From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from out-172.mta0.migadu.com (out-172.mta0.migadu.com [91.218.175.172]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 93A7A394792 for ; Fri, 17 Jul 2026 21:15:05 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=91.218.175.172 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1784322907; cv=none; b=CZ2BJYfgRwZKr2rz8YgBR0IUOiJOmFnoxA1DoH3s8aTJkOrNW4Jq0LoYJn5LeKnUzpcdK+OdsUhBBQ40yOaTtPNfJYL9ug7nWOEUe8KoVM9WxOGbd7TbYcX3k1AL3VNMOzd88kClq4wsk5VKbERGyIDJwXihvvyalZnoRTsaAZQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1784322907; c=relaxed/simple; bh=Dzu/rrAyRbstNbH/DkwgGDJe8ds/HYUrn7FIvemPGlk=; h=Content-Type:Mime-Version:Subject:From:In-Reply-To:Date:Cc: Message-Id:References:To; b=SOEifBXOibGCEmfSpwpkR173KQUauNszziKGSXEHs3tF4k/pptiP0ZGw2R1sMGoTnRIdMaOR/kK05EBdgup4nnS+KeHPm+ocKYr1XaSIqKm2KAfjN7TFe9xkrwxLwlxCkswxgtOGsK5lC/FqSyFuWAmemq6OZYSTUc6kwA4ujeY= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=maof7CI/; arc=none smtp.client-ip=91.218.175.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="maof7CI/" Content-Type: text/plain; charset=utf-8 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1784322903; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Dzu/rrAyRbstNbH/DkwgGDJe8ds/HYUrn7FIvemPGlk=; b=maof7CI/1sutO4P1tRRedCERqpdO2E34+lKgGMOLBQXmfiiskDF/nUSIR2Kv750AtyLvDJ XEl92eW59Cjv1l6FFui0QqoZzrbk9aqXNG12PPAEJAQpr/5/5HD6GK5a9M9OMb78/XMNLx mdiGpA5vNK3+yBHSVsOXxjiVnLNWey8= Content-Transfer-Encoding: quoted-printable Precedence: bulk X-Mailing-List: ksummit@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 (1.0) Subject: Re: [MAINTAINERS SUMMIT] The place of AI code review in the Linux Kernel process X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. From: Roman Gushchin In-Reply-To: <9e10dc4f-5d5c-4c20-831c-9137e719b337@kernel.org> Date: Fri, 17 Jul 2026 14:14:49 -0700 Cc: ksummit@lists.linux.dev Message-Id: <78346752-E2AC-4ACB-929D-70A45794474C@linux.dev> References: <9e10dc4f-5d5c-4c20-831c-9137e719b337@kernel.org> To: Krzysztof Kozlowski X-Migadu-Flow: FLOW_OUT > On Jul 17, 2026, at 2:05=E2=80=AFPM, Krzysztof Kozlowski = wrote: >=20 > =EF=BB=BFOn 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. >=20 > Prompts in a meaning how to parse kernel, work with it or produce > reports: yeah, sure. >=20 > 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=E2=80= =99t even need to write too much manually for LLMs. Thanks! >=20 > 1. Fix docs or kerneldoc to have these properly documented, > 2. Instruct LLM to read these documents. >=20 > 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. >=20 > 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!=