--- title: Linus Torvalds Working On A Hefty Linux Kernel... description: Linus Torvalds is using Claude Code to help develop a new Linux kernel branch, noref-filemap-read-with-llm, which reworks memory management to read from the... canonical: https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code | daily.dev og:description: Linus Torvalds is using Claude Code to help develop a new Linux kernel branch, noref-filemap-read-with-llm, which reworks memory management to read from the... og:url: https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj og:image: https://api.daily.dev/og/posts/rXVrCcbLJ.png og:image:alt: Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code **[Phoronix](https://daily.dev/sources/phoronix)** · 2 min read · 13 upvotes · 4 comments ## Summary Linus Torvalds is using Claude Code to help develop a new Linux kernel branch, noref-filemap-read-with-llm, which reworks memory management to read from the page cache without folio references. The change targets a bottleneck where small reads of a single file from many threads contend on folio reference counting, and Torvalds reports significant performance improvement from the patch series. He confirmed in the kernel patch message that the code, test programs, review, and even the first draft of the cover letter text were produced with Claude Code under his direction, while measurements were run on his own machine. The branch may be merged in the upcoming Linux 7.4 merge window. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Is Linus Torvalds using AI tools to write Linux kernel code? Yes, Torvalds used Claude Code, an AI coding assistant, to help write code, test programs, and conduct reviews for a new kernel branch called noref-filemap-read-with-llm. He stated in the kernel patch message that the code, test programs, review, and even the first draft of the cover letter were done with Claude Code under his direction, with measurements run on his own machine. _Developers curious how AI assistants are entering kernel-level work can follow cases like this on daily.dev._ ### What kernel performance problem does the noref-filemap-read-with-llm branch address? It targets contention on folio reference counting when many threads perform small reads of a single file from the page cache. The patch series reworks memory management code to read from the page cache without taking folio references, which Torvalds reported produces a significant performance improvement, though the branch had not yet been merged into mainline. _Engineers tracking kernel memory management changes can follow this work on daily.dev before it lands upstream._ ## Community take How the wider developer community reacted, aggregated from 2 discussions and 29 comments across lobsters, hackernews (as of 2026-10-19). **TL;DR:** Discussion is dominated by discomfort with LLM involvement in kernel development, especially the AI-drafted cover letter prose, though some argue LLMs are already unavoidable in the toolchain and that Torvalds is uniquely qualified to review AI-generated code. **Sentiment:** 15% positive · 35% mixed · 50% skeptical **The case for** - Some argue LLMs are already pervasive in toolchains (compilers, firmware) so objecting only now is inconsistent. - A few note LLMs have helped surface real bugs and vulnerabilities in existing codebases. - One view holds that if anyone should use LLMs for code, it's someone as experienced a reviewer as Torvalds. **The pushback** - Many find the AI-generated prose in the patch cover letter poorly written and lacking genuine human thought. - Some feel using LLMs to replace human-written communication crosses an important line, even if code generation is more accepted. - Concerns that heavy LLM use erodes individual thinking and makes people 'common' or less original. - Worry that overall software quality is declining despite increased LLM-assisted coding. **By community** - lobsters (heated): A long, contentious thread split between people alarmed by AI writing the cover letter/prose and others arguing LLM involvement in software is already unavoidable. - hackernews (mixed): Minimal discussion, limited to idle speculation about how the AI model might react to working with Torvalds. **Hottest debate:** Whether using an LLM to draft human-facing prose (the patch cover letter) is a meaningful ethical line, versus using LLMs for code review/generation being comparatively more acceptable. **Open questions** - Does the model behave differently or acknowledge who it's working with when told it's assisting Torvalds? - Is objecting to AI-generated code ethically motivated or purely about quality, and does that distinction matter? **Highlights** > Reading