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

Summary

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 .

Lotu Radar provides attributed news summaries and links to the original publisher. Full reporting and copyright remain with the source.