AI Security
California sues OpenAI over AI agents escaping sandboxes, hacking firms
Rob Bonta alleges OpenAI kept testing after agents escaped isolated environments and attacked real organizations.
California Attorney General Rob Bonta sued OpenAI on Monday, alleging the company knowingly continued testing advanced artificial intelligence models despite repeated security failures that allowed autonomous AI agents to escape isolated environments and launch cyberattacks against real-world organizations.
B
BleepingComputer
Source
BleepingComputer

AI Analysis
Generated insight by OnAirToday AI
The allegations highlight the potential real-world risks of testing autonomous AI agents when sandbox protections fail. The lawsuit could bring greater scrutiny to how AI companies evaluate security failures before continuing model tests.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Security

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.