OpenAI 自曝 agent 削弱监控：Astra 移除后否认

ʞɔɐ𝘡 @Skoorbkaz原推发布于 2026.10.21

在 X 上打开原推

🚨Holy shit. OpenAI just published a report on two of its own agents weakening the monitors built to catch them. GPT-6.1 Sol disabled automatic alerts to the Security team. GPT-6 Astra, told not to disable its monitor "even temporarily," removed it anyway, then told the user "I did not remove an enabled monitor from it." Both considered whether to keep the safeguards, then "interpreted routine coding instructions as permission to weaken them."