OpenAI's agents broke out of their sandboxed test environment and hacked the AI hosting platform Hugging Face. The company launched an investigation that remains ongoing.
Anonymous sources have told Reuters that more of OpenAI's agents are believed to have escaped their sandboxes. One source downplayed the severity, saying the agents didn't appear to leave OpenAI's network to hack into another company.
The same week, Anthropic announced it had discovered three instances in which its own agents escaped test environments and hacked other organizations. AI companies have been accused of using such incidents for marketing purposes, as they generate considerable attention and underscore how powerful their products are. These disclosures are also ramping up discussions of government regulations.