![[人人能懂] 越想越笨，越学越偏：我们真的了解AI的大脑吗？](https://image.xyzcdn.net/FuDP4HpAp8ezgVZMmEel3mblKCmJ.jpg@small)
137
000:01:15 AI变“聪明”的代价：那根看不见的绳子
00:05:47 给AI“长考”时间，它怎么反而变笨了？
00:11:35 AI的“潜移默化”：看不见的信号，看得见的风险
00:15:45 AI教育的秘诀：一句“再试试”的力量
00:19:28 高手记忆的秘密：不是记得多，而是会“扔”
本期介绍的几篇论文：
[LG] The Invisible Leash: Why RLVR May Not Escape Its Origin
[Stanford University & University of Tokyo]
---
[LG] Inverse Scaling in Test-Time Compute
[University of Edinburgh & EPFL & University of Texas at Austin]
---
[LG] Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
[Anthropic Fellows Program & Truthful AI]
---
[LG] A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
[Imperial College London & Northwestern University & University of Washington]
---
[LG] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
[Georgia Tech]
