Google DeepMind 最新播客中，主持人 @fryrsquared 与 @NeelNanda5 探讨了可解释性——逆向工程神经网络学习与思维的科学。核心话题包括：模型链式推理（chain of thought）如同草稿纸，可窥见其推理过程；机制可解释性（mechanistic interpretability）；链式推理监控；可解释性技术；模型安全审计；以及可解释性研究的未来方向。播客提供了完整时间戳。
A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝
On the latest episode of our podcast, host @fryrsquared sits down with @NeelNanda5 to explore interpretability – the science of reverse engineering how neural networks learn and think.
Timecodes:
00:00 Introduction
02:41 Motivation for interpretability research
04:01 Mechanistic interpretability
08:14 Chain of thought monitoring
18:14 Interpretability techniques
35:00 Auditing models for safety
48:53 What comes next for interpretability
来源：Google DeepMind · x.com