff that’s happening there. But a lot of the work that we’re doing, I think, we would aspire to and hope to make even more open than that. So, we’ll need to figure out a way to do that.

[D] A Jobless Rant - ML is a Fool's Gold

Aside from the clickbait title, I am earnestly looking for some advice and discussion from people who are actually employed. That being said, here's my gripe: I have been relentlessly inundated by the words "AI, ML, Big Data" throughout my undergrad from other CS majors, business and sales oriented people, media, and .ai type startups. It seems like everyone was peddling ML as the go to solution, the big money earner, and the future of the field. I've heard college freshman ask stuff like, "if I want to do CS, am I going to need to learn ML to be relevant" - if you're on this sub, I probably do not need to continue to elaborate on just how ridiculous the ML craze is. Every single university has opened up ML departments or programs and are pumping out ML graduates at an unprecedented rate. Surely, there'd be a job market to meet the incredible supply of graduates and cultural interest? Swept up in a mixture of genuine interest and hype, I decided to pursue computer vision. I majored in Math-CS at a top-10 CS university (based on at least one arbitrary ranking). I had three computer vision internships, two at startups, one at NASA JPL, in each doing non-trivial CV work; I (re)implemented and integrated CV systems from mixtures of recently published papers. I have a bunch of projects showing both CV and CS fundamentals (OS, networking, data structures, algorithms, etc) knowledge. I have taken graduate level ML coursework. I was accepted to Carnegie Mellon for an MS in Computer Vision, but I deferred to 2021 - all in all, I worked my ass off to try to simultaneously get a solid background in math AND computer science AND computer vision. That brings me to where I am now, which is unemployed and looking for jobs. Almost every single position I have seen requires a PhD and/or 5+ years of experience, and whatever I have applied for has ghosted me so far. The notion that ML is a high paying in-demand field seems to only be true if your name is Andrej Karpathy - and I'm only sort of joking. It seems like unless you have a PhD from one of the big 4 in CS and multiple publications in top tier journals you're out of luck, or at least vying for one of the few remaining positions at small companies. This seems normalized in ML, but this is not the case for quite literally every other subfield or even generalized CS positions. Getting a high paying job at a Big N company is possible as a new grad with just a bachelors and general SWE knowledge, and there are a plethora of positions elsewhere. Getting the equivalent with basically every specialization, whether operating systems, distributed systems, security, networking, etc, is also possible, and doesn't require 5 CVPR publications. TL;DR From my personal perspective, if you want to do ML because of career prospects, salaries, or job security, pick almost any other CS specialization. In ML, you'll find yourself working 2x as hard through difficult theory and math to find yourself competing with more applicants for fewer positions. I am absolutely complaining and would love to hear a more positive perspective, but in the meanwhile I'll be applying to jobs, working on more post-grad projects, and contemplating switching fields.

[N] Montreal-based Element AI sold for $230-million as founders saw value mostly wiped out

