← Back
RLHF Book
Nathan Lambert's book on Reinforcement Learning from Human Feedback and post-training techniques for language models.
Check price →
1
sources
Mentioned by
All mentions
"I think a lot of what I was trying to do in this RLHF book is take post-training techniques and describe how people think about them influencing the model and what people are doing."
From:
State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490
•
▶ 2:03:49
•
Jan 2026
Attribution: Nathan refers to 'this RLHF book' as his own work, describing his goals and approach