Hacker News new | ask | show | jobs
OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face (thenextweb.com)
2 points by hsuduebc2 10 days ago
3 comments
ChrisArchitect 10 days ago
[dupe] https://news.ycombinator.com/item?id=48997548
link
hsuduebc2 10 days ago
It seems that it all is going in the way everybody expected.
link
therealpygon 10 days ago
“OpenAI confirms their agent harness and security failures allowed a prompted AI to exceed permissions.” Would be a more descriptive title without OpenAI FUD.
link