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

341–350 of 461 posts

Re: Karpathy’s Pelican

#341

Post by dannyw »

HarHarVeryFunny wrote: post #47

It seems pretty clear that Anthropic models have been specifically trained to be good at generating three.js (JavaScript 3-D Graphics) code, so given current state of AI code generation in general, I don't find three.js models/animations as indicative of anything other than the model's ability to write three.js code. When Fable was first released the day-1 demos of it on Twitter (presumably from people who were given…

Why do you think it's pretty clear?

Anthropic models are excellent at working with Blender APIs, other industry standard 3D modelling programs and tasks, and game libraries that have nothing to do with Three.js.

Three.js is a quite popular library; and browser-based apps are more easily sharable and more portable. So models having a preference for using it when unprompted doesn't suggest anything, just like how models using React or Tailwind by default doesn't suggest anything.

Re: Karpathy’s Pelican

#342

Post by monk_grilla »

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.

Re: Karpathy’s Pelican

#343

Post by moron4hire »

singron wrote: post #226
matsemann wrote: post #41

I'm pretty tired of the "Y made this game in Z tokens" all over the internet last week. They look impressive, and it's cool that it's even possible, but they're useless as games. None of them are any fun. They're like the most boring variant of basic controllers you can imagine. None have any cool mechanics. None have any tweaks made from hours and hours of testing. All have the same cel-shader.

I've heard this called a "dancing bear" before. It's interesting because it's a bear dancing, not because the dancing is any good. These conversations get frustrating since one group is saying the dancing is bad, a second group is saying it's good (for a bear), and a third group is saying we are a few years from a bear-only dancing industry.

The hype train the caught me was VR. I'm reminded of the Microsoft Hololens. It was an incredible feat of engineering. At the same time, it was--at times, literally--a painful experience.

There was a vision of the Hololens being a general purpose compute device that enabled something more like the power of a desktop without being tethered to a sitting position at a desk. You could see it if you squinted hard (incidentally, the device caused a lot of eye strain). But even at the height of the VR hype cycle, I didn't know anyone pushing the Hololens on anyone. Nobody was telling the world they were going to be using Hololenses v1 or v2 as their only computer "or get left behind."

Re: Karpathy’s Pelican

#344

Post by osetinsky »

I’m exploring an analogous idea for music. The quality of the musical output has improved noticeably with the latest frontier models

Karpathy’s point about the models not being able to easily audit their work is something I’m struggling with —- how can the audio output be made perceivable? Curious what people think about this question.

Here’s a synth to play with+remix

https://underscore.audio/s/cmp_8b226859-420/iron_rareflash

Re: Karpathy’s Pelican

#345

Post by skydhash »

matthewfcarlson wrote: post #287
reaperducer wrote: post #279

Earlier quoted context omitted.

Sure, the task is not completed perfectly, but that's not the point. Isn't it? If the computer can't do it better than a human being, then what's the point? Being wrong at scale is not better than being right.

Many humans would struggle with this even with very good tooling (ie not writing raw svg and using illustrator). I struggle to draw a bicycle accurately. But yes, I suspect it will be diminishing returns and I doubt it will ever be perfect due to the average nature of AI but I’d like to be wrong.

> Many humans would struggle with this even with very good tooling

But no ones hire random humans for things like this. You go and hire a vector artist and they will get your a very good pelican on a a bike. That's how you get things done when you can't do it.

Re: Karpathy’s Pelican

#346

Post by aaron695 »

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.)

[dead]

Re: Karpathy’s Pelican

#347

Post by cyanregiment »

A quick peruse of the Three.js examples page should prove why it's so easy to get an LLM to produce decent Three.js.

https://threejs.org/examples/

Here's minecraft: https://threejs.org/examples/webgl_geometry_minecraft.html

Here's an FPS: https://threejs.org/examples/games_fps.html

The library is extremely well-documented. When Three.js vibe coded projects started blowing up on Twitter 1-2 years ago, I wasn't that impressed then either because I knew what it was doing.

Anyone who remembers the C compiler built by an LLM! backlash probably feels the same way:

Why would I use an LLM to create a well-known demo rather than fork that demo itself?

What I haven't seen yet from an LLM is it create anything fundamentally new and exciting: A new UIX that is actually good. A new service that is actually good. A game with an art style I haven't seen, music, storytelling - something you'd expect out of a AAA studio.

Given that rant: The coolest part is the multi-modality between text and animation. However, I think the end product would have been a lot better if it was just a video. Having it do it in Three.js didn't add a ton of wow factor for me, and it would have been a lot better looking as video.

> Something like an ephemeral GTA of X on demand.

Here's where you lose me. AAA gaming is very far away from this Three.js demo. But the novel part being the syncing of narrative to the visual scene - a text-to-audio (video) book type technology seems very possible (and useful).

Nice work. We need more big projects like this involving AI (if anything, to get away from the slop argument largely focusing on 1-shot experiments).

Re: Karpathy’s Pelican

#348

Post by monk_grilla »

Morromist wrote: post #319
paulddraper wrote: post #309

Earlier quoted context omitted.

Pelicans don't ride bicycles. It's physically impossible. The problem is to draw it in the least disturbing way possible.

True! But somehow Disney has been drawing ducks riding bikes in a way that seems to satisfy everyone since before my grandfather was born. https://ridesabike.com/donald-duck-daisy-duck-huey-dewey-and...

Wow, that was a highly relevant and specific website to source here!

Re: Karpathy’s Pelican

#349

Post by throwatdem12311 »

segmondy wrote: post #146
throwatdem12311 wrote: post #94

Earlier quoted context omitted.

It’s the people spamming these shitty games that lack imagination.

people are excited, let them be excited! but more than the excitement is realizing the implications of what this means for building software, first it looks like a toy and then it doesn't. the OP is talking about how the games are not playable and fun. who cares? that's not the point.

I would hope that if you’re making a game that the goal is for it to be fun! If that is not the point then there is no point at all.

Re: Karpathy’s Pelican

#350

Post by vanjajaja1 »

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

Post reply on HN