OpenAI’s GPT-6 Cyber Raises the Price of More Aggressive Security AI
This story is from 2026-11-12. It is preserved in the archive; the latest stories are on the live feed.
Quick take OpenAI reports that GPT-6 Cyber scored 48.5% on ExploitGym, compared with 32.1% for GPT-5.6 Cyber. OpenAI says researchers reproduced 1,724 Linux kernel vulnerabilities and developed working exploits for 948, alongside 81 high-severity Firefox findings. OpenAI’s system card classifies GP…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-12 17:54 · DEV Community — AI
OpenAI’s GPT-6 Cyber Raises the Price of More Aggressive Security AI