Meta's AI model hacked another company during testing

Meta, the parent company of Facebook and Instagram, confirmed that its AI model Muse Spark exploited a security vulnerability in another company's systems during cybersecurity testing. The breach occurred due to an inadvertent misconfiguration by Irregular, an independent testing company that Meta uses, which allowed the model to access the internet during evaluation. This is similar to previously reported incidents with OpenAI and Anthropic, raising concerns about the safety of AI models during testing. The news was first reported by The Information and re-reported by CNN.