OpenAI GPT-6 Cyber finds 81 Firefox vulnerabilities and 948 Linux kernel exploits
Original title: OpenAI’s New GPT-6 Cyber Finds 81 High-Severity Firefox Vulnerabilities and 948 Linux Kernel Exploits
The model scored 48.5% in ExploitGym and completed 95% of RemoteExploitBench tasks while avoiding out-of-scope exploitation 99.93% of the time.
OpenAI released GPT-6 Cyber, a specialized AI model for cybersecurity tasks that uncovered 81 high-severity Firefox flaws and built working exploits for 948 Linux kernel vulnerabilities. The model achieved 48.5% in the ExploitGym evaluation and completed 95% of tasks on RemoteExploitBench. OpenAI disclosed findings to Mozilla and Linux maintainers along with candidate patches.
- GPT-6 Cyber scored 48.5% in ExploitGym
- Completed 95% of RemoteExploitBench tasks
- Avoided out-of-scope exploitation 99.93% of time with safety prompts
- Sent 81 Firefox flaws and 304 critical Linux findings to maintainers
- Vendors
- OpenAI
- Organizations
- Mozilla
- AI models
- GPT-6 CyberGPT-5.6 Cyber
From the original article
3 min read at gbhackers.com
OpenAI has introduced GPT-6 Cyber, a security-focused model built to find and validate exploitable vulnerabilities while staying within the scope researchers set. The company says the model has already uncovered 81 previously unknown high-severity Firefox flaws and produced working exploits for 948 Linux kernel vulnerabilities. OpenAI’s New GPT-6 Cyber GPT-6 Cyber is a specialized variant […]
By Divya · gbhackers.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.