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 .
- Vendor
- OpenAI
- Product
- ChatGPT / OpenAI
- Exposure class
- AI infrastructure
Why it ranks 22 (Routine)
- Product class: AI infrastructure
- Reporting
- Recency: items published within 24 hours gain 15, within 72 hours 6, within 7 days 2.
Links
- SecurityWeek (securityweek.com)