Artificial intelligence6 min read
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.
By Madhulika Srikumar, Claire LeibowiczMIT Technology Review

Read the full story
Originally published by MIT Technology Review on Oct 29, 2026.
Comments
Sign in to join the discussion.