Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Karpathy’s Pelican

twitter.com

Post reply on HN
Print view View original

361–370 of 461 posts

Re: Karpathy’s Pelican

#361

Post by NewJazz »

jkahrs595 wrote: post #214
NewJazz wrote: post #205

Earlier quoted context omitted.

What do you mean by "oneshot"? The term applied to genai makes sense, but it doesn't make a whole lot of sense to apply the term to human art.

What doesn’t make sense? They aren’t drawing it by hand, they are still using SVG. Give them one chance before rendering it.

I feel like letting them render + screenshot + judge + iterate would still be called oneshotting. I mean, my coding agent calls tools to verify code correctness. I'd still call it oneshotting I guess.

Re: Karpathy’s Pelican

#363

Post by jedbrooke »

weakfish wrote: post #355

Out of curiosity, I asked Opus 5 to do the same with the first ~1.5 pages of Neuromancer by William Gibson, which I thought might be a good test of interpretation from the model. It refused to use the text verbatim because of copyright (ironic), but the output was interesting nonetheless. https://claude.ai/public/artifacts/275dc3c2-7bd3-432b-94ff-d...

it would be interesting to see results from works that don't have notable existing film/tv adaptations or illustrations (though I suppose there will always be fan art) to see if it’s really able to generate something novel. I’ve had my own version of this since I’ve been reading LotR recently too and I kinda wish I had read the book before watching the movie (not that the movies are bad though). Fortunately I am finding there is tons more content in the book than the movie :)

Also, large models refusing to work with copyright material is really hypocritical, copyright enforcement for thee but not for me

Re: Karpathy’s Pelican

#364

Post by reaperducer »

jryle70 wrote: post #340
reaperducer wrote: post #296

Earlier quoted context omitted.

Trillions of dollars spent. Trillions of gigawatts consumed. And people still celebrate "Yay! We're less wrong than the other guys!" This is what the tech industry has become? Less of a failure is still failure.

I don't know how much money has been spent for AI, and I very much doubt you do. Do you know if more has been spent on LLM the last 9 years -- since "Attention is all you need" -- than Internet infrastructure during, say 1995 to 2004? That included the dotcom crash. Did you lament how a failure the Internet was? LLM has progressed a lot in the last two year, judging from the pelican drawings. I personally couldn't ca…

I don't know how much money has been spent for AI, and I very much doubt you do.

Pick up a newspaper. Start with the Wall Street Journal. These are public companies. It's not a secret.

Re: Karpathy’s Pelican

#365

Post by attheballot »

jmugan wrote: post #93

A lot of people are posting here about how bad the end product is, but that is kind of the point. Models have moved beyond generating images to a new kind of benchmark that better exposes understanding of the physical world, and we can use benchmarks like this to measure future progress. (Of course, it will have to be a qualitative/subjective measurement.)

I fully agree.

But I do think this was a poor demonstration of the idea for another reason: Tolkien works have a HUGE corpus of training data. It's great that random users can come in and immediately recognize what the footage is, but it fails at the very first thing the pelican was meant to do:

- Render this thing you have only tangential training data of, that also happens to be an asymmetrical object so we can see how much you fuck up the details if you somehow flip the orientation half the time.

They should have used an obscure story, not "Most Studied Piece of Literally Work of The Past Century trademarksymbol"

Re: Karpathy’s Pelican

#366

Post by attheballot »

vanjajaja1 wrote: post #350
consumer451 wrote: post #339

The difference between this and Simon's pelican is that with Simon, I get the prompt. Last I checked, I did not see the prompt for this really cool thing, so it is not reproducible. Did I miss the prompt somewhere?

he said the prompt was the first paragraph of LoTR, but he didn't mention a preamble this guy seems to have taken that idea and got something similar/better, so likely the prompt isn't too special https://x.com/Izkimar/status/2083819741643178208?s=20

In other words, they did not even need a prompt. You could probably skip feeding the paragraph and just told "generate visuals for the opening paragraph of the LotR", and the LLM would successfully do it as it has a very good idea of what they are from its training data.

This is a bigger difference to the pelican than simple reproducibility steps. The pelican is intentionally esoteric, and thus open ended. The LotR is mundane and has a "correct" answer, aka, copy the movie.

It makes it a really awful test of capabilities. The pelican isn't a slop test. This crap is.

Re: Karpathy’s Pelican

#367

Post by doginasuit »

monk_grilla wrote: post #342
jmugan wrote: post #93

A lot of people are posting here about how bad the end product is, but that is kind of the point. Models have moved beyond generating images to a new kind of benchmark that better exposes understanding of the physical world, and we can use benchmarks like this to measure future progress. (Of course, it will have to be a qualitative/subjective measurement.)

I don't know I think it is charming in a way that is lacking in nearly everything else an LLM tries to do creatively. I have always preferred the result of getting an LLM to draw an svg or make a procedural animation like this to the uncanny hyper-realistic result of diffusion image/video generation.

To help explain AI to my elderly mother, I said it is like an alien intelligence on a planet too far away to directly observe Earth, and everything it knows about humanity and our world it learned from reading just about every book and website. You can ask it a question or to do some work and it can often give a useful response but it can never directly judge its accuracy if it relates to the physical world, it has only your judgment to work with.

Given that limitation, it is incredible what it can still accomplish. And when it falls short, it is often in a charming way, if you are open to seeing it that way. It reflects something like a child's understanding of the world, not entirely wrong, just incomplete.

The fluttering cubes that might have been bees or butterflies were my favorite part.

Re: Karpathy’s Pelican

#369

Post by eric_khun »

Everyone's about to make games sooner than expected. games are slow, might look buggy and unfinished. But I think that's just about time before we see fun games coming up. i'm betting on it with https://antics.gg . if you want to host your multiplayer vibecoded games, feel free to use us!
Post reply on HN