{"id":13830,"date":"2026-06-24T10:04:01","date_gmt":"2026-06-24T10:04:01","guid":{"rendered":"https:\/\/serisec.com\/index.php\/2026\/06\/24\/claude-fable-5-wrote-windows-kernel-code-in-rust-in-38-minutes\/"},"modified":"2026-06-24T10:04:01","modified_gmt":"2026-06-24T10:04:01","slug":"claude-fable-5-wrote-windows-kernel-code-in-rust-in-38-minutes","status":"publish","type":"post","link":"https:\/\/serisec.com\/index.php\/2026\/06\/24\/claude-fable-5-wrote-windows-kernel-code-in-rust-in-38-minutes\/","title":{"rendered":"Claude Fable 5 Wrote Windows Kernel Code in Rust in 38 Minutes"},"content":{"rendered":"<p>    Claude Fable 5 Wrote Windows Kernel Code in Rust in 38 Minutes<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/cybersecuritynews.com\/anthropic-claude-fable-5\/\" target=\"_blank\" rel=\"noreferrer noopener\">Anthropic\u2019s Claude Fable 5<\/a> generated a complete, bootable NT-compatible Windows kernel written in Rust called <em>ntoskrnl-rs<\/em> from an empty directory in just 38 minutes of active model work, raising profound questions about AI-authored trust and the future of critical infrastructure security.<\/p>\n<p class=\"wp-block-paragraph\">Documented by security researcher Matt Suiche and Tolmo\u2019s threat research on June 22, 2026, the project set out to rewrite <code>ntoskrnl<\/code>The Windows NT kernel, in Rust.<\/p>\n<p class=\"wp-block-paragraph\">Fable 5 handled the core scaffolding in a single contiguous session, producing approximately 5,100 lines of code across 27 files spanning the scheduler, memory manager, trap and interrupt machinery, object manager, and I\/O manager.<\/p>\n<p class=\"wp-block-paragraph\">The kernel successfully booted in the QEMU emulator and passed all 14 in-kernel self-tests, exiting with the project\u2019s standing pass contract: exit code 33.<\/p>\n<h2 id=\"h-claude-fable-5-wrote-windows-kernel-code\" class=\"wp-block-heading\"><strong>Claude Fable 5 Wrote Windows Kernel Code<\/strong><\/h2>\n<p class=\"wp-block-paragraph\">The wall-clock time across the full session was roughly four and a half hours, but most of that was the human operator away from the keyboard; the actual model-active work took 38 minutes.<\/p>\n<p class=\"wp-block-paragraph\">What distinguishes this from simple code generation is Fable 5\u2019s demonstrated capacity for unsupervised systems reasoning. The model caught two critical low-level bugs mid-generation without human intervention:<\/p>\n<ul class=\"wp-block-list\">\n<li>\n<strong>EOI ordering bug<\/strong>: It identified that the end-of-interrupt signal must be issued <em>before<\/em> a potential context switch, as preemption mid-dispatch would deadlock the local interrupt controller.<\/li>\n<li>\n<strong>IRQL emulation bug<\/strong>: When host tests returned 11\/12, Fable diagnosed that the interrupt request level (IRQL) emulation used a single global atomic across test threads, corrected it to a per-thread <code>thread_local<\/code> variable mirroring real per-CPU behavior, and passed 12\/12.<\/li>\n<\/ul>\n<p class=\"wp-block-paragraph\">The model also left architectural commentary embedded in the code explaining <em>why<\/em> the NT GDT selector ordering matches the <code>IA32_STAR<\/code> MSR format demonstrating forward-looking ABI reasoning, not pattern matching, <a href=\"https:\/\/tolmo.com\/blog\/when-the-model-writes-the-kernel\/\" target=\"_blank\" rel=\"noreferrer noopener\">reads Tolmo\u2019s report<\/a>.<\/p>\n<p class=\"wp-block-paragraph\">Fable 5 authored roughly 40% of the project\u2019s from-scratch code in only 3% of the total turns. The remaining 97% of turns eight days of iterative, debug-heavy bring-up ran on Claude Opus 4.8, which expanded the kernel to load unmodified Windows kernel drivers and run real Windows binaries including <code>sort.exe<\/code>, <code>choice.exe<\/code>, and <code>cmd.exe<\/code>.