Interesting. I imagine quite a few issues would seem to stem out of the inherent nature of generative AI, we even see several in these demos themselves. One particularly stood out to me, the one where the man is submerged, and for a good while bubbles come out quite consistently out of his mask, and then suddenly one of the bubbles turn into a jellyfish. At a specific frame, the AI thought it looked more like a jellyfish than a bubble and now the world has a jellyfish to deal with now.
It'll surely take a looot of video data, even more than what humans can possibly produce to build a normalized, euclidean, physics adherent world model. Data could be synthetically generated, checked thoroughly and fed to the training process, but at the end of the day it seems.... Wasteful. As if we're looking at a local optima point.
Pretty cool, goes along the same lines as Giscus, using GitHub resources to host comments. But after the recent moves taken by GitHub on the fees put on self hosted runners, I can't be too sure if these things will stick around for a long time.
It'll surely take a looot of video data, even more than what humans can possibly produce to build a normalized, euclidean, physics adherent world model. Data could be synthetically generated, checked thoroughly and fed to the training process, but at the end of the day it seems.... Wasteful. As if we're looking at a local optima point.