No way. Next level.

Awesome stuff. Moonlight and Archipelago are particularly beautiful. I work in shaders fairly regularly (mainly Metal-based), and it still amazes me how so little code can produce seemingly infinite universes.

Looks super interesting! Does it have support for auction mechanics (e.g. dutch auction)?

currently it just handles standard limit and market orders, with price-time priority

So they force-unwrapped a `null` and blew up the internet?

Would an `unwrap_or_else` have helped here?

Google: "I'll see your Marble and raise you a SIMA2".

This industry moves redonkulously fast.

Is Marble's definition of a "world model" the same as Yann LeCun's definition of a world model? And is that the same as Genie's definition of a world model?

Pretty sure it's used as a marketing term here. They train on images that you generate/give it, but the output of that training is not a model, it's a static 3d scene made up out of gaussian splats. You are not running inference on a model when traversing one of those scenes, you are just rendering the splats.

At the very least it differs greatly from "world model" as understood in earlier robotics and AI research, wherein it referred to a model describing all the details of the world outside the system relevant to the problem at hand.

Very different, it would seem. Then again, it’s never been clear to me why LeCun believes that LLM architectures don’t inherently produce world models in the course of training.

Nor I.

IMO LLM more or less literally cannot do what they do without a world model, not least because much of what language is, is a protocol for making assertions about that model, testing the degree to which it is shared, and seeking to alter the model one carries of one's interlocutor's model.

To the "parrot people" I suggest, there is no more optimized mechanism for the inner layers of a network to approach than one which most parsimoniously models the world, so as to correctly emit tokens reflective of that.

I like that they distinguish between the collider mesh (lower poly) and the detailed mesh (higher poly).

As a game developer I'm looking for:

• Export low-poly triangle mesh (ideally OBJ or FBX format — something fairly generic, nothing too fancy) • Export texture map • Export normals • Bonus: export the scene as "de-structured" objects (e.g. instead of a giant world mesh with everything baked into it, separate exports for foreground and background objects to make it more game engine-ready.

Gaussian splats are awesome, but not critical for my current renderers. Cool to have though.

Aren't the gausian splats the output here? Or are these worlds fully meshed and textured assets?

From my understanding, admittedly quite a shallow look so far, the model generates gaussian splats then from that could implement the collider.

I guess from the splat and the colliders you could generate actual assets that could be interactable/animated/have physics etc. Unsure, exciting space though! I just don't know how I would properly use this in a game, the examples are all quite on-rails and seem to avoid interacting too much with stuff in the environment.

The page shows, near the bottom, how the main output is gaussian splats, but it can also generate triangular meshes (visual mesh + collider).

However, to my eye, the triangular meshes shown look pretty low quality compared to the splat: compare the triangulated books on the shelves, and the wooden chair by the door, as well as weird hole-like defects in the blanket by the fireplace.

It's also not clear if it's generating one mesh for the entire world, it looks like it is - that would make interactability and optimisation more difficult (no frustrum culling etc, though you could feasibly chop the mesh up into smaller pieces I suppose).

This sounds interesting and practical. Where can we follow your project?

My website is in my profile. I'll try to remember to write a blog entry in a few months. (Fair warning, I redo my website every 5-10 years to keep up to date with web technologies.)

FWIW: I was playing with an inexpensive (for me) Revo Inspire over the weekend. It feels somewhere between learning an instrument and taking a daguerreotype. There's a lot of room for improvement in the equipment for someone like me who just wants to casually scan something so I can make an attachment part. (I kind of wish there was a box that I could clamp something in, and then have it be about as easy as a flatbed scanner.)

I ended up covering my key fob with blue painter's tape, which kinda-sorta got it to scan. (I tried dry shampoo and drawing on it with marker, but I could never get a big enough area to scan.) When I imported the scanned fob into Tinkercad, it really distorted.

I ended up ordering a set of digital calipers and I'm going to try skipping the 3D scan part and go directly to CAD.