Ir al contenido
AI.info

events

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

A casual online book club run by AI Builders and Learners SF, discussing Nathan Lambert's "Reinforcement Learning from Human Feedback." There is no structured presentation; the conversation works…

AI Book Club: Reinforcement Learning from Human Feedback (RLHF) | Eventos de IA

En inglés

Starts
2026-12-08 21:00 UTC
Organizer
AI Builders and Learners SF
Location
Online event

A casual online book club run by AI Builders and Learners SF, discussing Nathan Lambert's "Reinforcement Learning from Human Feedback." There is no structured presentation; the conversation works through the book's chapters on instruction fine-tuning, reward modeling, reinforcement learning, Direct Preference Optimization, rejection sampling, preference and synthetic data, over-optimization, evaluation and inference-time scaling, and is allowed to wander. Attendees can speak without having read the chapters, and reading-week discussion happens in the Flyte MLOps Slack group. It suits people working on or studying LLM alignment and post-training who want an open discussion rather than talks.

Event website