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

Reported by SecurityWeek (Eduard Kovacs)

Summary by Cyber Security News5 Nov 2026, 11:02 CET

About this summary. This is a short excerpt from the description that SecurityWeek published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://www.securityweek.com/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.

Read the full article at SecurityWeek →

Source attribution: headline and facts are from SecurityWeek (securityweek.com). Summary method: excerpt of the source description. See our source attribution policy.