From: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
To: users@kernel.org, tools@kernel.org, workflows@vger.kernel.org
Subject: Toy/demo: using ChatGPT to summarize lengthy LKML threads (b4 integration)
Date: Tue, 27 Feb 2024 17:32:34 -0500 [thread overview]
Message-ID: <20240227-flawless-capybara-of-drama-e09653@lemur> (raw)
Hi, all:
I was playing with shell-gpt and wrote a quickie integration that would allow
retrieving (slimmed-down) threads from lore, feeding them to ChatGPT, and
asking it to provide some basic analysis of the thread contents. Here's a
recorded demo session:
https://asciinema.org/a/643435
A few notes:
1. This is obviously not a replacement for actually reading email, but can
potentially be a useful asset for a busy maintainer who just wants a quick
summary of a lengthy thread before they look at it in detail.
2. This is not free or cheap! To digest a lengthy thread, you can expect
ChatGPT to generate enough tokens to cost you $1 or more in API usage fees.
I know it's nothing compared to how expensive some of y'all's time is, and
you can probably easily get that expensed by your employers, but for many
others it's a pretty expensive toy. I managed to make it a bit cheaper by
doing some surgery on the threads before feeding them to chatgpt (like
removing most of the message headers and throwing out some of the quoted
content), but there's a limit to how much we can throw out before the
analysis becomes dramatically less useful.
3. This only works with ChatGPT-4, as most threads are too long for
ChatGPT-3.5 to even process.
So, the question is -- is this useful at all? Am I wasting time poking in this
direction, or is this something that would be of benefit to any of you? If the
latter, I will document how to set this up and commit the thread minimization
code I hacked together to make it cheaper.
Best regards,
-K
next reply other threads:[~2024-02-27 22:32 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-27 22:32 Konstantin Ryabitsev [this message]
2024-02-27 23:35 ` Toy/demo: using ChatGPT to summarize lengthy LKML threads (b4 integration) Junio C Hamano
2024-02-28 0:43 ` Linus Torvalds
2024-02-28 20:46 ` Shuah Khan
2024-02-29 0:33 ` James Bottomley
2024-02-28 5:00 ` Willy Tarreau
2024-02-28 14:03 ` Mark Brown
2024-02-28 14:39 ` Willy Tarreau
2024-02-28 15:22 ` Konstantin Ryabitsev
2024-02-28 15:29 ` Willy Tarreau
2024-02-28 17:52 ` Konstantin Ryabitsev
2024-02-28 17:58 ` Willy Tarreau
2024-02-28 19:16 ` Konstantin Ryabitsev
2024-02-28 15:04 ` Hannes Reinecke
2024-02-28 15:15 ` Willy Tarreau
2024-02-28 17:43 ` Jonathan Corbet
2024-02-28 18:52 ` Alex Elder
2024-02-28 18:55 ` Bart Van Assche
2024-02-29 7:18 ` Hannes Reinecke
2024-02-29 8:37 ` Theodore Ts'o
2024-03-01 1:13 ` Bart Van Assche
2024-02-29 9:30 ` James Bottomley
2024-02-28 19:32 ` Luis Chamberlain
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=20240227-flawless-capybara-of-drama-e09653@lemur \
--to=konstantin@linuxfoundation.org \
--cc=tools@kernel.org \
--cc=users@kernel.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 read-only IMAP folder(s) and NNTP newsgroup(s).