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.

Related event: Nathan Lambert Completes RLHF Book After Two Years with Courses and Code(8 posts)→

Original post →

More from Companies & People

Companies & People channel →