From: Rik van Riel <riel@surriel.com>
To: "Lorenzo Stoakes (ARM)" <ljs@kernel.org>
Cc: David Hildenbrand <david@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Jason Gunthorpe <jgg@ziepe.ca>, Peter Xu <peterx@redhat.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
kernel-team@meta.com, Aristeu Rozanski <aris@ruivo.org>
Subject: Re: [PATCH RFC] mm/gup: batch contiguous pages in follow_page_mask() and return them via a pages array
Date: Sat, 01 Aug 2026 08:25:50 -0400 [thread overview]
Message-ID: <517bf6a8072a6e66f28f8ec08bec4b604f29491d.camel@surriel.com> (raw)
In-Reply-To: <am2_dWJKZBzwd8EK@lucifer>
On Sat, 2026-08-01 at 10:54 +0100, Lorenzo Stoakes (ARM) wrote:
>
> Thanks for doing a human pass but it LLM's habits really carried
> through
> here. In general:
>
> - No walls of text please - fewer words are better, clarity is king.
>
> - Don't write the code in English as a comment/commit msg - redudant
> and
> distracting.
>
> - Sensible patch separation obviously please.
>
> - Write as elegant/reasonable code as possible. If the code you touch
> was
> some horrible mega-function, take the time to refactor it. Pay down
> technical debt.
>
> These are all things LLMs are extremely bad at (even fable). So they
> need
> to be done by a human.
LLMs can apply those rules, when expressed in a way
that they get interpreted unambiguously by the LLM.
I'm slowly building up a collection of such rules
in the kernel-style repository.
AI can write in any style you ask it to.
/*
* Long in the Halls of Rq the weary wait,
* till __schedule, herald of the turning years,
* calls forth the next to walk the road of fate
* as prev fades west.
*/
AI can also flag such issues, once it knows to
look for them.
>
> >
> > In order for them to produce code that is at least a
> > good starting point for editing, they need to follow
> > rules.
> >
> > Once you apply the rules, Opus and Sonnet do not
> > produce results that are all that different from
> > each other.
> >
> > I just added a few new rules, so the tooling won't
> > even let me create too-large patches any more.
>
> I mean, sure, but what's needed here is human Rik :)
The 80/20 rule comes into play here.
If AI produces junk, the person starting with
LLM-produced code can spend days cleaning it
up, without getting things in a reasonable state.
If the AI produces a better starting point, the
remaining issues will stand out like a sore thumb,
and it's much easier to find and fix them.
I agree there will always be a need for human
judgment, but that doesn't mean we should not
improve our tooling.
--
All Rights Reversed.
next prev parent reply other threads:[~2026-08-01 12:26 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-30 7:53 Rik van Riel
2026-07-31 12:33 ` Lorenzo Stoakes (ARM)
2026-07-31 18:32 ` Rik van Riel
2026-08-01 9:54 ` Lorenzo Stoakes (ARM)
2026-08-01 12:25 ` Rik van Riel [this message]
2026-08-03 12:33 ` David Hildenbrand (Arm)
2026-08-03 14:44 ` Lorenzo Stoakes (ARM)
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=517bf6a8072a6e66f28f8ec08bec4b604f29491d.camel@surriel.com \
--to=riel@surriel.com \
--cc=akpm@linux-foundation.org \
--cc=aris@ruivo.org \
--cc=david@kernel.org \
--cc=jgg@ziepe.ca \
--cc=kernel-team@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=peterx@redhat.com \
/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
all inboxes | Powered by JetHome®