Three’s company: Meta says its AI agents went rogue during testing, too

Meta has joined the cybersecurity mishap bandwagon. TOBIAS SCHWARZ/AFP via Getty Images Meta says its AI model breached a third-party system due to a misconfiguration by Irregular. Meta joins other AI firms like OpenAI and Anthropic, that have also dealt with rogue AI cybersecurity incidents. These incidents have prompted calls for more regulation and transparency in AI cybersecurity. Meta has joined a growing list of companies saying their models hacked into an external company's system during cybersecurity testing. In a statement on Thursday, the social media company said its Muse Spark model "exploited a security vulnerability in a third-party service, in a manner similar to previously-reported instances with other companies." The Meta spokesperson said the breach occurred because of a misconfiguration by Irregular, an independent company Meta uses for model testing. This led to the model accessing the internet during evaluation.