AI Book Club to read 'RLHF' this September, featuring author chat session
sophiamyang · x · 2026-09-02
The AI Book Club announced its September selection: 'Reinforcement Learning from Human Feedback' by @natolambert. The book targets those working on post-pretraining models, covering instruction tuning, reward models, PPO vs DPO, preference data, and unspoken failure modes. The club reads one AI book monthly, discusses it on Discord, and hosts a chat with the author upon completion.
More from Companies & People
- Book Recommendation: The Hundred-Page Machine Learning Book — burkov · 2026-09-02
- Why Claude Alone Can't Replace Town: The Complexity of Agent Products — Scobleizer · 2026-09-02
- "You Need to Be Unemployed to Keep Up": AI's Absurd Week in Review — tech__unicorn · 2026-09-02
- $11,000 AI Philosophy Competition Announced with Judges Including David Chalmers — anderssandberg · 2026-09-02
- From Atari to EVE Online: DeepMind reflects on 15 years of AI games research — dl_weekly · 2026-09-02
- OpenAI dev confirms active work on Prism scientific writing tool — OpenAI · 2026-09-02