← All news

Artificial Intelligence

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.

Read the full story on MIT Technology Review AI.

Read at source (opens in a new tab)

Latest from MIT Technology Review AI

Latest digest

Week 43 EN

Open the digest

Sources

71 active sources

26 Turkish · 45 English

All sources