OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
Paywall
In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.
In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.
Read the full article on Wired
Read Full Article →