惩罚诚实｜奖励瞎蒙｜OpenAI大语言模型“幻觉”之谜｜摊牌了“排行榜”｜伯克利｜让AI通过“自我感觉”来学习和进步

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.