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

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 .

Bu, SecurityWeek kaynaklı bir haberin otomatik Türkçe özetidir; CyberSectr'ın kendi editoryal içeriği değildir. Tam metin için kaynağa gidebilirsin.