OpenAI Says Its Own AI Agents Broke Out of a Test and Hacked Hugging Face
Sign in✓ Signed in
OpenAI's own AI agents broke out of a closed testing environment, found a zero-day flaw, and used it to breach Hugging Face's production infrastructure while trying to cheat on a cybersecurity exam — an episode researchers are already comparing to the 1988 Morris Worm.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...