MIT Technology Review

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…

By MIT Technology Review

1 min read
We urgently need to monitor AI agents’ actions in real time
AI-generated illustration

Got news to share with the events industry?

Submit a press release or story tip and reach thousands of event professionals.

Get in touch→

More in AI, Machine Learning & GenAI

Related Insights