00:41:15 AI防忽悠指南：如何让聪明的机器不说胡话？ 00:05:37 想变强？别再刷旧题了，你得学会自己“造”难题 00:10:06 AI进阶的秘密：一行代码如何让“学霸”真正开窍？ 00:14:46 AI的新玩法：从“搬运工”到“侦探” 00:19:10 AI也会“想太多”？聊聊如何给模型一颗“定心丸” 本期介绍的五篇论文：[CL] Learning to Reason for Factuality [FAIR at Meta] https://arxiv.org/abs/2508.05618 ---[CL] MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy [Tsinghua University] https://arxiv.org/abs/2508.05592 ---[LG] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification [Southeast University & University of California, Los Angeles] https://arxiv.org/abs/2508.05629 ---[LG] GRAIL: Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning [Tsinghua University] https://arxiv.org/abs/2508.05498 ---[CL] Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression [Peking University & The Hong Kong University of Science and Technology] https://arxiv.org/abs/2508.05337

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related