Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: "softworkz ." <softworkz-at-hotmail.com@ffmpeg.org>
To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] [PATCH 0/3] avutil/dict2: Add AVDictionary2 with hash-based lookup
Date: Mon, 14 Apr 2025 13:21:11 +0000
Message-ID: <BN0P223MB0358C09356A59D9C88B5601BBAB32@BN0P223MB0358.NAMP223.PROD.OUTLOOK.COM> (raw)
In-Reply-To: <Z_zrLLO1fUUZxDAI@phare.normalesup.org>



> -----Original Message-----
> From: ffmpeg-devel <ffmpeg-devel-bounces@ffmpeg.org> On Behalf Of
> Nicolas George
> Sent: Montag, 14. April 2025 13:02
> To: FFmpeg development discussions and patches <ffmpeg-
> devel@ffmpeg.org>
> Subject: Re: [FFmpeg-devel] [PATCH 0/3] avutil/dict2: Add
> AVDictionary2 with hash-based lookup
> 
> ffmpegagent (HE12025-04-12):
> > This whole patchset has been antirely authored by AI, wich means
> that I
> > haven't written a single line of code.
> 
> You have got to be kidding. And not just because you waste everybody's
> time submitting a series of bullshit code, but by the fact that you
> did
> it in the first place, whether AI or yourself.
> 

I had written another message to explain the context of how this.

This isn't some ChatGPT BS code-snippets assembled to something that
"somehow" works.
For this experiment, the maximum in all directions that is currently 
available in terms of code generation has been thrown at this problem.
It involved agent-style patterns, in cooperative and autonomous ways,
iterative improvement (AI making changes, compiling, debugging, making
more changes - all on its own, etc.), multiple inference models chosen
depending on the current task, yet it still needed strong guidance at
certain points.
It went over 5-6 hours, where for 80% of the time there was an active 
request, burning GPU cycles in some data center. It has cost money for
which you can get ChatGPT Plus for half a year.

That's what makes it special - it kind of reflects what's currently 
possible at the high end (and publicly available) in code generation,
and thus, it's a first-hand example that might be more evident than all
the stories that you can read these days.


Of course, I would never post any trash code that everybody else could 
have achieved as well with a few clicks.

sw




_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

      parent reply	other threads:[~2025-04-14 13:21 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-12 15:11 ffmpegagent
2025-04-12 15:11 ` [FFmpeg-devel] [PATCH 1/3] " softworkz
2025-04-16 21:24   ` Michael Niedermayer
2025-04-16 22:38     ` softworkz .
2025-04-12 15:11 ` [FFmpeg-devel] [PATCH 2/3] doc/dict2: Add doc and api change for AVDictionary2 softworkz
2025-04-16 21:48   ` Michael Niedermayer
2025-04-16 22:43     ` softworkz .
2025-04-16 23:15     ` softworkz .
2025-04-16 23:40       ` Michael Niedermayer
2025-04-17 22:38         ` softworkz .
2025-04-19  2:28           ` Michael Niedermayer
2025-04-19 13:43             ` softworkz .
2025-04-20 20:37               ` Michael Niedermayer
2025-04-12 15:11 ` [FFmpeg-devel] [PATCH 3/3] tests/dict2: Add tests and benchmark " softworkz
2025-04-14 11:02 ` [FFmpeg-devel] [PATCH 0/3] avutil/dict2: Add AVDictionary2 with hash-based lookup Nicolas George
2025-04-14 11:50   ` softworkz .
2025-04-14 13:21   ` softworkz . [this message]

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=BN0P223MB0358C09356A59D9C88B5601BBAB32@BN0P223MB0358.NAMP223.PROD.OUTLOOK.COM \
    --to=softworkz-at-hotmail.com@ffmpeg.org \
    --cc=ffmpeg-devel@ffmpeg.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

Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
		ffmpegdev@gitmailbox.com
	public-inbox-index ffmpegdev

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git