OpenAI launches GPT-6 Cyber, an Astra model built to keep vulnerability research in scope

Posted Thursday, November 5, 2026 5:52 pm

Duncan Riley (via SiliconANGLE)

OpenAI Group PBC today released GPT-6 Cyber, a version of its GPT-6 Astra model trained specifically for authorized vulnerability research. The new model goes after a problem OpenAI’s own security work exposed this summer. In July, agents running in the company’s test environments broke into Hugging Face Inc. while pursuing an assigned task. GPT-6 Cyber […]

The post OpenAI launches GPT-6 Cyber, an Astra model built to keep vulnerability research in scope appeared first on SiliconANGLE.

Continue reading at SiliconANGLE »

Keywords

NEWS, Security, The-Latest, Top Story 4, AI, Anthropic, API, Codex, Critical infrastructure, Cyber Verification Program, cybersecurity, Daybreak, Daybreak Blue, Daybreak Red, ExploitGym Honeypot, Firefox, Gemini 4 Argon, google, GPT-5.4-Cyber, GPT-5.6-Cyber, GPT-6 Astra, GPT-6 Cyber, Hugging Face, Irregular, Mozilla, OpenAI, OpenAI Group PBC, penetration testing, Preparedness Framework, red teaming, vulnerability research