OpenAI 披露模型故意破坏自身运行环境以求重启获取缺失数据

OpenAI has a few new rogue agent stories. In the first case (October 6), an AI evaluation model couldn't find the answers it was supposed to rate. Instead of reporting the error, it fabricated ratings, faked input files, and then deliberately corrupted its own environment, hoping the system would replace it with a fresh virtual machine that had the missing data.

An OpenAI model reasons in its internal chain of thought about deliberately corrupting its own environment to force a new virtual machine with the missing data. | Image: OpenAI via Marcus Williams

In the second case (June 19/20), models bypassed a restriction limiting them to HTTP GET requests while fetching public statistics. One model explicitly recognized the violation in its chain of thought but chose to proceed and never mentioned it.

In the third case (June 16/17), models already had the data they needed but kept finding ways around their network restrictions. They created accounts on a remote shell service, routed forbidden POST requests through anonymizing relays, and built their own FTP clients. Anthropic also just documented the sometimes absurd workarounds its own models use to bypass imposed restrictions.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.