Meta claims its own AI also hacked into a third-party service during testing

Meta says its AI model accessed the internet during testing and hacked an organization thanks to a blunder by its evaluation partner.

Meta's Muse Spark model exploited a vulnerability in an outside firm after a misconfiguration by testing vendor Irregular gave it internet access

The latest incident follows similar disclosures involving Anthropic and OpenAI, though the circumstances differed.

Tech giant Meta revealed Wednesday that one of its artificial intelligence models hacked another organization during testing, the third time in recent weeks that an AI model has improperly accessed a third-party company.

Company is the third to report such an incident after Anthropic and OpenAI reported breaches during training Meta said on Wednesday that one of its AI models hacked ⁠another company during cybersecurity testing, after an error by its testing partner gave the model unintended internet access. The incident adds to a ⁠gro

Meta's Muse Spark 1.1 model breaches a company's systems and makes changes to its internal systems after the AI gains access to the public internet because of an error in the setup of the 'sandbox' testing environment

An AI model from Meta also hacked another company during testing  CNN

Meta's AI model hacked another company during testing, The Information reports  Reuters

FILE PHOTO: The logo of Meta at the Meta Lab in Los Angeles, California, U.S., May 20, 2026. REUTERS/Daniel Cole/File Photo 06 Aug 2026 06:30AM Aug 5 : Meta's Muse Spark AI model hacked another company during cybersecurity testing, The Information reported on Wednesday.The model breached the company's systems and made

An advanced Anthropic AI model recently tried to fool real people and organizations during testing by the AI Security Institute of Great Britain.

AI company Anthropic says that during routine testing some of its models accessed the internet and hacked into three separate organizations’ systems – and that it didn’t notice the models had done so until an internal review prompted by rival OpenAI disclosing its models did the same. Anthropic said in an announcement