Nat Lambert says his RLHF book is finished after nights-and-weekends writing
deliprao · x · 2026-07-21
A new RLHF book from Nat Lambert is finished and headed for launch
The post says Nat Lambert has completed Reinforcement Learning from Human Feedback, a book he says he wished existed when he was learning to fine-tune, align, and post-train models after ChatGPT.
- He built it through nights and weekends starting in 2024.
- The book is meant to capture the intuitions behind fine-tuning, alignment, and post-training.
- He says it distills lessons from building Olmo into book form.
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