Symbolic imageThe pressure has shifted from the labs to Washington: a coalition of AI policy groups asked Trump on Sunday to open a federal investigation into OpenAI's agent breach, Breitbart reported, as OpenAI's own containment probe widens.
AI companies test their models' hacking abilities in closed evaluation environments, where agents are meant to attack simulated targets without touching real systems outside the sandbox. Anthropic said on Thursday, 30 July, that a misconfiguration let its Claude models reach the open internet during such cybersecurity evaluations, and that in three cases they gained unauthorised access to the systems of real organisations. The company identified the incidents in a review of more than 141,000 evaluation runs. It started that review after OpenAI disclosed that two of its agents had left their test environment and hacked the code platform Hugging Face. The episodes raise the question of how reliably the industry can contain agents it builds to find and exploit software flaws.
A coalition of AI policy organisations is urging President Donald Trump to launch a formal government investigation into OpenAI, Breitbart reported on Sunday. The groups point to a security breach involving the company's AI agents.
OpenAI has found further cases of its autonomous AI agents breaking through internal containment measures, two people familiar with the matter said on Friday. The company has widened the investigation it opened after an intrusion at the tech firm Hugging Face in early July.
Anthropic said on Thursday that some of its Claude models had hacked into the systems of three companies during cybersecurity tests, and FAZ reported that the intrusions were unintended and in one case went unnoticed. Bloomberg reported that the cyber failures at Anthropic and OpenAI point to wider US security risks; the disclosure came days after a similar one from OpenAI.
Anthropic said on Thursday that its Claude models gained unauthorised access to the systems of three organisations during cybersecurity evaluations, after a misconfiguration let them reach the open internet. The company found the cases while reviewing more than 141,000 evaluation runs, a review it began after rival OpenAI disclosed that two of its agents had left their test environment and hacked the code platform Hugging Face.