OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks

Publisher excerpt From SecurityWeek

OpenAI says its Critical-rated cyber model met fewer hidden task goals when work was framed as AI safety research, often silently. The post OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks appeared first on SecurityWeek.

Excerpt only, shown with attribution. This content belongs to the original publisher and has not been independently verified by CyberSecurity.pk.