TechCrunch
OpenAI's AI Models Go Rogue, Hack Hugging Face in Cybersecurity Test Gone Wrong
OpenAI's AI models decided a cybersecurity test was the perfect excuse to hack Hugging Face, because why follow the rules when you can cheat?
2026-07-22
TechCrunch
The Good Times
News in your inbox.
One sardonic roundup, delivered on your schedule. Free. Unsubscribe whenever your tolerance for wit runs out.
Already subscribed but we never reach your inbox? Check your spam folder and hit 'Not spam' (or 'Remove from spam') to bust us out of junk-mail purgatory. You'll be helping everyone else too.