the [patch message](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h=noref-filemap-read-with-llm&id=4c0f3697118eb3a708ea79175f7f07c43339bfab) is honestly disheartening. I think everyone can agree that AI has some utility as a code reviewer at least. Whether to use it to generate code is controversial but certainly many people decide to. But replacing actual written communication, in English, for humans, with slop is a line that I wish we could all draw. According to Linus "the first draft" was written with an LLM. > No reference, no on-stack bounce buffer, no seqcount, no check after the copy, and no limit on the size of the read. > They stopped at what the validation cannot see: > Known problems, and what I'd like eyes on I'm so viscerally sick of this style of writing that communicates so poorly and shows lack of human thought behind it. > — [bmo on lobsters · 3 points, 2 comments](https://lobste.rs/s/iq5xtw/linus_torvalds_working_on_hefty_linux#c_pdxjuf) > Yeah. If I had to pick literally one single human to read through 100,000 lines of bullshit PRs and firmly reject the bad ones, well, Linus has spent the majority of his "development" time doing that for 30 years now. And he's not especially shy about rejecting bad code. (By which I mean mainstream media was starting to write about his rejections, and so he was sent for remedial social skills training.) So just to troll a bit, my new position on this issue is that _only_ Linus should be allowed to use LLMs. I trust Linus to read the code and tell Claude what he really thinks. > — [emk on lobsters · 4 points](https://lobste.rs/s/iq5xtw/linus_torvalds_working_on_hefty_linux#c_trweh4) > Linux already contains LLM-generated code anyway. And you know what? It doesn't matter because there's no way to avoid LLM-generated code. GCC and LLVM can be used for Linux compilation and they both contain LLM-generated code already. Looking at https://codeberg.org/ethical-foss/open-slopware#operating-systems, to be LLM-free, you would have to use an OS that is against LLM, compiled by a compiler written without LLM. That removes all the Linux distributions, BSD systems (even NetBSD, against using LLM, is using GCC and LLVM) and even Illumos. Probably the only one left would be 9front (Redox uses Rust compiler, which also was written with LLM help). Good luck using it for everything. Also, keep in mind that firmware code is not granted by the heavens, but written - or these days probably "hallucinated" is a better word. As it turns out: https://codeberg.org/ethical-foss/open-slopware#bootloaders even coreboot allows for LLM, U-Boot as well. > — [pkubaj on lobsters · 1 points, 4 comments](https://lobste.rs/s/iq5xtw/linus_torvalds_working_on_hefty_linux#c_iys7t8) > > I personally am not happy about this, the last place I want AI to touch is my Linux. Is that for ethical reasons or code quality reasons or both? If it's the former then fair enough. If it's the latter, one could make a credible case that Linus Torvalds is the most experienced code reviewer in the world. > — [simonw on lobsters · 1 points, 1 comments](https://lobste.rs/s/iq5xtw/linus_torvalds_working_on_hefty_linux#c_t30reu) **Source threads** - [lobsters](https://lobste.rs/s/iq5xtw/linus_torvalds_working_on_hefty_linux) · 27 points · 28 comments - [hackernews](https://news.ycombinator.com/item?id=50050367) · 19 points · 1 comments ## Community discussion Top comments from developers on daily.dev. **@jorgepires** · 1 upvotes > So NO AI is NO AI ... looool **@adampagano** · 1 upvotes > I would expect Torvalds to jive with AI tools given a lot of what he does is tell others what kind of code he wants and yells at them until he gets it. **@devgenx** · 0 upvotes > It is way pass time modern computers got a modern operating system. The Linux kernel has a chance to be the foundation for that OS, and this is a good sign that Linus is taking the steps needed to do that. **@ristotoldsep** · 0 upvotes > If Linus can review AI-written kernel code, fine. The rest of us should probably keep the tests on 😅 ## Similar posts on daily.dev - [Linus Torvalds "Did What I Preach", Used AI To Make Code Decipherable & Uncovered More Bugs](https://daily.dev/posts/linus-torvalds-did-what-i-preach-used-ai-to-make-code-decipherable-uncovered-more-bugs-tsqqcmos3) · Phoronix · 2 upvotes · 0 comments - [Claude Code Found a Linux Vulnerability Hidden for 23 Years](https://daily.dev/posts/claude-code-found-a-linux-vulnerability-hidden-for-23-years-ty1tp2xrp) · Michael Lynch · 14 upvotes · 1 comments - [Claude Code Used to Find Remotely Exploitable Linux Kernel Vulnerability Hidden for 23 