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 early access, and/or Anthropic employees) were pretty much 100% three.js stuff. Yes, it looks nice, but it doesn't tell me any better than an Erdos proof whether the LLM will be able to run my vending machine.
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?
Because the degree of realism in a video is determined by implicit knowledge of concepts like "in front of", "behind", "next to", "inside", "outside", "between", "occluded by", etc. as well as distances, angles, and the relative size of objects when viewed from a perspective.
I guess I just don't have an intuition for why that is different from what it does for non-"spatial" things. Like the fact that it works is still because it produced the code it did token by token. Whether its dealing with, e.g., "beside the rock" or "in the array", it's doing the same kind of inferential activity.
> I just don't have an intuition for why that is different from what it does for non-"spatial" things
A big reason people separate this out is because it was only a short time ago that AI models were noticably and uniquely bad at this. I don't say this to be like "oh so imagine where theyll be in x amount of time", rather that this thing that was once a serious limitation of the technology is slowly being compensated for by larger and better trained models
>Whether its dealing with, e.g., "beside the rock" or "in the array", it's doing the same kind of inferential activity.
Are you sure about that? Presumably the spatial concept of "inside" and the computer memory concept of "inside" have different contextual embeddings in an LLM, not so different from how our brains have different neural activation patterns when we use different concepts. Unless you think that "the same kind of inferential activity" also applies to human neurons firing.
You are correct. It’s important not to let hype peddlers imply AI possesses consciousness.
[dead]
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.
I don't think so. I've used Claude to generate 3D animations in python purely by making and manipulating raw meshes, and I've had great results. A more likely explanation is that 3D graphics is just pretty straightforward matrix algebra, and models (or Claude specifically) has that down cold.
Don’t worry. I’m sure they’re not training it to be good at things like writing database backends, financial services, logistics systems, user interfaces, or anything of economic value. As long as you’re not working on three.js specifically, I’m sure Anthropic isn’t making any progress you should be worried about.
Do you feel that rendering a 3-D picture of Bilbo Baggins' house is a good indicator of generating economic value (i.e "AGI" in OpenAI parlance)?
[flagged]
But LLM's passed the Turing test, so we're done, right? ;-) Seriously, though, I agree with you that people keep moving the ball.
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.