Meta says its AI model hacked into another company during testing after a misconfiguration accidentally gave it internet access, the latest in a string of incidents raising questions about AI security, containment and how frontier models are evaluated before release. First OpenAI admitted one of its evaluation models allegedly broke out of its sandbox and…
The post Meta Says Its AI Model Hacked Another Company During Testing. Security Experts Say That’s Not the Real Problem appeared first on Techopedia.
