Using OSS models to build AI apps with millions of users
summary
Builds and launches dozens of tiny open‑source AI apps, several hitting millions: roomGPT.io 2.9M, restorePhotos.io 1.1M, Blinkshot.io 1M, LlamaCoder.io 1.4M. Uses a one‑API‑call architecture and a repeatable stack: TogetherAI for models, Next.js+TypeScript, Neon/Postgres, Clerk, Prisma, Vercel. Emphasizes simple UX, viral share loops, rapid launch/iterate cycles, free open‑source releases, and sponsorships/credits to cover compute; many apps succeed, some don’t, so volume and fast pivots decide outcomes.
AI-written summary · about
chapters (4)
related talks
17mOpen Innovation: Unlocking AI's Potential
20mTrue Exponential: Building a Generative AI Company
39mResponsible Applied AI at Scale
27mRevolutionizing API Strategy in the AI Era
36mImplementing AI for fun and profit
53mHow to Build and Scale Ultra-Lean Gen AI Startups
36mGenerative AI + Python: Unlocking Efficiency, Personalization, and Insight
54mThe Future of AI: Building the Most Impactful Technology Together