Nat Lambert says his RLHF book is finished after a year of nights and weekends
dejavucoder · x · 2026-07-21
Nat Lambert says his new book, Reinforcement Learning from Human Feedback, is finished.
- He describes it as the book he wished existed when he was learning to fine-tune, align, and post-train models after ChatGPT.
- The material has been assembled from his own experience building Olmo.
- He says the project was written on nights and weekends starting in 2024, with the goal of transferring practical intuitions into book form.
Related event: Nat Lambert Completes RLHF Book with 10+ Hour Course(11 posts)→
More from AGI Musings
- 'AGI is here' vs reality: AI labs still ship some of the jankiest desktop apps ever — MilesCranmer · 2026-09-11
- Harry Collins: LLMs can't do frontier science because they can't invent new language — whoamisri · 2026-09-11
- The Waymo effect: how AI is quietly making research less collaborative — JohnHammersley · 2026-09-11
- Misquoted: Anthropic Staff Warned of Double-Digit Extinction Risk by 2030, Not Dismissed It — davidmanheim · 2026-09-11
- Economist Ben Moll: You Can Model Anthropic's 15% AI GDP Growth, But It Won't Happen — sebkrier · 2026-09-11
- Cohere Labs launches interactive tool mapping which tasks of 178 occupations AI can automate — Cohere_Labs · 2026-09-11