Nathan Lambert says his RLHF book is finished after two years of nights and weekends
TheZachMueller · x · 2026-07-21
Nathan Lambert says his book Reinforcement Learning from Human Feedback is done.
He describes it as the resource he wished he had while learning to fine-tune, align, and now post-train models after ChatGPT. The book has been built over nights and weekends since 2024, and he says he tried to transfer as much of the intuition from building Olmo into book form as possible.
The post frames the book as a practical foundation for people working on RLHF and post-training rather than as a polished marketing launch.
Related event: Nat Lambert Completes RLHF Book with 10+ Hour Course(11 posts)→
More from Companies & People
- OpenAI Foundation funds UNC tumor antigen project, hiring senior experimental scientist — iskander · 2026-10-27
- Anthropic IPO timing fuels claims anti-open-weights panic is self-serving — mark_k · 2026-10-27
- PhD applicant emails up 4x YoY due to AI — writing without AI now makes you stand out — AI4Code · 2026-10-27
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- Anthropic S-1 reveals Dario can handpick a board majority forever via founder control — cocktailpeanut · 2026-10-27
- Mistral researcher: research freedom is overrated compared to company problems — konstmish · 2026-10-27