A collection of articles, discussions, and quotes about Sashiko across the community and tech media.
Direct discussions and feedback from the Linux kernel community.
"But I think that lately quite a noticeable percentage of reports have become very much valid. As you say, Sashiko tends to be quite good. Even when it flags something unnecessarily and there's no actual problem, there's likely to be a reason for the question. And we've seen some truly stellar reports too. Things that are deep and subtle, and the AI is 100% correct. So anybody who thinks that all AI is slop is in denial about the current state." — Linus Torvalds
"Rule #1 is, surely, 'don't add bugs'. This thing finds bugs. If its hit rate is 50% then that's plenty high enough to justify people spending time to go through and check its output. [...] That's a really high hit rate! How can we possibly not use this, if we care about Rule #1?" — Andrew Morton
"I read through the AI debug logs. What steps it took to reason that the fix is correct, and it convinced me that I'm wrong. Applied." — Alexei Starovoitov
In-depth coverage from the premier Linux news source.
- Development tools: Sashiko, b4 review, and API specification
- The Sashiko patch-review system
- The role of LLMs in patch review
- Exelbierd: What's actually in a Sashiko review?
Coverage in widely read technical publications.
- The Register: Sashiko code review linux
- The Register: Greg Kroah-Hartman AI kernel
- Phoronix: Sashiko Linux AI Code Review
- Phoronix: Sashiko AI Reviewing Rust Linux
- Bexelbie: What's in a Sashiko review
- Let's Data Science: Sashiko generates preexisting bug noise for maintainers
- Top AI Product: Sashiko caught 53% of Linux kernel bugs...
- Gigazine: Sashiko Linux bug AI