Re: Stop false review statements

["Danilo Krummrich" <dakr@kernel.org>]

On Mon May 18, 2026 at 7:19 PM CEST, Roman Gushchin wrote:
>
>> On May 17, 2026, at 8:56 AM, Danilo Krummrich <dakr@kernel.org> wrote:
>> That said, I personally don't mind too much, I really like sashiko, which is
>> also why I asked for adding the driver-core list. My experience has been that it
>> does a very decent job in providing feedback for C code; my feeling is that
>> feedback for Rust code is not quite on par yet, but of course it also highly
>> depends on the complexity and scope of the corresponding changes.
>
> This is super interesting. An obvious idea is that the training set is
> relatively limited, if we’re talking rust for kernel code. Did you notice any
> common topics or patterns?

My experience is - and that's probably not surprising as it may tie back to the
relatively limited training set you mention above - that it sometimes loses
context at the FFI boundary, where it has to consider the semantics of the C and
the Rust APIs.

I think the difficult part is not necessarily that there is a language boundary
by itself, but rather that it can be difficult for LLMs to capture the semantic
layer that a Rust API puts on top of a C API in order to derive a safe API.

This also has been my experience in other LLM contexts; the most significant
improvements I saw in output quality have been by providing more semantic
context for the abstraction design.

Probably easy to look up, but does Sashiko consider cover letters already?

> Does it produce more false positives or worse in finding actual bugs in
> comparison to the c code?

I'd say both, and I think the reason is probably the same for both. But to be
fair, this is probably also biased by the class of changes I deal with on the C
and on the Rust side too.

It is also fair to say that in Rust we (almost) don't have whole classes of bugs
that we have on the C side; and the class of memory safety issues makes a huge
proportion of bugs on the C side.

If the model is particularly good at finding memory safety issues (and I think
it is), it of course also messes with the statistics of false positives
comparing C with Rust.

> I personally think that it’s always better to cc some mailing list and/or
> maintainers, so there is a second pair of eyes. I totally agree that replying
> just to the author is less effective.  Of course, we can add the text you’re
> proposing, but why not simply configure sashiko to cc the mailing list?

I'm not sure it addresses much of this concern, as I prefer to keep everyone the
patch (series) has been sent to explicitly in the loop.

Of course everyone has a different workflow, but I think it is fair to assume
that most people who are addressed directly follow along through their inbox and
not through the mailing list.

So, I think the real alternative is "reply all", which for multiple reasons I'm
not convinced is the right general call to make yet.

(I do consider it for one of the components I maintain though.)

Thanks,
Danilo