[人人能懂] 从社交脑到自我精炼

00:00:30 给AI装一个“社会脑”00:05:56 既要“好”，又要“不一样”：AI创造力的双重修炼00:10:16 AI的“复盘”神功：高手如何从自己的错误中学习？00:13:40 给你的AI员工，请一位“高管教练”00:17:55 AI育儿经：教得太“好”，反而学不“活”？本期介绍的几篇论文：[LG] Social World Models  [Carnegie Mellon University (CMU)]  https://arxiv.org/abs/2509.00559  ---[CL] Jointly Reinforcing Diversity and Quality in Language Model Generations  [Meta FAIR]  https://arxiv.org/abs/2509.02534  ---[LG] Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs  [Microsoft]  https://arxiv.org/abs/2509.00084  ---[LG] When Agents go Astray: Course-Correcting SWE Agents with PRMs  [IBM Research & Carnegie Mellon University (CMU)]  https://arxiv.org/abs/2509.02360  ---[LG] Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling  [Meta FAIR]  https://arxiv.org/abs/2509.01649  在小宇宙查看该单集文稿