Ian RogersMar 17
I've been helping the team that have brought up https://sashiko.dev/ for AI generated LKML reviews. It's really impressive to see the wider set of issues that the AI reviews can bring up, and this will help with the quality of code in the Linux code base. #sashiko_dev #linux
Sashiko

Show threadAlex BradburyMar 27

@irogers this is really neat! I started playing with it to see how well an open weight model like Kimi K2.5 does on the included benchmarks.

Is the team looking at introducing additional tools (static analysis, clang-format, even a built kernel binary + qemu + debugger?) as part of the process?

Show threadJohn RegehrApr 4
@asb @irogers this is super interesting. do you have results yet? what platform are you running Kimi on?
Show threadAlex Bradbury
@regehr @irogers here are my notes (I guess from a week ago already) https://gist.github.com/asb/c4ecf2ebb55570ce63168b8248ab5f2d from the smallest sashiko benchmark set and a somewhat "vibed" setup.. But I need to return to this now https://github.com/sashiko-dev/sashiko/pull/21 landed and try something a bit more thorough. Early indications were promising even if output format issues tripped it up. I'm interested to try with GLM-5 / 5.1 too. Kimi is via a subscription at https://synthetic.new/
Incomplete very quick experiment of sashiko with Kimi K2.5

Incomplete very quick experiment of sashiko with Kimi K2.5 - sashiko_test_notes.md

Gist
Apr 4 at 8:30pmWeb
Show threadAlex BradburyApr 4
@regehr @irogers my starting point had been reading https://lwn.net/Articles/1063303/ which raised the question of what if Google stop contributing the compute, but I felt it was a shame it didn't characterise how much compute is needed per review. I hadn't looked at the Sashiko prompts before - it is a more heavyweight (in terms of token count) process than I might have guessed.
Development tools: Sashiko, b4 review, and API specification

The kernel project has a unique approach to tooling that avoids many commonly used development [...]

LWN.net
Show threadJohn RegehrApr 4
@asb @irogers thanks!