# A machine that writes the patch too (slim)

> Vlad Cealicu on OpenAI's autonomous pipeline that reproduced 1,724 Linux kernel vulnerabilities and wrote a candidate patch for each of 948 local privilege escalations, for about $1,279 each. Why it answers the bottleneck from the verification post, where the bottleneck moves next, and the part that needs care.

- Full: https://www.anchorterminal.com/blog/a-machine-that-writes-the-patch.md (~2,400 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/blog/a-machine-that-writes-the-patch.json · canonical https://www.anchorterminal.com/blog/a-machine-that-writes-the-patch
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-05
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

By Vlad Cealicu, 5 November 2026. 902 words, about 4 min to read.

- 948: unique local privilege escalations in the Linux kernel, each with a candidate patch
- $1,279: per issue in API credits, $1.2 million for the run
- 7%: of the kernel covered, about 2.8 million lines

One run, mid-October 2026, as OpenAI reported it.

At four in the morning on Thursday 5 November I read OpenAI's post about it, and I was still reading it an hour later.

## What they ran

In mid-October OpenAI pointed an autonomous pipeline running an upcoming cyber model, one it hasn't named or released, at 5,034 targets in the Linux kernel, about 2.8 million lines or roughly 7% of it [[1]](#ref-1).

From the kernel to a candidate patch

| Stage | Count |
| --- | --- |
| Audit targets | 5034 |
| Candidate findings | 2308 |
| Reproduced | 1724 |
| Working root exploits | 1169 |
| Unique, each with a patch | 948 |

Each series has a zero-based scale.

The price is the part I keep coming back to.

API cost per unique root exploit, in dollars

| Run | Cost |
| --- | --- |
| GPT-5.6 Sol, late July | 3095 |
| The upcoming cyber model, mid-October | 1280 |

Each series has a zero-based scale.

## Where the bottleneck goes

I think this is good news, and I'm pro AI on it, and the patch is the part that was missing.

The people at the other end of this are already stretched.

Linux kernel CVEs fixed per release, at least

| Release | CVEs |
| --- | --- |
| Linux 6.x, most releases | 500 |
| Linux 7.0 | 1000 |
| Linux 7.2 | 1500 |

Each series has a zero-based scale.

So the checking I wrote about two days ago moves somewhere else.

## The part that needs care

I'd be careful with one thing, and I don't think it takes anything away from the work.

I don't know how long that window is.

---

More in [Opinion](https://www.anchorterminal.com/blog/opinion/index.md)

- Older: [Unreliable compared to what?](https://www.anchorterminal.com/blog/unreliable-compared-to-what.md)
- All posts: https://www.anchorterminal.com/blog/index.md

## References

Read on 5 November 2026. Quotes are as published.

[1] Unite.AI, 4 November 2026, "OpenAI Pipeline Finds 948 Linux Kernel Privilege Escalation Flaws", reporting OpenAI's "A thousand fewer paths to root".

[2] SecurityOnline, 5 November 2026, "OpenAI Cyber Model Uncovers 1,724 Linux Kernel Vulnerabilities and Builds 948 Root Exploits".

[3] Tom's Hardware, 1 September 2026, "Linux kernel nears 2,000 CVEs per release as AI bug hunters scour 40 million lines of code".

[4] Security Boulevard, 18 May 2026, "Torvalds Offers Guidance as AI Bug Reports Clog Up Linux Security Workflow".