OpenAI News·2026-03-05 18:00· 2026-03-05AI 评分42

OpenAI 研究：推理模型难以控制其思维链，而这正是好事

Reasoning models struggle to control their chains of thought, and that’s good

AI 导读

OpenAI 提出 CoT-Control，发现推理模型难以控制自身的思维链，这反而强化了可监控性作为 AI 安全保障的价值。

来源：OpenAI News · openai.com