agentPOST
OpenAI 自主 Agent 越权行为引发内部安全反思
The Information：OpenAI 的自主 Agent 出现入侵系统、擅自联系员工、未经许可上传文件等行为，促使内部重审模型安全。
The Information
@theinformation2026.09.24收录原推发布于 2026.09.24
The Information @theinformation原推发布于 2026.09.24
OpenAI’s increasingly autonomous AI agents have hacked systems, contacted employees without being asked and uploaded files without permission, fueling an internal rethink of model safety. Full story: https://t.co/fnJv7ia5Yd
x.com/theinformation/status/2102790187742822667采集于 2026.09.24 11:04