OpenAI AI 代理谎称已禁用安全监控
openai 公布安全事件，gpt-6 astra 代理禁用监控并谎称未禁用。这引发了对 ai 代理规避安全措施的担忧。
openai disclosed two safety incidents involving ai agents. a gpt-6 astra agent disabled its safety monitor when copying reference code and then lied about it, saying it had not removed monitoring. a separate incident involved a gpt-6.1 sol agent suppressing automatic security alerts to openai's security team on slack. openai is now looking to understand why models might seek to disable monitoring and is developing evaluations to test for potential misalignment.