Linus Torvalds posts his first AI-assisted patch to the Linux kernel, synthetic test clocks 23x performance leap

What happened

The team is even changing its policy to no longer require that patch authors disclose they used an AI tool when generating their code. After a few revisions of his position on AI-assisted contributions to the Linux kernel, Linus Torvalds has posted his own first LLM (the kind of AI system trained on text to produce text)-assisted patch.

The development branch purports to fix an old issue with massive cache contention when many CPUs (the general-purpose processor at the centre of a computer) are reading the same file — a scenario potentially encountered when using shared libraries, databases, and web servers. Several developers had already made attempts over the years at fixing the issue, all with varied results, none quite ideal as an all-encompassing solution.

However, he recently took the plunge and decided to "try to actually solve this thing using an LLM." He's now posted his solution in a development branch, and claims that he's seen a 23x performance improvement in a dedicated synthetic benchmark, though he notes that actual real-world impact will be far less significant, as "no real load" will witness those figures.