linux-doc.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
To: Sasha Levin <sashal@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
	Greg KH <greg@kroah.com>,
	corbet@lwn.net, linux-doc@vger.kernel.org,
	workflows@vger.kernel.org, josh@joshtriplett.org,
	kees@kernel.org, konstantin@linuxfoundation.org,
	linux-kernel@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	"Dr. David Alan Gilbert" <linux@treblig.org>
Subject: Re: [PATCH 0/4] Add agent coding assistant configuration to Linux kernel
Date: Thu, 31 Jul 2025 02:02:26 +0200	[thread overview]
Message-ID: <20250731020226.3d008bcb@foz.lan> (raw)
In-Reply-To: <aIpah6DTRd99mMqb@lappy>

Em Wed, 30 Jul 2025 13:46:47 -0400
Sasha Levin <sashal@kernel.org> escreveu:

> >> Some sort of a "traffic light" system:
> >>
> >>   1. Green: the subsystem is happy to receive patches from any source.
> >>
> >>   2. Yellow: "If you're unfamiliar with the subsystem and using any
> >>   tooling to generate your patches, please have a reviewed-by from a
> >>   trusted developer before sending your patch".
> >>
> >>   3. No tool-generated patches without prior maintainer approval.  
> >

That sounds a terrible idea. I mean, maintainers should be green for good
patches and red for bad ones. It doesn't matter if they're aided or
generated by AI or $TOOL. At the end, the one submitting it shall be able
to properly understand, describe and debug it. It shall also be able to
test it in real life before submitting.

AI can do good things, but can also do bad things. I'd say that anyone
using it shall double-check the code at least twice, checking if are
there any hidden bugs.

I've been doing myself some experiments: sometimes, LLM can quickly point
something broken, doing root cause analysis, completing a TODO requirement
and even write unittests and code.

However, sometimes, AI starts to "allucinate"(*), pointing to things that
don't exist, like inventing fields on structures and command line
arguments that don't exist (it likely inferred the names from projects 
could be using similar patterns/goals).

(*) AI being an statistics tool, the correct term is to diverge.

> >Perhaps. Of course there's the Coccinelle scripts that fix a bunch of code
> >around the kernel that will like be ignored in this. But this may still be
> >a good start.  

This is something that maintainers don't want: yet-another-tool that
newbies wanting to have their one microsecond of fame by getting patches
merged to start sending stuff that weren't tested nor bring any value.
Maybe we can add a text about that.

Thanks,
Mauro

  parent reply	other threads:[~2025-07-31  0:02 UTC|newest]

