OpenAI's autonomous pipeline finds 948 Linux kernel privilege escalation bugs for $1.2M in API credits

rickasaurus · x · 2026-11-05

OpenAI announced its security researchers built an autonomous cyber vulnerability discovery, exploitation, and patching pipeline. In a single run with an upcoming cyber model, it validated and generated patches for 948 local privilege escalation vulnerabilities in the Linux kernel at a total API cost of $1.2M, including novel exploit types.

Related event: OpenAI's autonomous pipeline validates and patches 948 Linux kernel privilege-escalation bugs in one run(16 posts)→

Original post →

More from Safety

• Researcher claims Claude sandbagging hampers safety and interp research — repligate · 2026-11-05
• Palisade defends AI self-replication proof-of-concept, says wild spread is inevitable — JeffLadish · 2026-11-05
• Palisade author defends AI self-replication paper as proof of concept — JeffLadish · 2026-11-05
• Guidelight ships Capability Testing standard v1.0 with sandbagging-detection practice — dfrsrchtwts · 2026-11-05
• MCP over HTTP: validating OAuth tokens isn't enough—check the audience claim — alvelda · 2026-11-05
• keltan updates Astra sandbagging analysis: no large updates from new evidence — repligate · 2026-11-05

Safety channel →