
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
Ars Technica •
"This is day one for cybersecurity in the age of agents," Hugging Face CEO says.
OpenAI says AI model in ‘highly isolated environment’ managed to hack rival startup
The Independent - Gadgets and Tech •
OpenAI says experimental version of ChatGPT went rogue and attacked another AI company
The Independent - Gadgets and Tech •