According to Globe and Mail article: Element AI sold for $230-million as founders saw value mostly wiped out, document reveals Montreal startup Element AI Inc. was running out of money and options when it inked a deal last month to sell itself for US$230-milion to Silicon Valley software company ServiceNow Inc., a confidential document obtained by the Globe and Mail reveals. Materials sent to Element AI shareholders Friday reveal that while many of its institutional shareholders will make most if not all of their money back from backing two venture financings, employees will not fare nearly as well. Many have been terminated and had their stock options cancelled. Also losing out are co-founders Jean-François Gagné, the CEO, his wife Anne Martel, the chief administrative officer, chief science officer Nick Chapados and Yoshua Bengio, the University of Montreal professor known as a godfather of “deep learning,” the foundational science behind today’s AI revolution. Between them, they owned 8.8 million common shares, whose value has been wiped out with the takeover, which goes to a shareholder vote Dec 29 with enough investor support already locked up to pass before the takeover goes to a Canadian court to approve a plan of arrangement with ServiceNow. The quartet also owns preferred shares worth less than US$300,000 combined under the terms of the deal. The shareholder document, a management proxy circular, provides a rare look inside efforts by a highly hyped but deeply troubled startup as it struggled to secure financing at the same time as it was failing to live up to its early promises. The circular states the US$230-million purchase price is subject to some adjustments and expenses which could bring the final price down to US$195-million. The sale is a disappointing outcome for a company that burst onto the Canadian tech scene four years ago like few others, promising to deliver AI-powered operational improvements to a range of industries and anchor a thriving domestic AI sector. Element AI became the self-appointed representative of Canada’s AI sector, lobbying politicians and officials and landing numerous photo ops with them, including Prime Minister Justin Trudeau. It also secured $25-million in federal funding – $20-million of which was committed earlier this year and cancelled by the government with the ServiceNow takeover. Element AI invested heavily in hype and and earned international renown, largely due to its association with Dr. Bengio. It raised US$102-million in venture capital in 2017 just nine months after its founding, an unheard of amount for a new Canadian company, from international backers including Microsoft Corp., Intel Corp., Nvidia Corp., Tencent Holdings Ltd., Fidelity Investments, a Singaporean sovereign wealth fund and venture capital firms. Element AI went on a hiring spree to establish what the founders called “supercredibility,” recruiting top AI talent in Canada and abroad. It opened global offices, including a British operation that did pro bono work to deliver “AI for good,” and its ranks swelled to 500 people. But the swift hiring and attention-seeking were at odds with its success in actually building a software business. Element AI took two years to focus on product development after initially pursuing consulting gigs. It came into 2019 with a plan to bring several AI-based products to market, including a cybersecurity offering for financial institutions and a program to help port operators predict waiting times for truck drivers. It was also quietly shopping itself around. In December 2018, the company asked financial adviser Allen & Co LLC to find a potential buyer, in addition to pursuing a private placement, the circular reveals. But Element AI struggled to advance proofs-of-concept work to marketable products. Several client partnerships faltered in 2019 and 2020. Element did manage to reach terms for a US$151.4-million ($200-million) venture financing in September, 2019 led by the Caisse de dépôt et placement du Québec and backed by the Quebec government and consulting giant McKinsey and Co. However, the circular reveals the company only received the first tranche of the financing – roughly half of the amount – at the time, and that it had to meet unspecified conditions to get the rest. A fairness opinion by Deloitte commissioned as part of the sale process estimated Element AI’s enterprises value at just US$76-million around the time of the 2019 financing, shrinking to US$45-million this year. “However, the conditions precedent the closing of the second tranche … were not going to be met in a timely manner,” the circular reads. It states “new terms were proposed” for a round of financing that would give incoming investors ranking ahead of others and a cumulative dividend of 12 per cent on invested capital and impose “other operating and governance constraints and limitations on the company.” Management instead decided to pursue a sale, and Allen contacted prospective buyers in June. As talks narrowed this past summer to exclusive negotiations with ServiceNow, “the company’s liquidity was diminishing as sources of capital on acceptable terms were scarce,” the circular reads. By late November, it was generating revenue at an annualized rate of just $10-million to $12-million, Deloitte said. As part of the deal – which will see ServiceNow keep Element AI’s research scientists and patents and effectively abandon its business – the buyer has agreed to pay US$10-million to key employees and consultants including Mr. Gagne and Dr. Bengio as part of a retention plan. The Caisse and Quebec government will get US$35.45-million and US$11.8-million, respectively, roughly the amount they invested in the first tranche of the 2019 financing.

