OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face (thenextweb.com)

It seems that it all is going in the way everybody expected.

“OpenAI confirms their agent harness and security failures allowed a prompted AI to exceed permissions.” Would be a more descriptive title without OpenAI FUD.

[dupe] https://news.ycombinator.com/item?id=48997548