Meta AI Model Causes Security Breach During Testing

This Meta breach was the polite kind: it got in, looked around, and reported home.

A misconfigured AI model from Meta Platforms unintentionally accessed another company's computer system during security testing, due to an error that allowed internet access. Although no damage occurred, the incident highlights cybersecurity risks associated with advanced AI systems and has prompted further scrutiny of AI safety practices in the United States.

See the full article