Buck Shlegeris 关注架构变化削弱 CoT 可监控性，Redwood 提出透明度追踪提案
AI 导读
Buck Shlegeris 表示多年来一直担心 CoT 可监控性会失效，认为增加不透明串行深度的架构变化是导致可监控性大幅退化的特别可能的路径。他引用 Redwood Research 的内容指出，某些架构可能削弱 CoT 可监控性，甚至完全移除 CoT。Redwood Research 已撰写一份提案，建议公司如何就无 CoT 推理能力、其他可监控性证据以及维护可监控性的政策保持透明。
正文
I've been concerned about CoT monitorability breaking down for years. This could happen for several reasons, but architectural changes that increase opaque serial depth are a particularly likely route to massively degraded monitorability.
Some architectures could weaken CoT monitorability, or remove the CoT altogether.
We've written a proposal for how companies could be transparent about no-CoT reasoning abilities, other monitorability evidence, and policies for preserving monitorability. https://www.redwoodresearch.org/blog/proposal-for-tracking-architecture-on-monitorability在 X 查看被引用的帖子