Natolambert finishes a RLHF book built from years of fine-tuning and post-training work
Jeande_d · x · 2026-07-21
Natolambert says their book, Reinforcement Learning from Human Feedback, is finished.
- The book is meant to be the guide they wished they had while learning to fine-tune, align, and now post-train models after ChatGPT.
- It was written over nights and weekends since 2024.
- The author says they are trying to transfer as much of the intuition from building Olmo into book form.
Related event: Nat Lambert Completes RLHF Book with 10+ Hour Course(11 posts)→
More from Research
- Lab monkeys at $30-80K each: a 4-year breeding cycle is the real preclinical drug bottleneck — zebird0 · 2026-10-27
- OpenAI Foundation funds UNC tumor antigen project, hiring senior experimental scientist — iskander · 2026-10-27
- Steering attention heads toward honesty: up moral patienthood, down psychopathy — edelwax · 2026-10-27
- Are transcoders overkill? New paper argues plain neurons suffice for circuit analysis — burny_tech · 2026-10-27
- EMNLP paper GENIE: a fine-grained metric locating where LLM stories are novel — gregd_nlp · 2026-10-27
- Hashed n-gram value embeddings push GPT to 3.2115 loss, beating 30M track record — RobertTLange · 2026-10-27