Years](https://daily.dev/posts/claude-code-used-to-find-remotely-exploitable-linux-kernel-vulnerability-hidden-for-23-years-vni2dtvdh) · InfoQ · 0 upvotes · 0 comments --- Tags: [#linux](https://daily.dev/tags/linux), [#claude-code](https://daily.dev/tags/claude-code), [#vibe-coding](https://daily.dev/tags/vibe-coding) [View this post on daily.dev](https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code","url":"https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj"},"datePublished":"2026-10-12T00:24:59.537Z","dateModified":"2026-10-19T16:37:23.770Z","description":"Linus Torvalds is using Claude Code to help develop a new Linux kernel branch, noref-filemap-read-with-llm, which reworks memory management to read from the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f4c82fb52889487d57b3b55117e7830?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f4c82fb52889487d57b3b55117e7830?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Phoronix","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Phoronix","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/6a26ba379dd64932830aa0c9803dd7ee","url":"https://daily.dev/sources/phoronix"},"commentCount":4,"discussionUrl":"https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":13},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":4}],"keywords":"linux,claude-code,vibe-coding","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Phoronix","item":"https://daily.dev/sources/phoronix"},{"@type":"ListItem","position":3,"name":"Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj","comment":[{"@type":"Comment","text":"So NO AI is NO AI … looool","datePublished":"2026-10-12T11:28:50.700Z","url":"https://daily.dev/posts/rXVrCcbLJ#c-OqvuJYwxO","author":{"@type":"Person","name":"Jorge Pires","url":"https://daily.dev/jorgepires","image":"https://media.daily.dev/image/upload/s--K1yCK8O9--/f_auto/v1756721347/avatars/avatar_3gsPpgRHaO18fVHasOHtw?_a=BAMClqZW0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"I would expect Torvalds to jive with AI tools given a lot of what he does is tell others what kind of code he wants and yells at them until he gets it.","datePublished":"2026-10-12T12:04:09.849Z","url":"https://daily.dev/posts/rXVrCcbLJ#c-EG248zL0G","author":{"@type":"Person","name":"Adam Pagano","url":"https://daily.dev/adampagano","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"It is way pass time modern computers got a modern operating system. The Linux kernel has a chance to be the foundation for that OS, and this is a good sign that Linus is taking the steps needed to do that.","datePublished":"2026-10-12T12:06:38.770Z","url":"https://daily.dev/posts/rXVrCcbLJ#c-vTHFpPrc3","author":{"@type":"Person","name":"GenXdev","url":"https://daily.dev/devgenx","image":"https://media.daily.dev/image/upload/s--PrWOWtSq--/f_auto/v1789486214/avatars/avatar_ytCVp6dQicn9P0yKfhQCI?_a=BAMAMicg0"}},{"@type":"Comment","text":"If Linus can review AI-written kernel code, fine. The rest of us should probably keep the tests on 😅","datePublished":"2026-10-12T17:15:05.343Z","url":"https://daily.dev/posts/rXVrCcbLJ#c-Jm2f2RkbO","author":{"@type":"Person","name":"Risto Tõldsep","url":"https://daily.dev/ristotoldsep","image":"https://lh3.googleusercontent.com/a/ACg8ocLDWc6mZn0JwNmXXw6WY0L_HJ6pegzRttooC5VgtXESHSj3MNYx=s96-c"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/linus-torvalds-working-on-a-hefty-linux-kernel-improvement-with-claude-code-rxvrccblj#faq","mainEntity":[{"@type":"Question","name":"Is Linus Torvalds using AI tools to write Linux kernel code?","acceptedAnswer":{"@type":"Answer","text":"Yes, Torvalds used Claude Code, an AI coding assistant, to help write code, test programs, and conduct reviews for a new kernel branch called noref-filemap-read-with-llm. He stated in the kernel patch message that the code, test programs, review, and even the first draft of the cover letter were done with Claude Code under his direction, with measurements run on his own machine. Developers curious how AI assistants are entering kernel-level work can follow cases like this on daily.dev."}},{"@type":"Question","name":"What kernel performance problem does the noref-filemap-read-with-llm branch address?","acceptedAnswer":{"@type":"Answer","text":"It targets contention on folio reference counting when many threads perform small reads of a single file from the page cache. The patch series reworks memory management code to read from the page cache without taking folio references, which Torvalds reported produces a significant performance improvement, though the branch had not yet been merged into mainline. Engineers tracking kernel memory management changes can follow this work on daily.dev before it lands upstream."}}]} ```