That is both really useful and a great example of why they should have stopped writing code in C decades ago. So many kernel bugs have arisen from people adding early returns without thinking about the cleanup functions, a problem that many other language platforms handle automatically on scope exit.
That's cool. Another interesting metric, however, would be the false positive ratio: like, I could just build a bogus system that simply marks everything as a bug and then claim "my system found 100% of all bugs!"
In practice, not just the recall of a bug finding system is important but also its precision: if human reviewers get spammed with piles of alleged bug reports by something like Sashiko, most of which turn out not to be bugs at all, that noise binds resources and could undermine trust in the usefulness of the system.
Looks cool, but this site is a bit difficult for me to grok.
I think the table might be slightly inside-out? The Status column appears to show internal pipeline states ("Pending", "In Review") that really only matter to the system, while Findings are buried in the column on the far right. For example, one reviewed patchset with a critical and a high finding is just causally hanging out below the fold. I couldn't immediately find a way to filter or search for severe findings.
It might help to separate unreviewed patches from reviewed ones, and somehow wire the findings into the visual hierarchy better. Or perhaps I'm just off base and this is targeting a very specific Linux kernel community workflow/mindset.
I think this is a great and interesting project. However, I hope that they're not doing this to submit patches to the kernel. It would be much better to layer in additional tests to exploit bugs and defects for verification of existance/fixes.
(Also tests can be focused per defect.. which prevents overload)
From some of the changes I'm seeing: This looks like it's doing style and structure changes, which for a codebase this size is going to add drag to existing development. (I'm supportive of cleanups.. but done on an automated basis is a bad idea)
No, it's reviewing patches posted on LKML and offering suggestions. The original patch posted corresponding to your link was this, which was (presumably!) written by a human:
Style and structure is not the goal here, the reason people are interested in it is to find bugs.
Having said that, if it can save maintainers time it could be useful. It's worth slowing contribution down if it lets maintainers get more reviews done, since the kernel is bottlenecked much more on maintainer time than on contributor energy.
My experience with using the prototype is that it very rarely comments with "opinions" it only identifies functional issues. So when you get false positives it's usually of the form "the model doesn't understand the code" or "the model doesn't understand the context" rather than "I'm getting spammed with pointless advice about C programming preferences". This may be a subsystem-specific thing, as different areas of the codebase have different prompts. (May also be that my coding style happens to align with its "preferences").
Have you ever programmed with AI? It needs a lot of hand holding for even simple things sometimes. Forgets basic input, does all kinds of brain dead stuff it should know not to do.
Both the curl and the SQLite project have been overburdened by AI bug reports.
Unless the Google engineers take great care to review each potential bug for validity the same fate might apply here. There have been a lot of news regarding open source projects being stuffed to the brim with low effort and high cost merge requests or issues.
You just don't see all the work that is caused unless you have to deal with the fallout...
This project has nothing to do with bug reports... it's an opt-in tool for reviewing proposed changes that kernel developers can decide to use (if they find it useful).
well tbf code review is probably the most useful part of "AI coding", if it catches even a single bug you missed its worth it, plus false positives would waste dev time but not pollute the kernel
We've already seen how bug bounty projects were closed by AI spam; I think it was curl? Or some other project I don't remember right now.
I think AI tools should be required, by law, to verify that what they report is actually a true bug rather than some hypothetical, hallucinated context-dependent not-quite-a-real-bug bug.
For an example of a review (picked pretty much at random) see: https://sashiko.dev/#/patchset/20260318151256.2590375-1-andr...
The original patch series corresponding to that is: https://lkml.org/lkml/2026/3/18/1600
Edit: Here's a simpler and better example of a review: https://sashiko.dev/#/patchset/20260318110848.2779003-1-liju...
I'm very glad they're not spamming the mailing list.
That's cool. Another interesting metric, however, would be the false positive ratio: like, I could just build a bogus system that simply marks everything as a bug and then claim "my system found 100% of all bugs!"
In practice, not just the recall of a bug finding system is important but also its precision: if human reviewers get spammed with piles of alleged bug reports by something like Sashiko, most of which turn out not to be bugs at all, that noise binds resources and could undermine trust in the usefulness of the system.
I think the table might be slightly inside-out? The Status column appears to show internal pipeline states ("Pending", "In Review") that really only matter to the system, while Findings are buried in the column on the far right. For example, one reviewed patchset with a critical and a high finding is just causally hanging out below the fold. I couldn't immediately find a way to filter or search for severe findings.
It might help to separate unreviewed patches from reviewed ones, and somehow wire the findings into the visual hierarchy better. Or perhaps I'm just off base and this is targeting a very specific Linux kernel community workflow/mindset.
Just my 1c.
Reviewers are more likely to instead subscribe to get the review inline, and then potentially incorporate that with their feedback.
You sound like a troglodyte.
(Also tests can be focused per defect.. which prevents overload)
From some of the changes I'm seeing: This looks like it's doing style and structure changes, which for a codebase this size is going to add drag to existing development. (I'm supportive of cleanups.. but done on an automated basis is a bad idea)
I.e. https://sashiko.dev/#/message/20260318170604.10254-1-erdemhu...
https://lkml.org/lkml/2026/3/9/1631
Having said that, if it can save maintainers time it could be useful. It's worth slowing contribution down if it lets maintainers get more reviews done, since the kernel is bottlenecked much more on maintainer time than on contributor energy.
My experience with using the prototype is that it very rarely comments with "opinions" it only identifies functional issues. So when you get false positives it's usually of the form "the model doesn't understand the code" or "the model doesn't understand the context" rather than "I'm getting spammed with pointless advice about C programming preferences". This may be a subsystem-specific thing, as different areas of the codebase have different prompts. (May also be that my coding style happens to align with its "preferences").
>"good catch - thanks for pointing that out"
We've already seen how bug bounty projects were closed by AI spam; I think it was curl? Or some other project I don't remember right now.
I think AI tools should be required, by law, to verify that what they report is actually a true bug rather than some hypothetical, hallucinated context-dependent not-quite-a-real-bug bug.