public inbox for io-uring@vger.kernel.org
 help / color / mirror / Atom feed
From: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
To: Sasha Levin <sashal@kernel.org>
Cc: axboe@kernel.dk, csander@purestorage.com,
	io-uring@vger.kernel.org,  torvalds@linux-foundation.org,
	workflows@vger.kernel.org
Subject: Re: [RFC] b4 dig: Add AI-powered email relationship discovery command
Date: Thu, 11 Sep 2025 19:24:03 -0400	[thread overview]
Message-ID: <20250911-neon-speedy-walrus-dcc499@meerkat> (raw)
In-Reply-To: <20250909163214.3241191-1-sashal@kernel.org>

On Tue, Sep 09, 2025 at 12:32:14PM -0400, Sasha Levin wrote:
> Add a new 'b4 dig' subcommand that uses AI agents to discover related
> emails for a given message ID. This helps developers find all relevant
> context around patches including previous versions, bug reports, reviews,
> and related discussions.

All right, I've got ollama working on my gaming rig now, so that I can get
back to my summarization work without having to rely on big vendors. Thanks
for pushing me in that direction, because it never felt quite right to be
using a centralized service for this work. At least that large nvidia card
does something other than help me deliver packages to Port Knot City.

> The command:
> - Takes a message ID and constructs a detailed prompt about email relationships
> - Calls a configured AI agent script to analyze and find related messages
> - Downloads all related threads from lore.kernel.org
> - Combines them into a single mbox file for easy review

I'm going to take a look at it, but I want to use "b4 dig" to analyze commits
and establish their provenance. I will then look at whether we can use LLMs to
provide additional perks like summarization or highlights of important
messages (those offering nacks, criticisms, warnings, etc). This seems like the
"least wrong" way of using an LLM at this moment, especially with the legality
of the code it produces still largely untested in courts.

Thanks for submitting this to push me into this direction. I won't take this
directly, but I'll rely on it to see how you get certain things done.

Regards,
-K

  parent reply	other threads:[~2025-09-11 23:24 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-05 11:18 [GIT PULL] io_uring fix for 6.17-rc5 Jens Axboe
2025-09-05 17:24 ` Linus Torvalds
2025-09-05 17:45   ` Konstantin Ryabitsev
2025-09-05 18:06     ` Linus Torvalds
2025-09-05 19:33       ` Link trailers revisited (was Re: [GIT PULL] io_uring fix for 6.17-rc5) Konstantin Ryabitsev
2025-09-05 20:09         ` Linus Torvalds
2025-09-05 20:47         ` Sasha Levin
2025-09-06 11:27         ` Greg KH
2025-09-06 11:27           ` Greg KH
2025-09-06 11:30             ` Greg KH
2025-09-06 13:51           ` Konstantin Ryabitsev
2025-09-06 15:31             ` Linus Torvalds
2025-09-06 18:50               ` Konstantin Ryabitsev
2025-09-06 19:19                 ` Linus Torvalds
2025-09-08  9:11                   ` Jani Nikula
2025-09-08 11:59                 ` Mark Brown
2025-09-08 20:11         ` dan.j.williams
2025-09-09 11:29           ` Mark Brown
2025-09-09 13:17           ` Rafael J. Wysocki
2025-09-09 14:18             ` Jakub Kicinski
2025-09-09 14:35               ` Jens Axboe
2025-09-09 14:42                 ` Konstantin Ryabitsev
2025-09-09 14:48                   ` Vlastimil Babka
2025-09-09 14:50                     ` Jens Axboe
2025-09-09 15:30                       ` Rafael J. Wysocki
2025-09-09 16:40                       ` Linus Torvalds
2025-09-09 17:08                         ` Mark Brown
2025-09-09 17:50                           ` Linus Torvalds
2025-09-09 17:58                             ` Linus Torvalds
2025-09-09 18:31                               ` Konstantin Ryabitsev
2025-09-09 19:36                                 ` dan.j.williams
2025-09-10  1:12                                 ` dan.j.williams
2025-09-10 12:19                                   ` Mark Brown
2025-09-09 17:25                         ` dan.j.williams
2025-09-09 17:56                           ` Alexei Starovoitov
2025-09-09 18:01                             ` Linus Torvalds
2025-09-09 18:13                               ` Alexei Starovoitov
2025-09-09 18:06                         ` Vlastimil Babka
2025-09-09 18:14                           ` Linus Torvalds
2025-09-09 18:22                             ` Vlastimil Babka
2025-09-09 21:05                               ` Mark Brown
2025-09-10  1:33                                 ` Konstantin Ryabitsev
2025-09-09 14:44                 ` Greg KH
2025-09-09 15:14                 ` Danilo Krummrich
2025-09-09 16:32         ` [RFC] b4 dig: Add AI-powered email relationship discovery command Sasha Levin
2025-09-09 17:22           ` Laurent Pinchart
2025-09-09 17:26             ` Jens Axboe
2025-09-09 18:54               ` Sasha Levin
2025-09-10 10:13                 ` Laurent Pinchart
2025-09-10 10:55                   ` Sasha Levin
2025-09-10 11:29                     ` Laurent Pinchart
2025-09-10 13:38             ` Konstantin Ryabitsev
2025-09-10 14:03               ` Andrew Dona-Couch
2025-09-11 14:48           ` Nicolas Frattaroli
2025-09-11 15:05             ` Sasha Levin
2025-09-11 19:13               ` Nicolas Frattaroli
2025-09-11 19:57                 ` Sasha Levin
2025-09-15 11:26                   ` Mark Brown
2025-09-15 11:48                     ` Sasha Levin
2025-09-15 12:03                       ` Mark Brown
2025-09-11 23:24           ` Konstantin Ryabitsev [this message]
2025-09-07 22:04     ` [GIT PULL] io_uring fix for 6.17-rc5 Jonathan Corbet
2025-09-05 19:04   ` Jens Axboe
2025-09-05 19:07     ` Jens Axboe
2025-09-05 19:13     ` Caleb Sander Mateos
2025-09-05 19:16       ` Jens Axboe
2025-09-05 19:15     ` Linus Torvalds
2025-09-05 19:23       ` Jens Axboe
2025-09-05 19:21     ` Linus Torvalds
2025-09-05 19:30       ` Jens Axboe
2025-09-05 20:54         ` Linus Torvalds
2025-09-06  0:01           ` Jens Axboe
2025-09-07 18:47             ` Jonathan Corbet
2025-09-08 22:15             ` Alexei Starovoitov

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=20250911-neon-speedy-walrus-dcc499@meerkat \
    --to=konstantin@linuxfoundation.org \
    --cc=axboe@kernel.dk \
    --cc=csander@purestorage.com \
    --cc=io-uring@vger.kernel.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