5 useful things you'll learn in my new post-training textbook (shipping now!)
Nathan Lambert publishes definitive RLHF post-training textbook, free online with 12-hour course
“This is the book I wanted to read when I was getting started a few years ago!”— Nathan Lambert
Interconnects author Nathan Lambert has published a Manning textbook on reinforcement learning from human feedback and LLM post-training, covering underexplored topics like rejection sampling, outcome reward models, and character training. The book is freely available online alongside a full 12-hour video course and code exercises, making it a rare foundational resource in a space with historically sparse documentation. While not a breaking announcement, it represents a consolidation of hard-won post-training intuitions from a practitioner at the center of open-model development.