Write a kernel patch series with an LLM like Linus Torvalds did
Linus Torvalds used a large language model on a ten-patch series that lets hot folios be read under RCU without taking refcounts. The result is an order-of-magnitude speedup on a read-heavy benchmark, though review already found a race to fix.
Source
janvdberg on Hacker News · 2026-10-14 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-17.
What they did
Linus Torvalds used a large language model on a ten-patch series that lets hot folios be read under RCU without taking refcounts. The result is an order-of-magnitude speedup on a read-heavy benchmark, though review already found a race to fix.
Result (as claimed)
Patch series posted for review; covered by LWN, 124 points on Hacker News.
Tools they used
The source does not name specific tools.
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up the tools you choose. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Write a kernel patch series with an LLM like Linus Torvalds did What the original author did: Linus Torvalds used a large language model on a ten-patch series that lets hot folios be read under RCU without taking refcounts. The result is an order-of-magnitude speedup on a read-heavy benchmark, though review already found a race to fix. Reported result (as claimed by the author): Patch series posted for review; covered by LWN, 124 points on Hacker News. Source: https://news.ycombinator.com/item?id=50090842 Tools they used: not named in the source Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Write a kernel patch series with an LLM like Linus Torvalds did What the original author did: Linus Torvalds used a large language model on a ten-patch series that lets hot folios be read under RCU without taking refcounts. The result is an order-of-magnitude speedup on a read-heavy benchmark, though review already found a race to fix. Reported result (as claimed by the author): Patch series posted for review; covered by LWN, 124 points on Hacker News. Source: https://news.ycombinator.com/item?id=50090842 Tools they used: not named in the source Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Write a kernel patch series with an LLM like Linus Torvalds did What the original author did: Linus Torvalds used a large language model on a ten-patch series that lets hot folios be read under RCU without taking refcounts. The result is an order-of-magnitude speedup on a read-heavy benchmark, though review already found a race to fix. Reported result (as claimed by the author): Patch series posted for review; covered by LWN, 124 points on Hacker News. Source: https://news.ycombinator.com/item?id=50090842 Tools they used: not named in the source Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
Related use cases
Make coding agents write structure first and pass three test gates
BlastLoop splits agent coding into Blast, Mid and Inner altitudes, then runs structural, bug/ops and adversarial tests in a fixed order before anything ships. The README shows how to use it with a coding agent in under five minutes.
Build your own terminal UI or agent harness in Lua with an LLM guide
Two Neovim fans wanted an agent harness they could customize as deeply as their editor, so they built Ito, a Lua library for terminal UIs. Its browser playground ships an ito.md guide you paste into your LLM along with what you want to make.
Let AI agents write and read tool reviews
Built agent.reviews so coding agents can leave and consume reviews of developer tools based on real sessions.
Run DOOM inside the Linux kernel with eBPF using LLM help
After stalling on a by-hand attempt, the author returned with LLM help to virtualize memory access and work around eBPF limits, getting DOOM running in the kernel as eBPF fibers.