Linus Torvalds published an experimental Linux kernel patch series that he built with Claude Code
Linus Torvalds published an experimental eight-patch series on a branch called noref-filemap-read-with-llm. According to the commit message dated October 10, the code, the test programs, the review and the first draft of the text were done with an LLM coding assistant (Claude Code) “under my direction.” The measurements were run on his own machine.
It targets folio reference count contention when many threads make small reads of one file. Memory removed from the page cache is freed only after an RCU grace period, so reads can copy without a reference. On Torvalds’ laptop, eight threads went from about 10 million to 30-33 million reads per second. A 10-patch rcu-free-v3 version dated October 13, including two patches by Kiryl Shutsemau, reports 13.3 million to 304 million reads per second with 64 threads on a Threadripper.
The patches have not been merged. Torvalds calls the memory waiting to be freed “the part of this series that is least solved.”
Sources
- Linus Torvalds (linux.git, kernel.googlesource.com aynası), “mm: read from the page cache without folio references”, Original commit; Claude Code disclosure, laptop measurements and list of known problems, (kernel.googlesource.com)
- Linus Torvalds (torvalds/linux, GitHub), “mm/filemap: read from the page cache without folio references”, Revised version on the rcu-free-v3 branch; Assisted-by: LLM tag and Threadripper measurements, (github.com)
- Phoronix, “Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code”, First report to spot the branch, (phoronix.com)
- Linuxiac, “Linus Torvalds Experiments with AI-Generated Kernel Code, Sees 3x Speedup”, Summary of the patches and laptop measurements, (linuxiac.com)
About this story
Spotted an error in this story? [email protected] · Instagram
Short link: thejarrus.com/en/torvalds-claude-code
This story in Turkish: Linus Torvalds, Claude Code ile hazırladığı deneysel bir Linux çekirdeği yama serisini yayımladı
On the same topic
NTT Data is in the final stages of talks to build Anthropic’s first data center in Japan, Nikkei reports
Nikkei says NTT Data is close to a deal to build an Osaka data center for Anthropic with up to 500 MW of power and construction costs of up to ¥1 trillion.
Anthropic says small AI models may be months away from being able to self-replicate on IoT devices
An Anthropic Frontier Red Team report says small models may soon be able to copy themselves onto devices such as smart ovens and Android TV boxes.
Anthropic says its new distillation defenses have cut the data harvested from Claude by around 90 to 99 percent
Anthropic says preserved thinking, restricted reasoning access and a two-stage classifier have cut the data distillers harvest from Claude by 90-99%.