--- title: AI helped a Linux developer find bottlenecks in the... description: A Linux kernel developer, Stoakes, used an LLM to help identify bottlenecks in the kernel, finding that the AI was much better at locating the problem than at... canonical: https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AI helped a Linux developer find bottlenecks in the kernel, but the code it made to fix it was "hideous" | daily.dev og:description: A Linux kernel developer, Stoakes, used an LLM to help identify bottlenecks in the kernel, finding that the AI was much better at locating the problem than at... og:url: https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq og:image: https://api.daily.dev/og/posts/nsQhZr2pQ.png og:image:alt: AI helped a Linux developer find bottlenecks in the kernel, but the code it made to fix it was "hideous" 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. # AI helped a Linux developer find bottlenecks in the kernel, but the code it made to fix it was "hideous" **[XDA Developers](https://daily.dev/sources/xda-developers)** · 2 min read · 0 upvotes · 0 comments ## Summary A Linux kernel developer, Stoakes, used an LLM to help identify bottlenecks in the kernel, finding that the AI was much better at locating the problem than at generating clean fixes. The AI-generated code was described as 'hideous' and required extensive auditing, rewriting, and manual editing of commit messages before it could be merged. Despite the messy code, the resulting fixes delivered major performance gains: allmodconfig builds up to 36% faster, incremental builds up to ~70% faster, and noop builds up to ~90% faster. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much faster are Linux kernel builds after fixing the bottlenecks an AI helped identify? Allmodconfig builds became up to 36% faster, incremental builds up to roughly 70% faster, and noop builds up to about 90% faster. A kernel developer named Stoakes used an LLM to locate the bottlenecks, then manually rewrote and audited the AI-generated fixes before merging them, since the raw AI code was messy and required heavy editing. _Developers weighing AI-assisted performance work can follow real-world kernel results like this on daily.dev._ ### Is AI-generated code reliable enough to merge directly into the Linux kernel? No, according to one kernel developer's experience, AI-generated fixes were described as hideous and required extensive auditing, rewriting, and edits to commit messages, the cover letter, and comments before they were acceptable. The LLM was far more useful for pinpointing where bottlenecks existed than for producing clean, mergeable code to fix them. _Anyone deciding how much to trust AI-generated code can track examples like this via daily.dev._ ## Similar posts on daily.dev - [AI Made A Lot Of "Hideous" Code But Found Major Bottlenecks For Faster Linux Compilation](https://daily.dev/posts/ai-made-a-lot-of-hideous-code-but-found-major-bottlenecks-for-faster-linux-compilation-c9ex1mqlu) · Phoronix · 0 upvotes · 0 comments - [Linux development is really benefiting from AI, but not from its coding](https://daily.dev/posts/linux-development-is-really-benefiting-from-ai-but-not-from-its-coding-waryldg10) · XDA Developers · 1 upvotes · 0 comments - [Torvalds: AI is fine for competent devs, but spare us the 'drive-by' patches](https://daily.dev/posts/torvalds-ai-is-fine-for-competent-devs-but-spare-us-the-drive-by-patches-vdbe02qam) · The Register · 1 upvotes · 0 comments --- Tags: [#linux](https://daily.dev/tags/linux), [#performance](https://daily.dev/tags/performance), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq) ```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":"AI helped a Linux developer find bottlenecks in the kernel, but the code it made to fix it was \"hideous\"","url":"https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq"},"datePublished":"2026-09-09T04:33:34.837Z","dateModified":"2026-09-09T13:19:15.129Z","description":"A Linux kernel developer, Stoakes, used an LLM to help identify bottlenecks in the kernel, finding that the AI was much better at locating the problem than at...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/43f860ad905b30969d5599258bcabdcf?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/43f860ad905b30969d5599258bcabdcf?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","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":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"linux,performance,code-review","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"AI helped a Linux developer find bottlenecks in the kernel, but the code it made to fix it was \"hideous\""}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ai-helped-a-linux-developer-find-bottlenecks-in-the-kernel-but-the-code-it-made-to-fix-it-was-hide-nsqhzr2pq#faq","mainEntity":[{"@type":"Question","name":"How much faster are Linux kernel builds after fixing the bottlenecks an AI helped identify?","acceptedAnswer":{"@type":"Answer","text":"Allmodconfig builds became up to 36% faster, incremental builds up to roughly 70% faster, and noop builds up to about 90% faster. A kernel developer named Stoakes used an LLM to locate the bottlenecks, then manually rewrote and audited the AI-generated fixes before merging them, since the raw AI code was messy and required heavy editing. Developers weighing AI-assisted performance work can follow real-world kernel results like this on daily.dev."}},{"@type":"Question","name":"Is AI-generated code reliable enough to merge directly into the Linux kernel?","acceptedAnswer":{"@type":"Answer","text":"No, according to one kernel developer's experience, AI-generated fixes were described as hideous and required extensive auditing, rewriting, and edits to commit messages, the cover letter, and comments before they were acceptable. The LLM was far more useful for pinpointing where bottlenecks existed than for producing clean, mergeable code to fix them. Anyone deciding how much to trust AI-generated code can track examples like this via daily.dev."}}]} ```