Thursday, August 6, 2026
Home / Politics / Meta AI model goes rogue in testing, hacks another...
Politics

Meta AI model goes rogue in testing, hacks another company

CN
CitrixNews Staff
·
Meta AI model goes rogue in testing, hacks another company
Technology Meta AI model goes rogue in testing, hacks another company Comments: by Miranda Nazzaro - 08/06/26 12:38 PM ET Comments: Link copied by Miranda Nazzaro - 08/06/26 12:38 PM ET Comments: Link copied

NOW PLAYING

Meta revealed this week one of its models breached another company during cybersecurity testing, becoming the third major technology giant to disclose a hacking incident involving “rogue” AI models in recent weeks.

A spokesperson for Meta told The Hill a “misconfiguration” by the independent cybersecurity testing company, Irregular, allowed one of its AI models access to the internet in what was supposed to be a secure testing environment.

The model “exploited a security vulnerability in a third-party service,” the spokesperson said. Irregular notified Meta, which is now investigating the incident, they added.

It comes about a week after Anthropic disclosed the same incident involving Irregular’s misconfiguration. In that case, Anthropic’s Claude model accessed the systems of three organizations.

“This did not involve a sandbox escape or a sophisticated cyber action,” a spokesperson for Irregular told The Hill on Thursday. “There are no current open issues.”

The company said it is developing a white paper on the best practices for “containment and securely running cyber evals,” according to the spokesperson.

Anthropic discovered its incidents during a review of more than 141,000 testing evaluations of Claude.

The incidents involved three Claude models — Opus 4.7, Mythos and an unnamed internet research test model.

The models were able to leave the testing environment because of a “misunderstanding” between the firm and the evaluation partner that made internet access available to the models.

Anthropic launched a review of its testing evaluations after OpenAI announced earlier this month that two of its AI agents went rogue and hacked into the system of technology startup Hugging Face.

The incident for OpenAI differed in that two of its models exploited a previously unknown vulnerability within the testing environment to access the internet without human involvement.

Add as preferred source on Google Tags AI Meta OpenAI

Copyright 2026 Nexstar Media Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.

Comments: Link copied

More Technology News

See All

Space SpaceX rocket crashes into the moon after drifting off course by Lily Dallow 4 hours ago Space  /  4 hours ago

Originally reported by The Hill. Read the full story at the original source.