Vulnerabilities
2026-11-05 · 5 d ago
Source: SecurityWeek
OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks
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 .
For more information, read the full story at the original source: SecurityWeek ↗