laprise
Re:Imagecli: A single-binary Rust CLI for image processing
on Tuesday February 17, 2026 @08:59AM (#47047546)
I just made this for my own usage, so I'll share it to amortize my Claude Code carbon footprint... lol. I think the concept of single binary CLIs like ffmpeg are gaining importance in this "agent" age, so figured it might be useful to have that for images.
Dumbfeed – A dumb chronological feed of AI news
Re:Training open-source LLMs on ChatGPT output is a really bad idea.
on Monday April 24, 2023 @02:00PM (#35690963)
I understand what you mean, and that's a fair point. However, as John Schulman pointed out in his talk, it is possible to clone the behavior of the model, but it won't work to avoid hallucination since the underlying pretrained models are different. If we clone ChatGPT's behavior (by using its output), we'll get the worst of both worlds: weird output coming from its RLHF step AND hallucination.
Re:Training open-source LLMs on ChatGPT output is a really bad idea.
on Monday April 24, 2023 @11:46AM (#35689105)
" LLM indbreeding."… I like it
Re:Training open-source LLMs on ChatGPT output is a really bad idea.
on Monday April 24, 2023 @09:45AM (#35687574)
Yeah, just to be clear, I think using ChatGPT for creating small datasets for niche models makes total sense. I'm talking about creating foundation models which is a different thing.
Re:Training open-source LLMs on ChatGPT output is a really bad idea.
on Monday April 24, 2023 @09:14AM (#35687252)
Btw, this kind of language is already all over the place:
https://twitter.com/d_feldman/status/1649466422018318338
Which is hilarious and sad at the same time.
Re:Training open-source LLMs on ChatGPT output is a really bad idea.
on Monday April 24, 2023 @09:09AM (#35687204)
yes exactly, this "as an ai model I can/can't" you're mentioning is precisely what is learned during the RLHF alignment phase.
Re:Training open-source LLMs on ChatGPT output is a really bad idea.
on Monday April 24, 2023 @09:07AM (#35687184)
Yes indeed, Yoav Goldberg's post is essentially a good summary of John Schulman's talk, which is excellent. I highly recommend people watch it.
However, my point goes beyond this technical argument. I would argue that even if, by some magical process, we could perfectly replicate GPT-4 behaviour, I still don't think it's a good idea or at least it's not enough. Don't get me wrong, it would be really handy to have a free version running on our own cluster, but it wouldn't fix the other issues I mentioned.
Training open-source LLMs on ChatGPT output is a really bad idea.
A Decade of Data Science Hypes: The Good Parts
An interactive data visualization of the 2016 Election news media coverage
The Cost of Lost Knowledge
Re:Free SQL dump with 200 million tweets from 13 million users
on Wednesday June 08, 2011 @10:44PM (#2635762)
Neat ! here some tips for creating a kick ass graph visualization: http://www.martinlaprise.info/2010/02/15/visualize-your-own-...
Re:Apple's Pricing Decoys
on Wednesday September 01, 2010 @11:48PM (#1655223)
Indeed ! Wow... that's so lame
GithubGraph + ubigraph server = pure awesomeness
Re:Geocities-izer - Make Any Webpage Look Like It Was Made By A 13 Yea...
on Tuesday April 27, 2010 @08:25PM (#1300290)
This is insane !
Re:Discovering Fractals: The Lorenz Attractor
on Monday April 26, 2010 @01:41PM (#1295397)
Of course ... it's a fractal (dimension = 2.05). Fractal present some degree of self-similarity, not a perfect one. In fact, this is the whole beauty of it.
New Hiring Formula Values Math Pros
Weekend project: compute a 68 gigapixels fractal image
Re:Why NoSQL is bad for startups
on Thursday April 01, 2010 @03:40PM (#1235234)
Funny !
Re:Visualizing the Lorentz attractor in 3D with Python and VTK
on Sunday February 28, 2010 @05:33PM (#1157583)
Wow … shame on me ! I did too much of special relativity :-)
Visualizing the Lorentz attractor in 3D with Python and VTK
Visualize your own twitter graph
Explore your GitHub social graph with python
Re:Why the Apple iPad has no Java or Flash
on Thursday February 04, 2010 @11:00PM (#1102672)
Amen !