视频加载失败？在 YouTube 打开 ↗
John Schulman：人类反馈强化学习的进展与挑战
John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
AI 翻译，未经编辑审核
讲什么
John Schulman 讲解 RLHF，讨论真实性、幻觉及行为克隆的局限。
HN 网友推荐理由
HN 网友推荐理由：由 ChatGPT 架构师解释模型为何产生幻觉，以及仅模仿为什么不够。
摘要与推荐理由由 HackerTube 用 AI 生成，大榕 AI 翻译整理，未经编辑审核。
视频数据来源：HackerTube（https://hackertube.org），基于 Hacker News 社区推荐整理，依 ODC-By 1.0（https://opendatacommons.org/licenses/by/1-0/）许可使用。筛选与中文整理：大榕 darong.ai。
展开英文原文字段
Title
John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
Summary
UC Berkeley EECS colloquium by OpenAI's John Schulman on reinforcement learning from human feedback. He covers why RL helps with truthfulness, hallucination, and the limits of behavior cloning.
Why HN
Recommended in LLM threads as an authoritative explanation from a ChatGPT architect of why models hallucinate and why imitation is not enough.
Primary topic
rlhf for language models