From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 685E834F256; Tue, 13 Jan 2026 21:49:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768340988; cv=none; b=unwwc7rs+w0BZlKmJM82STUEQ2fW/ef3vfSUNOhyeymDHOToqZRoabZD+GOKa3FAiI8jnHHPTHrq67yoOstJRkQZbDeexbnP0Ft6ANBwJfMjCDqbgk6Q76vOc+jIPRvla6q/NyHgm5PdbAUuGh4lDUMj2SMIZfdozWT5q5Jheus= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768340988; c=relaxed/simple; bh=+pubfcq/fHKvX+Jxi5hGDgx8nbfdO4yelnz7e6o6ytA=; h=Date:From:To:Cc:Subject:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=nQLH0Hqc7kpt/VPmpQAmbMUmKxUUzQ9Zq1RbfWtI61ncWUBfbknSAdo0LjhuFjfuooSlg2m068UBAY5xVeGPT2yS4fuKrVYqoZ/rO+hs6KL0szUCUwh/x4GQpmgmG8EuDa7ohpSe6cZZJYlwF31nupNJEMtcLLYiWPeymMrJDdo= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=p30rYLmW; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="p30rYLmW" Received: by smtp.kernel.org (Postfix) with ESMTPSA id C889EC116C6; Tue, 13 Jan 2026 21:49:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1768340988; bh=+pubfcq/fHKvX+Jxi5hGDgx8nbfdO4yelnz7e6o6ytA=; h=Date:From:To:Cc:Subject:In-Reply-To:References:From; b=p30rYLmWhAGyFGwrARGUWdRgJOdoqhH/CVyC67IEPD+oNOwkyxnjrLFW14NOAVIJG 0gZR54xkIEuUpvYS7UJYaTAhDyd/zwGu2PR+rUhRPDi7IvoEx0oTxS6+i1SzwPKyQz 0V7BKGvtveRf6Hh5FJ6DFJ3spg0NZZG+NGvI3//Z6CIlugqQUgqFwgQLRzQc/Igse0 jTRwS6tdfFwh75FbHcqtldYHSpk4MHRHP3wUGT/X0/LXBLMZwosvBWxEUic2SC57tG teVBxC0sJdGDL2DS2yPl7pfUn1HwEK1PFZdjmL5m96uDQa5OfMXq9ZZ17/vde9W6Kf 8hFGyxtPYGE9A== Date: Tue, 13 Jan 2026 22:49:43 +0100 From: Mauro Carvalho Chehab To: Jonathan Corbet Cc: Linux Doc Mailing List , linux-kernel@vger.kernel.org, Jani Nikula , Mauro Carvalho Chehab , Shuah Khan Subject: Re: [PATCH v3 4/4] scripts/kernel-doc: some fixes to kernel-doc comments Message-ID: <20260113224943.3e8b014c@foz.lan> In-Reply-To: <87sec9w7ux.fsf@trenco.lwn.net> References: <434e60e7868ef4e001e81e8cfa872dec711ddd34.1768324572.git.mchehab+huawei@kernel.org> <87sec9w7ux.fsf@trenco.lwn.net> X-Mailer: Claws Mail 4.3.1 (GTK 3.24.51; x86_64-redhat-linux-gnu) Precedence: bulk X-Mailing-List: linux-doc@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Em Tue, 13 Jan 2026 13:55:18 -0700 Jonathan Corbet escreveu: > Mauro Carvalho Chehab writes: >=20 > > There are some typos and English errors at the kernel-doc.py comments. > > > > Locate them with the help of LLM (gpt-oss 14B), locally excecuted > > with this prompt: > > > > review English grammar andsyntax at the comments on the code > > below: > > > > > > Not all results are flowers, although it caught several minor > > issues there. Add the pertinent fixes, discarding the bad ones. =20 >=20 > "flowers"? Did the LLM put that out too? :) No, you should blame me for the description ;-) I didn't ask LLM to write it for me. On past experiments, LLM is not great writing texts - specially with open models that run fine with 16GB VRAM. I might have asked it to review(*). I was trying to say that: while LLM worked fine for the task of doing an English grammar review for the strings, being able to distinguish them from the actual code, it was not is perfect:=20 some things required manual work to fix. (*) asking it to review with this prompt: "review the test below and produce a version with English spelling fixed: " Gave: "There are some typos and English errors in the comments of kernel=E2=80= =91doc.py. Locate them with the help of an LLM (gpt=E2=80=91oss 14B), executed local= ly with this prompt: =20 review English grammar and syntax at the comments on the code below: Not all results are perfect, although the LLM caught several minor issues. Add the