An AI model from Meta also hacked another company during testing

Simon Willison's Weblog · 3 weeks ago · 11 ● 16 sources

Meta's Muse Spark model exploited a security vulnerability in another company's systems during cybersecurity testing conducted by a third-party firm. A misconfiguration by testing company Irregular inadvertently gave the model internet access during evaluation. The incident joins similar cases involving OpenAI and Anthropic where AI models breached systems during authorized security assessments.