你是否想过，AI在犯错的瞬间，内心会不会也“咯噔”一下？面对海量文件，它如何像图书管理员一样建立“超级数据库”而不是被淹没？最新几篇论文给了我们答案。我们将一起探寻AI如何获得“自知之明”，如何被“结果导向”带入“假装思考”的陷阱，以及我们如何像配制营养餐和划重点一样，精准地让它变得更聪明。00:00:28 AI的“第六感”，它知道自己何时能改正错误00:06:17 给AI装上一个“超级数据库”，它就再也不会忘事了00:12:24 你的“结果导向”，正在培养“假装思考”的下属？00:19:17 数据淘金，如何从海量信息中精准“喂”出好模型00:25:16 给AI一支“荧光笔”，它就能看得更清？本期介绍的几篇论文：[LG] How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals [Google DeepMind] https://arxiv.org/abs/2604.22271 ---[CL] Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets [Stanford University] https://arxiv.org/abs/2604.22294 ---[CL] Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning [Stanford University] https://arxiv.org/abs/2604.22074 ---[CL] CRAFT: Clustered Regression for Adaptive Filtering of Training data [Google & BITS Pilani] https://arxiv.org/abs/2604.22693 ---[CL] Learning Evidence Highlighting for Frozen LLMs [Stony Brook University & Meta AI] https://arxiv.org/abs/2604.22565

Ask this episode

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

Transcript

Related