Thread overview: 101+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-27 19:57 [PATCH 0/4] Add agent coding assistant configuration to Linux kernel Sasha Levin
2025-07-27 19:57 ` [PATCH 1/4] agents: add unified agent coding assistant configuration Sasha Levin
2025-07-28  2:37   ` Kees Cook
2025-07-28  4:43     ` Sasha Levin
2025-07-28  5:16       ` Kees Cook
2025-07-28  5:39         ` Sasha Levin
2025-07-30 22:06   ` Kevin Hilman
2025-07-30 23:47     ` Sasha Levin
2025-08-01 20:53     ` Rob Herring
2025-08-08 18:07       ` Kevin Hilman
2025-07-27 19:58 ` [PATCH 2/4] agents: add core development references Sasha Levin
2025-07-28  2:39   ` Kees Cook
2025-07-28  5:00     ` Sasha Levin
2025-07-28  5:10       ` Kees Cook
2025-07-28  5:59         ` Sasha Levin
2025-07-28  6:18           ` Kees Cook
2025-07-28 12:35             ` Sasha Levin
2025-07-30 16:25             ` Sasha Levin
2025-07-30 17:35               ` Al Viro
2025-07-30 18:29                 ` Sasha Levin
2025-07-30 18:18               ` Matthew Wilcox
2025-07-30 18:41                 ` Sasha Levin
2025-07-28  4:24   ` Greg KH
2025-07-28  4:52     ` Sasha Levin
2025-07-28  5:02       ` Kees Cook
2025-07-27 19:58 ` [PATCH 3/4] agents: add coding style documentation and rules Sasha Levin
2025-07-28  2:40   ` Kees Cook
2025-07-28  5:10     ` Sasha Levin
2025-07-28  5:21       ` Kees Cook
2025-07-28  6:03         ` Sasha Levin
2025-07-30  9:31           ` Krzysztof Kozlowski
2025-07-30 14:48             ` Jakub Kicinski
2025-07-30 15:10             ` Steven Rostedt
2025-07-27 19:58 ` [PATCH 4/4] agents: add legal requirements and agent attribution guidelines Sasha Levin
2025-07-28  2:43   ` Kees Cook
2025-08-05 22:08   ` Jeff Johnson
2025-08-05 23:11     ` Laurent Pinchart
2025-08-05 23:33       ` Sasha Levin
2025-08-06 14:12   ` Konstantin Ryabitsev
2025-08-06 21:53     ` Sasha Levin
2025-07-28  7:58 ` [PATCH 0/4] Add agent coding assistant configuration to Linux kernel Vlastimil Babka
2025-07-28  9:27   ` David Hildenbrand
2025-07-28 10:37     ` Greg KH
2025-07-28 10:47       ` David Hildenbrand
2025-07-28 13:05         ` Sasha Levin
2025-08-04  9:23           ` Michal Hocko
2025-08-04  9:41             ` Michal Hocko
2025-08-04 13:25             ` Sasha Levin
2025-08-04 22:03               ` Jiri Kosina
2025-08-04 22:14                 ` Steven Rostedt
2025-08-04 22:30                   ` Jiri Kosina
2025-08-04 22:53                   ` dan.j.williams
2025-08-04 23:30                     ` Sasha Levin
2025-08-04 23:39                       ` Laurent Pinchart
2025-08-05 13:29                         ` Steven Rostedt
2025-07-28 11:57   ` Sasha Levin
2025-07-28  8:42 ` Lorenzo Stoakes
2025-07-28 10:35   ` Greg KH
2025-07-28 10:52     ` Lorenzo Stoakes
2025-07-28 12:45       ` Sasha Levin
2025-07-28 13:13         ` Lorenzo Stoakes
2025-07-28 13:23           ` Sasha Levin
2025-07-28 13:28             ` Lorenzo Stoakes
2025-07-30 15:27       ` Steven Rostedt
2025-07-30 15:34         ` Lorenzo Stoakes
2025-07-30 16:18           ` Steven Rostedt
2025-07-30 16:33             ` Mauro Carvalho Chehab
2025-07-30 16:36             ` Sasha Levin
2025-07-30 16:59               ` Lorenzo Stoakes
2025-07-30 17:12                 ` Sasha Levin
2025-07-30 17:23                   ` Lorenzo Stoakes
2025-07-30 17:32                     ` Steven Rostedt
2025-07-30 18:03                       ` Sasha Levin
2025-07-30 18:18                         ` Lorenzo Stoakes
2025-07-30 18:04                       ` Lorenzo Stoakes
2025-07-30 19:16                         ` Mark Brown
2025-07-30 17:25                   ` Steven Rostedt
2025-07-30 17:34                 ` Mark Brown
2025-07-30 17:36                 ` Kees Cook
2025-08-04 10:20                 ` Jiri Kosina
2025-07-30 17:05               ` Steven Rostedt
2025-07-30 17:46                 ` Sasha Levin
2025-07-30 17:59                   ` Al Viro
2025-07-30 18:10                     ` Sasha Levin
2025-07-30 18:24                       ` Lorenzo Stoakes
2025-07-30 18:59                         ` Sasha Levin
2025-07-30 19:10                     ` Theodore Ts'o
2025-07-30 19:40                       ` Steven Rostedt
2025-07-30 19:51                       ` Al Viro
2025-07-30 19:27                   ` Steven Rostedt
2025-07-31  0:02                   ` Mauro Carvalho Chehab [this message]
2025-07-30 16:40             ` Dr. David Alan Gilbert
2025-07-30 17:10               ` Lorenzo Stoakes
2025-07-30 17:20                 ` Steven Rostedt
2025-07-30 17:33                   ` Lorenzo Stoakes
2025-07-30 17:12               ` Steven Rostedt
2025-07-30 17:39                 ` Dr. David Alan Gilbert
2025-07-30 17:51               ` Kees Cook
2025-07-30 16:58             ` Lorenzo Stoakes
2025-07-28 10:56     ` Laurent Pinchart
2025-08-12 18:13 ` Nicolas Frattaroli

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=20250731020226.3d008bcb@foz.lan \
    --to=mchehab+huawei@kernel.org \
    --cc=corbet@lwn.net \
    --cc=greg@kroah.com \
    --cc=josh@joshtriplett.org \
    --cc=kees@kernel.org \
    --cc=konstantin@linuxfoundation.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@treblig.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=rostedt@goodmis.org \
    --cc=sashal@kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=workflows@vger.kernel.org \
    /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;
as well as URLs for NNTP newsgroup(s).