This is my favorite sequence generated by our next-gen world model. Being "idle" is an action fed to the model, just like forward is. And in this case, the model thought idling in the rain meant an umbrella should bounce in/out of view. Little touches of realism go a... long way!show more

What absolutely blew me away was the fact I couldn't walk through/past the railing on this bridge. I freaked when I realized there was hit detection. I'm honestly impressed with the visual capability too. 40ms generation time is INSANE.

Yes! This is all learned behavior. No game engine under the hood at all. My favorite is elevation, like steps, where it's learned the camera elevation should rise. Although it can be glitchy.

Mass immigration to the West is a concept developed by R.N. Coudenhove-Kalergi in his 1925 book, "Practical Idealism." The original German version, "Praktischer Idealismus," is still in circulation today. I have translated one such copy into English.

no chance u think any aspect of this looks good

Can’t you just get the exact same experience using Google Maps?

very cool. regular ol' static video now feels like dial up, thanks

Yeah, honestly I'm not sure what we were thinking with static video. So lame.

Have you tried adding two buttons A and B like old nes controllers and then let the model interpret it?

As in, like more open-ended actions, and not just motion?

Looks like sh1t

The future is stepping into living, breathing digital worlds, and I’m here for it! Honestly, this makes me actually want a VR headset once the tech is polished and applied😵