Clicking - nothing works.
Since this is from a chinese company/developer, having such an interesting concept/implementation, still getting just 2 comments.. whereas projects far less important or impactful get much more. This isn't the first time I have observed this bias.
I know the comments will try to justify this with well we don;t have a playable demo or code, but that still doesn't negate what I've said. The bias is there.
It's posted at midnight on Thursday (eastern time).
It's mobile unfriendly, hard to read, and has no videos. The other models had playable demos and videos, and they were posted in the middle of the day so we could think about it during work.
The hype wave for this stuff is going to require bigger splashes for each new model. New image-to-3D models garner a yawn, and it's going to be the same here soon.
These folks put a lot of thought into their branding (and CSS), but they kind of let the excitement fizzle as there's nothing to look at and evaluate. We just have to trust that they did things? It's a bunch of pictures of a car and green text.
It's far too late to open the paper.
Basically they just don't excel at marketing. 3/10.
Edit: I had no idea this was Chinese until you said it. The page doesn't mention names at top, and it didn't suck me into the paper.
was intrigued by the post but couldn't get anything to play
Of those ten:
• 6 had zero comments, 1 had only my own comment • 1 had 7 • 1 had 17 • 1 had 148
I have no reason to think there's a nationality thing here, stuff just falls off the top fast and most people don't comment or upvote… same as with most comments themselves.
Personally, these were the kind of glitches which made games feel magical and "real" to me as a kid. Being able to analyze a system by breaking it made it seem so much more tangible, like an actual place I had an NTSC-sized porthole into.
MissingNo. is another good example. I have fond memories spending untold hours in my favorite game engines trying to break free. The Jak and Daxter series were some of my favorite to break, due to the uniqueness and flexibility of the engine and the weird ways that the chunk loading system could be broken.
I am guessing the main thing holding this stuff back in terms of fidelity and consistency or generalization is just compute. But the new techniques they have here have just dramatically lowered the compute costs and increased the generalization.
Maybe just something like the giant Cerebras SRAM chips will get to the next 10 X in scale that smooths this out and pushes it closer to Star Trek. Or maybe some new paradigm like memristors.
But I'm looking forward to within just a few years being able to put on some fairly comfortable mixed reality glasses and just asking for whatever or whoever I want to appear in my home (for example) according to my whim.
Or, train it on a lot of how-to videos such as cooking. It just materializes an example of someone showing you exactly what you need to do right in your kitchen.
Here's another crazy idea: train on videos and interactions with productivity applications rather than games. In the future, for small businesses, we skip having the AI generate source code and just describe how the application works. The data and program state are just stored in a giant context window, and the application functionality changes the instant you make a request.
Wouldn't a working approach be to just create a really low resolution 3D world in the traditional "3D game world" sense to get the spatial consistency. Then this crude map with attributes is fed into frame generation to create the resulting world? It wouldn't be infinite, but on the other hand no one has a need for an infinite world either. A spherical world solves the border issue pretty handily. As I understood it, there was some element of that in the new FS2024 (discussed yesterday on HN).