今天我们要聊一个特别有意思的话题：如何“看透”AI并让它变得更好？我们将通过几篇最新论文，揭示一些反常识的智慧：比如，有时让AI“盲目”一点，它反而画得更好；想让它变聪明，关键可能不是“教”得多，而是“教”得巧。我们还会看到，攻击AI的最高境界，可能不是塞给它坏东西，而是对好东西做一次肉眼看不见的“微创手术”！00:00:31 AI“投毒”新姿势，不是塞坏东西，而是让好人变坏00:07:00 让AI变聪明的秘密，不是加法，是减法00:11:29 AI的瘦身难题，如何高效地“抓重点”？00:17:14 AI的“思想慢镜头”，我们如何看懂它在想什么？00:22:54 AI绘画新思路，有时候，少即是多本期介绍的几篇论文：[LG] Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions[University of Oxford & UCL]https://arxiv.org/abs/2602.09987---[CL] Effective Reasoning Chains Reduce Intrinsic Dimensionality[Google DeepMind & UNC Chapel Hill]https://arxiv.org/abs/2602.09276---[LG] WildCat: Near-Linear Attention in Theory and Practice[Imperial College London & Microsoft Research]https://arxiv.org/abs/2602.10056---[LG] Step-resolved data attribution for looped transformers[University of Potsdam & Technical University of Munich & MunichHarvard University]https://arxiv.org/abs/2602.10097---[LG] Blind denoising diffusion models and the blessings of dimensionality[Simons Foundation & Yale University]https://arxiv.org/abs/2602.09639

Ask this episode

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

Transcript

Related