mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Dr. David Alan Gilbert" <linux@treblig.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: James Bottomley <James.Bottomley@hansenpartnership.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Christian Brauner <brauner@kernel.org>,
	tech-board-discuss@lists.linux.dev, linux-kernel@vger.kernel.org,
	ksummit-discuss@lists.linuxfoundation.org,
	christianvanbrauner@gmail.com
Subject: Re: LLM based rewrites
Date: Mon, 9 Mar 2026 18:38:21 +0000	[thread overview]
Message-ID: <aa8TnXA8qsG92hyX@gallifrey> (raw)
In-Reply-To: <20260309143406.3d45e36e@gandalf.local.home>

* Steven Rostedt (rostedt@goodmis.org) wrote:
> On Mon, 09 Mar 2026 11:19:42 -0700
> James Bottomley <James.Bottomley@HansenPartnership.com> wrote:
> 
> > I don't think LLMs will be able to come up with the necessary proof of
> > separation without essentially recreating the clean room process, which
> > grows cost prohibitive as the complexity of the work increases.
> 
> I con see one AI bot reading the original code, and then making the prompts
> to pass to a second AI bot to produce the code.

That's what Chardet did:
https://github.com/chardet/chardet/issues/327#issuecomment-4005195078

however, there's a fun question of whether the second AI had already seen
the code; a lot of LLMs seem to have been trained on a lot of open
source code already.

Dave

> -- Steve
> 
-- 
 -----Open up your eyes, open up your mind, open up your code -------   
/ Dr. David Alan Gilbert    |       Running GNU/Linux       | Happy  \ 
\        dave @ treblig.org |                               | In Hex /
 \ _________________________|_____ http://www.treblig.org   |_______/

  reply	other threads:[~2026-03-09 18:53 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-07 20:49 Christian Brauner
2026-03-09 13:57 ` Steven Rostedt
2026-03-09 15:31   ` H. Peter Anvin
2026-03-09 16:16     ` Steven Rostedt
2026-03-09 16:33       ` Jonathan Corbet
2026-03-09 16:55         ` H. Peter Anvin
2026-03-09 17:09           ` H. Peter Anvin
2026-03-09 18:19           ` James Bottomley
2026-03-09 18:34             ` Steven Rostedt
2026-03-09 18:38               ` Dr. David Alan Gilbert [this message]
2026-03-09 18:54               ` James Bottomley
2026-03-10  4:52           ` Theodore Tso
     [not found]             ` <CAMTJT3_cVaA7aJmDa6j288-qwP3jzvM_R2pdk+XmE+1U=Sovbg@mail.gmail.com>
2026-03-10 12:47               ` Theodore Tso
2026-03-10 14:10                 ` Dr. Greg
2026-03-09 16:05 ` Dave Hansen
2026-03-09 16:16 ` James Bottomley

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=aa8TnXA8qsG92hyX@gallifrey \
    --to=linux@treblig.org \
    --cc=James.Bottomley@hansenpartnership.com \
    --cc=brauner@kernel.org \
    --cc=christianvanbrauner@gmail.com \
    --cc=corbet@lwn.net \
    --cc=hpa@zytor.com \
    --cc=ksummit-discuss@lists.linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tech-board-discuss@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

all inboxes | Powered by JetHome®