From: Roman Gushchin <roman.gushchin@linux.dev>
To: Krzysztof Kozlowski <krzk@kernel.org>
Cc: ksummit@lists.linux.dev
Subject: Re: [MAINTAINERS SUMMIT] The place of AI code review in the Linux Kernel process
Date: Fri, 17 Jul 2026 14:14:49 -0700 [thread overview]
Message-ID: <78346752-E2AC-4ACB-929D-70A45794474C@linux.dev> (raw)
In-Reply-To: <9e10dc4f-5d5c-4c20-831c-9137e719b337@kernel.org>
> On Jul 17, 2026, at 2:05 PM, Krzysztof Kozlowski <krzk@kernel.org> wrote:
>
> On 15/07/2026 18:55, Roman Gushchin wrote:
>> * Prompt development and testing.
>> Currently, prompts are maintained in two GitHub repositories and are
>> changed manually or with the help of AI coding agents. However, there is
>> no established practice for testing them, especially across various LLM
>> models. At the last LSFMMBPF conference, there was a discussion about
>> moving them into the kernel tree. I see some pros and cons to this
>> approach, but the ownership and testing models are not entirely clear.
>
> Prompts in a meaning how to parse kernel, work with it or produce
> reports: yeah, sure.
>
> Prompts teaching kernel code: I don't think so. I find it really
> incorrect approach to create a dedicated and duplicated basic knowledge
> for LLMs, instead of focusing on knowledge for developers. I understand
> that LLM has to be taught basics of C [1], but we should not duplicate
> kernel coding style or kernel rules into LLM-only instructions. Instead:
I agree.
I also experiment with Sashiko auto-creating prompts based on human
feedback in emails and initial results look promising. So maybe we don’t
even need to write too much manually for LLMs.
Thanks!
>
> 1. Fix docs or kerneldoc to have these properly documented,
> 2. Instruct LLM to read these documents.
>
> We do have tribal knowledge and it should be our kernel docs for the
> developers, first of all. If the knowledge is so important for LLM that
> it must be duplicated in prompts (just read some of the subsystem
> specifics at [2]), then maybe better add it to some guide "writing HID
> driver" or "common mistakes in Bluetooth", so developer writing such
> driver that will find it. And LLM too.
>
> I keep growing such codified and condensed (keep as short as possible)
> rules for subsystem I am part of [3] and LLM should read that one. LLM
> does not need dedicated doc, different than developers need. Well,
> except teaching C. [1] :)
This is awesome actually!
prev parent reply other threads:[~2026-07-17 21:15 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-15 16:55 [MAINTAINERS SUMMIT] The place of AI code review in the Linux Kernel process Roman Gushchin
2026-07-15 17:51 ` Miguel Ojeda
2026-07-15 21:37 ` Roman Gushchin
2026-07-17 6:43 ` Ben Copeland
2026-07-16 15:32 ` Sasha Levin
2026-07-15 17:56 ` Mauro Carvalho Chehab
2026-07-15 18:57 ` Jason Gunthorpe
2026-07-15 21:21 ` Roman Gushchin
2026-07-16 22:26 ` Mauro Carvalho Chehab
2026-07-17 23:17 ` Linus Torvalds
2026-07-18 0:01 ` Mark Brown
2026-07-18 1:09 ` Laurent Pinchart
2026-07-18 1:17 ` Linus Torvalds
2026-07-18 13:38 ` Arnaldo Melo
2026-07-18 14:14 ` Guenter Roeck
2026-07-18 16:15 ` SJ Park
2026-07-18 16:13 ` Jason Gunthorpe
2026-07-15 19:45 ` Dmitry Torokhov
2026-07-16 0:03 ` Steven Rostedt
2026-07-16 0:30 ` SJ Park
2026-07-17 21:05 ` Krzysztof Kozlowski
2026-07-17 21:14 ` Roman Gushchin [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=78346752-E2AC-4ACB-929D-70A45794474C@linux.dev \
--to=roman.gushchin@linux.dev \
--cc=krzk@kernel.org \
--cc=ksummit@lists.linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox