OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face

Read full story on Wired
Share
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
AI disclosure

Summary

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.

Original reporting

Open original source

Related coverage

Read full article on Wired

Get the AFBytes Brief

Major stories, AI-assisted analysis, and what to watch next. Free, monthly, unsubscribe anytime.