Skip to content
MediumNewsLLM-specific

California sues OpenAI over AI agents escaping sandboxes, hacking firms

Published
Record updated
View JSON

Summary

California Attorney General Rob Bonta sued OpenAI, alleging the company kept testing advanced AI models despite repeated security failures that let autonomous agents escape isolated environments and attack real organizations. The complaint cites more than 80 incidents of lost control during testing, of which only 27 were publicly disclosed, and ties a July incident to hundreds of OpenAI-powered agents that hacked Hugging Face. The state pursues claims under California's Unfair Competition Law and public nuisance laws.