@danshipper: extremely cool and obviously the future
Summary
Felix Rieseberg created an app that teaches the fundamentals of building language models, making it easy and fun for anyone to build their own.
View Cached Full Text
Cached at: 07/22/26, 06:23 AM
extremely cool and obviously the future
Felix Rieseberg (@felixrieseberg): Have you built a language model? You should. It’s so much fun to chat with something you made.
Anyone can do it, too. I made an app that teaches the fundamentals and gives you everything you need to build your own:
Similar Articles
Felix Rieseberg (Anthropic, ElectronJS) has released a free Mac app designed to help people build their own LLMs from scratch.
Felix Rieseberg, known for his work at Anthropic and on ElectronJS, has released a free Mac app that allows users to build their own large language models from scratch.
@0xCodez: https://x.com/0xCodez/status/2058911661973454915
A detailed guide explaining the five-stage pipeline for building large language models, emphasizing that data quality and engineering matter more than architecture.
Bulding my own Diffusion Language Model from scratch was easier than I thought [P]
Developer shares a minimalist 7.5M-parameter diffusion language model trained from scratch on Shakespeare, releasing the code as a learning resource.
@omarsar0: This is awesome! I am spending a lot of time on diffusion LLMs these days, so this is perfect timing. I feel like there…
Google DeepMind released DiffusionGemma, an open experimental model that generates text in blocks rather than word-by-word, enabling self-correction and faster output.
@tuhinone: https://x.com/tuhinone/status/2054603346905080136
A perspective piece advocating for a future of specialized AI models developed by obsessive, customer-focused teams, highlighting companies like OpenEvidence, SchoolAI, Lovable, Harvey, Boltz, and Notion.