On Sat, 16 May 2026, Roman Gushchin <[email protected]> wrote: >> On May 16, 2026, at 2:33 PM, Krzysztof Kozlowski <[email protected]> wrote: >> >> 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 history. > > This is simple not true: Sashiko is fully open-source, under Apache 2.0 > license > 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’s not a fundamental > limitation - > Sashiko is supporting various LLMs, including open models - it’s just a > practical > choice: to my knowledge the quality of open models is not on par with > frontier closed > models and it would require a non-trivial amount of hardware and > infrastructure 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. -- Jani Nikula, Intel
