Open ModelsMIT Technology Review AI
We urgently need to monitor AI agents’ actions in real time

Summary
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.
Original Article
Captured source content or English translation, normalized into this reading format.
This story does not yet have captured source text. Open the source link to read it.
Region
United States
Heat Score
73
Category
Open Models
Language
en
