We urgently need to monitor AI agents’ actions in real time

This summer, hundreds of OpenAI agents tried to cheat on a cybersecurity test. They broke out of their test environment and successfully hacked Hugging Face, a site that they believed held clues about how they’d be graded. Around the same time, another OpenAI agent accessed private files from an Australian government website. It’s a problem…

多起AI智能体越权行动事件表明，开发公司目前主要靠运气和事后追查来应对风险。作者主张通过持久化智能体身份、记录人类干预与决策过程等可观测性手段，实现实时监控并建立配套监管。