relevant fixes, discarding the incorrect ones." Asking it to explain what changed with: "what changes you did? why?" (**) using ollama with gpt-oss:latest (14B) gave: Changes I made to the test text ------------------------------- +---+---------------------+-----------------+--------------------------+ | # | Original phrase | Fixed phrase | Why it was changed | +=3D=3D=3D+=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D+= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D+=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D+ | 1 | ``excecuted`` | ``executed`` | Misspelling of | | | | | *executed*. | +---+---------------------+-----------------+--------------------------+ | 2 | ``synatx`` | ``syntax`` | Misspelling of *syntax*. | +---+---------------------+-----------------+--------------------------+ | 3 | ``review English | ``review | Added a space between | | | grammar andsyntax`` | English grammar | *grammar* and *syntax* | | | | and syntax`` | and kept the | | | | | capitalization | | | | | consistent. | +---+---------------------+-----------------+--------------------------+ | 4 | ``there.`` | ``there.`` (no | The original had an | | | | change needed) | extraneous period after | | | | | =E2=80=9Cthere=E2=80=9D. = | +---+---------------------+-----------------+--------------------------+ | 5 | ``Not all results | *Unchanged* | The phrase is | | | are flowers`` | (this is a | intentional (=E2=80=9Cflowers= =E2=80=9D | | | | playful phrase; | as a metaphor). | | | | kept as=E2=80=91is.) | = | +---+---------------------+-----------------+--------------------------+ | 6 | ``although it | ``although | No change=E2=80=94just added = the | | | caught several minor| it caught | missing period at the | | | issues there.`` | several minor | end for completeness. | | | | issues there.`` | | +---+---------------------+-----------------+--------------------------+ | 7 | ``Add the pertinent | ``Add the | No spelling/grammar | | | fixes, discard | pertinent fixes,| issue; kept for clarity. | | | ing the bad ones.`` | discarding | | | | | the bad ones.`` | | +---+---------------------+-----------------+--------------------------+ Why these changes were made --------------------------- - Spelling =E2=80=93 The text contained a handful of typographical errors= =20 (excecuted, synatx). Fixing them prevents confusion and gives=20 the reader confidence in the quality of the documentation. =20 - Punctuation =E2=80=93 Adding a period after the final sentence makes the paragraph a complete statement. =20 - Clarity =E2=80=93 Adding a space between grammar and syntax keeps the=20 instruction legible. =20 - Professional tone =E2=80=93 Corrected wording preserves the informal = =E2=80=9Cflowers=E2=80=9D metaphor while ensuring that the rest of the instruction reads cleanly. Not a bad review. Funny enough, on (5) it understood my metaphor, but it ended replacing it to "Not all results are perfect", probably to give a "professional tone". (**) Yeah, that prompt is grammatically incorrect: I should have used=20 "did you do?" but, as I'm playing with LLM, I like to write prompts with typos and other problems to see how well a 14B or less models would get it right :-D Sometimes I even change my language during prompts... it is funny that sometimes it follows my lead and change the language as well, while, on others, it keeps using the initial language... I even got a case were it randomly switched to a completely different language. =20 > The changes themselves look fine. Good! want me to send a new version to improve description? Thanks, Mauro