AI 导读
如果对齐问题已经严重到 OpenAI 愿意把 20% 的研究推理算力投入到思维链监控上，那说明对齐问题正在成为一个相当严重的隐患。 我们真的需要跨实验室的通用政策与标准。
正文
If alignment issues are becoming big enough that OpenAI is willing to commit 20% of research inference compute to chain-of-thought monitoring, that suggests that alignment issues are becoming a pretty serious concern.
We really need universal policies & standards across labs. https://t.co/LZLCmvWw8u
来源：@emollick · x.com