Linus Torvalds tests AI coding tool on Linux kernel
The Linux creator used Anthropic's Claude Code on a long-running kernel performance problem, but reviewers later flagged a race condition in the patches.
By Standard Topic. AI-generated from the reporting listed under Coverage. Published . Updated .
This story is no longer being updated. It reflects reporting up to .
What happened
Linux creator Linus Torvalds has begun relying on AI for kernel work, with Anthropic's Claude Code taking on a page cache performance problem that developers had wrestled with for over two years. His 10-patch series reported a 23-fold throughput gain in a synthetic benchmark, but reviewers later found a race. The changes remain experimental and are not yet in the official kernel, and kernel developers also dropped a rule requiring contributors to disclose AI tool use.
Why it matters
The changes are still experimental and have not been merged into the official Linux kernel. Torvalds said contributors need to grasp the code they submit, regardless of tooling.
Coverage
- Linus Torvalds let Claude Code fix the Linux page cache. Then reviewers found a race. (thenewstack.io)
- Linux kernel devs drop obligatory confession of AI tool usage (theregister.com)
More from Technology & AI
- Eight states sue OpenAI, alleging misleading AI safety claims
- OpenAI announces solution to Navier-Stokes math problem
- Datadog bets AI agents can handle testing of AI-written code
- Anthropic and OpenAI sketch wealth-sharing plans before IPOs
- Mamdani administration proposes AI customer service rules
- Florida engineers study how AI behaves in high-risk situations