Rules for AI coding assistants working with the Linux kernel codebase

The NetBSD developers have a significantly more sane approach.

“Code generated by a large language model or similar technology, such as GitHub/Microsoft's Copilot, OpenAI's ChatGPT, or Facebook/Meta's Code Llama, is presumed to be tainted code, and must not be committed without prior written approval by core.”

https://www.netbsd.org/developers/commit-guidelines.html

> files for various AI coding assistants (Claude, GitHub Copilot, Cursor, Codeium, Continue, Windsurf, and Aider). These are all symlinked to a central documentation file

I really hope some standard emerges soon, because we've also checked in several symlinks at work depending on different people's preferences (plus I create a local one when I test a new tool) and it's a little frustrating they can't play nicely together.

https://lore.kernel.org/lkml/20250725175358.1989323-2-sashal... part2 https://lore.kernel.org/lkml/20250725175358.1989323-3-sashal... part 3