<\/p>\n<p class=\"wp-block-paragraph\">The model split was deliberate. Fable 5 carries aggressive cybersecurity safety classifiers broad enough to trip on adjacent defensive work. Notably, Fable shipped on June 10, 2026, as the public version of <a href=\"https:\/\/cybersecuritynews.com\/anthropics-mythos-ai-model\/\" target=\"_blank\" rel=\"noreferrer noopener\">Anthropic\u2019s Mythos<\/a> cybersecurity model, and within days, a US government export-control directive forced Anthropic to suspend access entirely.<\/p>\n<p class=\"wp-block-paragraph\">The kernel boots. It is not yet trusted. Fable 5 itself named the gap unprompted, flagging the dispatcher lock hand-off, spinlocks, and DPC queue as the highest-risk paths, and recommending <code>loom<\/code> for exhaustive concurrency exploration and <code>Miri<\/code> for undefined behavior detection.<\/p>\n<p class=\"wp-block-paragraph\">This is the critical security implication: authoring capability has outpaced verification. A model can produce the Trusted Computing Base of an x86_64 kernel faster than any human team can audit it.<\/p>\n<p class=\"wp-block-paragraph\">Until tooling like formal verification, property testing, and concurrency model checkers can close that gap, an AI-authored kernel remains a booting artifact of unknown correctness and unknown correctness has no place in a TCB.<\/p>\n<p class=\"wp-block-paragraph\">The internet\u2019s critical infrastructure runs on aging C codebases maintained largely because rewriting a TCB has historically been too costly and too risky. An AI-authored Rust kernel represents a double lever: Rust eliminates the memory-safety bug classes that dominate OS CVEs, while an AI model eliminates the human-cost bottleneck of the rewrite itself.<\/p>\n<p class=\"wp-block-paragraph\">Once verification tooling matures, the economic case for leaving legacy C in place collapses and large portions of the stack become candidates for AI-driven, memory-safe rewrites.<\/p>\n<p class=\"has-text-align-center has-background wp-block-paragraph\" style=\"background:linear-gradient(180deg,rgb(238,238,238) 91%,rgb(169,184,195) 100%)\"><strong>Follow us on\u00a0<a href=\"https:\/\/news.google.com\/publications\/CAAqMggKIixDQklTR3dnTWFoY0tGV041WW1WeWMyVmpkWEpwZEhsdVpYZHpMbU52YlNnQVAB?hl=en-IN&amp;gl=IN&amp;ceid=IN:en\" target=\"_blank\" rel=\"noreferrer noopener\">Google News<\/a>,\u00a0<a href=\"https:\/\/www.linkedin.com\/company\/cyber-news-live-\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">LinkedIn<\/a>,\u00a0and\u00a0<a href=\"https:\/\/x.com\/cyber_press_org\" target=\"_blank\" rel=\"noreferrer noopener\">X<\/a>\u00a0to Get More Instant Updates.<\/strong><\/p>\n<p>The post <a href=\"https:\/\/cybersecuritynews.com\/claude-fable-5-windows-kernel-code\/\">Claude Fable 5 Wrote Windows Kernel Code in Rust in 38 Minutes<\/a> appeared first on <a href=\"https:\/\/cybersecuritynews.com\/\">Cyber Security News<\/a>.<\/p>\n<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Guru Baran<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/cybersecuritynews.com\/claude-fable-5-windows-kernel-code\/\">Go to cyber-security-news<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Claude Fable 5 Wrote Windows Kernel Code in Rust in 38 Minutes Anthropic\u2019s Claude Fable 5 generated a complete, bootable NT-compatible Windows kernel written in Rust called ntoskrnl-rs from an empty directory in just 38 minutes of active model work, raising profound questions about AI-authored trust and the future of critical infrastructure security. Documented by [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[129,63],"tags":[130],"class_list":["post-13830","post","type-post","status-publish","format-standard","hentry","category-cyber-security","category-cyber-security-news","tag-cyber-security-news"],"_links":{"self":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts\/13830"}],"collection":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/comments?post=13830"}],"version-history":[{"count":0,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts\/13830\/revisions"}],"wp:attachment":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/media?parent=13830"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/categories?post=13830"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/tags?post=13830"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}