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

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

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

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

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

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

[D] Misuse of Deep Learning in Nature Journal’s Earthquake Aftershock Paper

Recently, I saw a post by Rajiv Shah, Chicago-based data-scientist, regarding an article published in Nature last year called Deep learning of aftershock patterns following large earthquakes, written by scientists at Harvard in collaboration with Google. Below is the article: Stand Up for Best Practices: Misuse of Deep Learning in Nature’s Earthquake Aftershock Paper The Dangers of Machine Learning Hype Practitioners of AI, machine learning, predictive modeling, and data science have grown enormously over the last few years. What was once a niche field defined by its blend of knowledge is becoming a rapidly growing profession. As the excitement around AI continues to grow, the new wave of ML augmentation, automation, and GUI tools will lead to even more growth in the number of people trying to build predictive models. But here’s the rub: While it becomes easier to use the tools of predictive modeling, predictive modeling knowledge is not yet a widespread commodity. Errors can be counterintuitive and subtle, and they can easily lead you to the wrong conclusions if you’re not careful. I’m a data scientist who works with dozens of expert data science teams for a living. In my day job, I see these teams striving to build high-quality models. The best teams work together to review their models to detect problems. There are many hard-to-detect-ways that lead to problematic models (say, by allowing target leakage into their training data). Identifying issues is not fun. This requires admitting that exciting results are “too good to be true” or that their methods were not the right approach. In other words, it’s less about the sexy data science hype that gets headlines and more about a rigorous scientific discipline. Bad Methods Create Bad Results Almost a year ago, I read an article in Nature that claimed unprecedented accuracy in predicting earthquake aftershocks by using deep learning. Reading the article, my internal radar became deeply suspicious of their results. Their methods simply didn’t carry many of the hallmarks of careful predicting modeling. I started to dig deeper. In the meantime, this article blew up and became widely recognized! It was even included in the release notes for Tensorflow as an example of what deep learning could do. However, in my digging, I found major flaws in the paper. Namely, data leakage which leads to unrealistic accuracy scores and a lack of attention to model selection (you don’t build a 6 layer neural network when a simpler model provides the same level of accuracy). To my earlier point: these are subtle, but incredibly basic predictive modeling errors that can invalidate the entire results of an experiment. Data scientists are trained to recognize and avoid these issues in their work. I assumed that this was simply overlooked by the author, so I contacted her and let her know so that she could improve her analysis. Although we had previously communicated, she did not respond to my email over concerns with the paper. Falling On Deaf Ears So, what was I to do? My coworkers told me to just tweet it and let it go, but I wanted to stand up for good modeling practices. I thought reason and best practices would prevail, so I started a 6-month process of writing up my results and shared them with Nature. Upon sharing my results, I received a note from Nature in January 2019 that despite serious concerns about data leakage and model selection that invalidate their experiment, they saw no need to correct the errors, because “Devries et al. are concerned primarily with using machine learning as [a] tool to extract insight into the natural world, and not with details of the algorithm design.” The authors provided a much harsher response. You can read the entire exchange on my github. It’s not enough to say that I was disappointed. This was a major paper (it’s Nature!) that bought into AI hype and published a paper despite it using flawed methods. Then, just this week, I ran across articles by Arnaud Mignan and Marco Broccardo on shortcomings that they found in the aftershocks article. Here are two more data scientists with expertise in earthquake analysis who also noticed flaws in the paper. I also have placed my analysis and reproducible code on github. Standing Up For Predictive Modeling Methods I want to make it clear: my goal is not to villainize the authors of the aftershocks paper. I don’t believe that they were malicious, and I think that they would argue their goal was to just show how machine learning could be applied to aftershocks. Devries is an accomplished earthquake scientist who wanted to use the latest methods for her field of study and found exciting results from it. But here’s the problem: their insights and results were based on fundamentally flawed methods. It’s not enough to say, “This isn’t a machine learning paper, it’s an earthquake paper.” If you use predictive modeling, then the quality of your results are determined by the quality of your modeling. Your work becomes data science work, and you are on the hook for your scientific rigor. There is a huge appetite for papers that use the latest technologies and approaches. It becomes very difficult to push back on these papers. But if we allow papers or projects with fundamental issues to advance, it hurts all of us. It undermines the field of predictive modeling. Please push back on bad data science. Report bad findings to papers. And if they don’t take action, go to twitter, post about it, share your results and make noise. This type of collective action worked to raise awareness of p-values and combat the epidemic of p-hacking. We need good machine learning practices if we want our field to continue to grow and maintain credibility. Link to Rajiv's Article Original Nature Publication (note: paywalled) GitHub repo contains an attempt to reproduce Nature's paper Confrontational correspondence with authors

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

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

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

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

[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

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.