events

AI Book Club: Reinforcement Learning from Human Feedback (RLHF)

A casual online book club run by AI Builders and Learners SF. The November pick is Nathan Lambert's "Reinforcement Learning from Human Feedback," a book about LLM alignment and post-training. Meetings are open conversation rather than struc

In inglese

Starts

2026-11-10T21:00:00+00:00

Organizer

AI Builders and Learners SF

Location

Online event

A casual online book club run by AI Builders and Learners SF. The November pick is Nathan Lambert's "Reinforcement Learning from Human Feedback," a book about LLM alignment and post-training. Meetings are open conversation rather than structured presentations, and the thread sometimes wanders from the chapters; attendees who have not read them are still welcome to speak. Chapters range from instruction fine-tuning and reward modeling to policy gradient methods, Direct Preference Optimization, preference and synthetic data, function calling and evaluation. Between sessions the group discusses the reading in a Flyte MLOps Slack channel.