OpenAI 表示思维链监控是防御AI代理失调的关键层,为保持可监控性,他们避免惩罚。
RT @OpenAI: Chain of thought monitors are a key layer of defense against AI agent misalignment. To preserve monitorability, we avoid penali…
likes: 1867 | retweets: 157 | replies: 212 | views: 226810