本期节目,我们将深入AI的“内心世界”:你会发现,让AI多“思考”一会儿,它反而可能变得更诚实;而有时它的“思考”其实不是为了推理,更像是在努力“回忆”。我们还会聊到,最新论文如何让AI拥有调试代码的“灵魂”,如何量化它有多少“小秘密”不愿公开,以及一个聪明的“外行”AI领导,要如何带好一支能打的“内行”AI团队。
00:00:32 AI 不仅会写代码,还会自己找 Bug?
00:05:03 AI会撒谎吗?一个让你意外的答案
00:10:09 思考,不是为了推理,而是为了回忆
00:15:26 AI的“草稿纸”,它到底有多少不能说的秘密?
00:21:32 聪明的“外行”领导,如何带出能打的“内行”团队?
本期介绍的几篇论文:
[LG] Towards a Neural Debugger for Python
[Meta FAIR & Johannes Kepler University Linz]
---
[CL] Think Before You Lie: How Reasoning Improves Honesty
[Google DeepMind]
---
[CL] Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
[Google Research]
---
[AI] Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
[Google DeepMind]
---
[LG] SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding
[CMU & Virginia Tech]
![[人人能懂AI前沿] 从模拟执行到量化坦诚:AI思考的五重解构](https://image.xyzcdn.net/FuDP4HpAp8ezgVZMmEel3mblKCmJ.jpg@small)