Torvalds Let Claude Code Write 8 Kernel Patches: 3x Reads on One Laptop, Not Merged

Description and use

Linus Torvalds used Claude Code to create eight patches that triple small‑read throughput in the Linux page cache, but the changes remain unmerged.

Problem

Developers need a clear process for integrating AI‑written code into production kernels while maintaining accountability and reproducibility.

Outcome

The AI‑generated patches tripled small‑read throughput on a single laptop, demonstrating the potential of agent‑assisted kernel development, but the changes are not yet merged and include regressions.

Workflow

• 1. Author a branch name indicating AI authorship (e.g., noref-filemap-read-with-llm).
• 2. Generate code, tests, and a draft cover letter with Claude Code under human direction.
• 3. Run benchmarks on the author’s hardware and record results with precision.
• 4. Publish regressions alongside wins and maintain an open‑problems list.
• 5. Add an "Assisted‑by: LLM" trailer to commits and sign off manually.
• 6. Review agent‑written changes in small, isolated commits before merging.

Evidence

On his laptop, eight threads reading one file went from about 10 million to 30–33 million reads per second

Source

The cover letter credits Claude Code, Anthropic's coding agent, with the code, the test programs, the review behind the list of open problems, and the first draft of the cover letter itself

Source

The kernel's AI Coding Assistants guide asks contributions to carry an Assisted-by: LLM tag

Source