# OpenAI reports an autonomous pipeline that produced 948 working Linux kernel privilege escalation exploits

> Original title: We’ve assembled a world class cyber team and I’m excited for us to share more about our work over the weeks and months.

- Source: Tibo
- Published: 2026-11-05T01:02:03.000Z
- Bad Influence: https://badinfluence.news/items/h0gcy0wh2hlvbwob7y216t1wy
- Original: https://x.com/thsottiaux/status/2118146794362405231

## Summary

OpenAI says its security researchers built an autonomous pipeline that finds, exploits and patches vulnerabilities. In one 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 $1.2 million. The accompanying funnel shows 2,308 candidate findings, 1,724 validated findings, and 291 working leak PoCs alongside the 948 working LPE exploits. Tibo says he is excited to share more about the work over the coming weeks and months.

## Post

We’ve assembled a world class cyber team and I’m excited for us to share more about our work over the weeks and months.

## Quoted post @OpenAI

> Our 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 $1.2 million.

https://x.com/OpenAI/status/2118119451401048497