A new RLHF book is finished after nights and weekends since 2024
HamelHusain · x · 2026-07-21
@natolambert says his book Reinforcement Learning from Human Feedback is finished. He describes it as the book he wished he had while learning to fine-tune, align, and post-train models after ChatGPT, and says it distills fundamentals he learned while building Olmo on nights and weekends since 2024.
Related event: Nat Lambert Completes RLHF Book with 10+ Hour Course(11 posts)→
More from Research
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Finch 1: a geospatial foundation model trained on imagery from 50+ sensors — Scobleizer · 2026-10-27
- Skyfall AI's SKY-001 world model turns sketches into CAD builds in 3.9s, vs 199s for GPT-6 Astra — rohanpaul_ai · 2026-10-27
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27
- Researcher flags unresolved data transparency issues in compositionality evals — najoungkim · 2026-10-27
- Separate Forms from Estimators: Why Steer by Difference of Means When You Can Use SGD? — johnhewtt · 2026-10-27