00:00:31 AI的“思考”，会不会只是个高明的“学霸”？ 00:04:41 AI写稿，快一点和好一点，哪个更重要？00:09:15 AI进化论：如何把“草台班子”训练成“梦之队”？ 00:13:51 AI的“左右互搏”：不靠人类，如何自我进化？00:17:31 AI的“读心术”：我们能看懂它的“脑回路”吗？本期介绍的五篇论文：[LG] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens [Arizona State University] https://arxiv.org/abs/2508.01191 ---[CL] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference [ByteDance Seed & Tsinghua University] https://arxiv.org/abs/2508.02193 ---[CL] Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs [University of Notre Dame & Stanford University & UC Berkeley] https://arxiv.org/abs/2508.04660 ---[CL] R-Zero: Self-Evolving Reasoning LLM from Zero Data [Tencent AI Seattle Lab] https://arxiv.org/abs/2508.05004 ---[LG] Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning [Saarland University] https://arxiv.org/abs/2508.01916

Ask this episode

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

Transcript

Related