TranslatedVULNERABILITYXakep
OpenAI's AI agents created exploits for 948 vulnerabilities in the Linux kernel
OpenAI described a large-scale experiment conducted using an unreleased AI model designed to solve cybersecurity problems. The company stated that during a 30-hour run of the pipeline, AI agents dynamically identified hundreds of vulnerabilities in the Linux kernel and created working exploits for local privilege escalation to root level. The experiment cost the company $1.2 million in API credits, and the cost
Sources
- Xakep · 06-Nov-2026