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

171–180 of 461 posts

Re: Karpathy’s Pelican

#171

Post by beepbooptheory »

fasterik wrote: post #148
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…

Taking a single paragraph of literary text, which is abstract and ambiguous, and converting it into a 3D animation requires an enormous amount of implicit knowledge about spatial relationships, intuitive physics, everyday objects, and so forth. Not to mention the mathematics of 3D transformations and computer graphics more generally. Saying that it's indicative of no more than three.js coding ability is absurd.

Why does it require knowledge about spatial relationships?

Re: Karpathy’s Pelican

#172

Post by YmiYugy »

I don't think it's a bad way to benchmark new models, I just find it concerning that the author implies that "pelican on a bicycle" has been exhausted. At the risk of making overly broad, unfalsifiable claims I think multi-year exposure to AI content has dramatically raised our expectations for speed and volume but lowered them for quality. We see a very janky pelican and declare the problem solved.

Re: Karpathy’s Pelican

#173

Post by trvz »

garganzol wrote: post #162
bredren wrote: post #8

I worked with an LLM to build a ~3D animation of the Back to the Future delorean Time Machine as a way to spice up the hero on a docs page. That took a fair amount of custom tuning and I had to create a tuning view to get some of the behaviors right. But it was enough fun that I generalized it to take in ~any scene description from a film. It goes out and gets more detailed descriptions and film stills if available b…

The product you've built the animation for is only for macOS, which is a pity cause it has a way wider appeal than macOS market share is. You have low-hanging fruits right there, don't miss them.

macOS covers 90% of people who would ever pay him.

Re: Karpathy’s Pelican

#174

Post by trial3 »

charcircuit wrote: post #164
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.)

Bad? It has a charming style. I would watch the whole book if it was made like this.

yeah, definitely, in the same way that we all regularly go and look back fondly at our chatgpt ghiblified family photos

Re: Karpathy’s Pelican

#175

Post by Applejinx »

abletonlive wrote: post #154
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…

[flagged]

Oh, they still are, it's just that it's a rare parrot that can reproduce 'all of the written corpus of three.js' or stochastically align all that with arbitrary and weird conditions for what to squawk out.

This is what you get. It's like the more general concept of starting with the written word (or 1000 words) and then replacing it with a picture. You've done something strikingly different, but is it serving the same function?

It's fascinating to see this stuff combine such disparate sources in unexpected ways. But it is parrot, just not in the way you're expecting.

Re: Karpathy’s Pelican

#176

Post by onion2k »

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…

I don't find three.js models/animations as indicative of anything other than the model's ability to write three.js code.

This weekend I've been converting a game from three.js to ogl.js in order to see if I can optimise the time-to-interactive loading time. I took the three.js driven page weight from about 600KB (500KB being three.js) to about 50KB, and reduced the loading time from multiple seconds on a 4G mobile connection to around 0.5s.

This has mostly been a combination of Opus 5 and Sonnet 5 in Claude Code. It very clearly has a good grasp of WebGl, and of what impacts page loading times and rendering speed. It was able to drive Claude Code's integrated browser to measure the impact of changes, and as I spiked out a test of ogl.js it could test the differences changes made.

It's not the best game (https://tinyslots.ooer.com) but that's on me. As an exercise in building 3D in a browser, and in page speed optimization, with Claude models I am really impressed.

Re: Karpathy’s Pelican

#177

Post by Waterluvian »

Speaking of benchmarks has anyone given AIs Where’s Waldo pages and asked it to find Waldo?

I’ve been trying it on them all and can’t find one that does it consistently. The best will tell me they can’t. The worst confidently point out one of countless Waldo-likes.

Re: Karpathy’s Pelican

#178

Post by Supermancho »

emp17344 wrote: post #138
ben_w wrote: post #132

Earlier quoted context omitted.

While they are bad at creative work*, this reasoning isn't going to show it. If you took the best, most creative, human writer in the world, and for thought experiment reasons they had amnesia (to mimic AI blank context windows) specifically while you asked them for a story idea 100 times in a row, my expectation is that this human would also give you the same idea at least 80 times out of that 100. * still better th…

Better than the mean human? The mean human creates far better stories while daydreaming. AI enthusiasts have such a distorted view of human capability, it’s bizarre.

The qualification "better" is doing some hefty lifting in your assumption.

What you think is better is not what I think is better. Imagination is not storytelling. You ask the "mean human" to write, it's going to be worse than an LLM in spelling and grammar, if you get anything at all.

Re: Karpathy’s Pelican

#179

Post by gordonhart »

siliconc0w wrote: post #170

There is a tipping point between procedurally generating everything in SVG to maybe giving them tool access to something like 3dsmax (or having them build and then use a tool to do the thing vs doing the thing).

I’d love to see this benchmark using Blender. Asking a model to animate a scene in Three.js is a square peg/round hole; it doesn’t convey much when the model can’t get it to fit. With Blender the human expert ceiling for this task has been proven to be very high

Re: Karpathy’s Pelican

#180

Post by mikojan »

After watching this video I am absolutely positive that the issue is not a lack of stamina in humans. It is that humans have the capacity to realize that this is a bad idea long before they complete it.
Post reply on HN