Re: Stop false review statements

On Sat, 16 May 2026, Roman Gushchin <[email protected]> wrote:
>> On May 16, 2026, at 2:33=E2=80=AFPM, Krzysztof Kozlowski <[email protected]=
g> wrote:
>>=20
>> I find it opposite: clogging commits with useless information, because
>> some arbitrary and completely closed-source tool did analysis means
>> nothing to me one year later when I look at the commit in the Git histor=
y.
>
> This is simple not true: Sashiko is fully open-source, under Apache 2.0 l=
icense
> and the code belongs to LF. Yes, the instance behind sashiko.dev is using
> Gemini 3.1 Pro LLM, which is not open-source, but it=E2=80=99s not a fund=
amental limitation -=20
> Sashiko is supporting various LLMs, including open models - it=E2=80=99s =
just a practical
> choice: to my knowledge the quality of open models is not on par with fro=
ntier closed
> models and it would require a non-trivial amount of hardware and infrastr=
ucture to run
> an open model at the required scale.

In the context of the "Reviewed-by: Sashiko" discussion, this actually
makes it really hard to assess the quality of those reviews. It is
*currently* using a boatload of tokens with a specific LLM, and I find
it's often asking pretty good questions.

People build their reviewer track record and gain trust over time, but
the reviews from what is portrayed as "Sashiko" heavily depend on the
models and resources spent in the background. As a maintainer, it's far
easier (though still laborous) to deal with the negative feedback from
LLMs than the positive, because you won't really know how rigorous the
review was when the response is just "LGTM".


BR,
Jani.

--=20
Jani Nikula, Intel