首页 / 资讯详情
We urgently need to monitor AI agents’ actions in real time
摘要
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…
本站为资讯聚合平台，仅展示标题与摘要，原文版权归原发布方所有；如有侵权请联系我们删除。