If this can generate VR videos and Scenes for the Vision Pro and other headsets

We would definitely be in the next era today     See Less

I love progress…but being from the “third world”, l hate that we keep minting billionaires and swallowing thousandaires to make them. 😫

How does all this tech actually enrich     See More ary folk’s lives?    See Less

This is so reminiscent of lucid dreaming... and also the concept that we are always dreaming, it's just that our waking dreams are framed by the physical world.

Future generative     See More l be guided by a 3d physics engine of some sort. We're so very close!

As 2 minute papers would say... Just another couple of papers down the line... and what a time to be alive!    See Less

I think we should STOP discussing what's "true understanding" (often conflated with "human understanding", which is inherently anthropocentric). Finding patterns in a     See More data and combining them to generate a new chain of events that a human couldn't see or generate alone, to me reads as a form of understanding and intelligence. These models have their representation of data and reality. We should aknowledge that, for the common good, instead of being always so dismissive just because they lack the diapason of intent and (human version of) consciousness that sparked their process in motion. I think it would be much more productive to focus on the possibilities, and risk mitigation, of a human-AI interaction where we elevate each other and are part of a whole ecosystem (which includes also the web of interactions and impacts humans have on other living beings). Future is about seeing the whole picture.    See Less

i think we are going to see an explosion of TV shows in the next few years.     See Less

OpenAI is literally following the path of the "Omega Team" from the book Life 3.0. Read it up, I think that chapter is available online for free. Makes you think that they already     See More nd just desperately need more computing power. And speaking of ANY online business or startup, everyone is at risk of becoming irrelevant.    See Less

AI videos still have lucid dream qualities.     See Less

15:47 Well how is it gonna learn to play chess from stock footage alone?     See Less

Great video as always! I think the video at 7:46 has been generated by sora though, it's listed as one example on open     See More log post. Speaks for itself that it isn't obvious anymore whether or not a video is AI generated    See Less

As well as extending the length and quality... it will need to create the audio and sync it up and keep it consistent. Imagine asking your wall (actually a TV) to create a good movie for you     See More you, and knows what you like. Then it plans out the movie and begins generating it. As it's watching you it notices what's working and what isn't and begins adjusting the script (it has to keep in mind what has already happened in the movie and the look of the people) and generating the movie as it goes. Does it sound outlandish? It shouldn't. Everything I've just described is really only limited by a few steps, and of course compute.

You'll also need old TV shows upscaled near perfectly and 4:3 video turned into 16:9 or even 3D (the depth stuff is arriving) with the AI filling in the detail that's missing in that old 4:3 image and keeping it consistent as you turn around or revisit old locations. None of this is all that SF now - there are still things to work through, but it's within reach. It's no longer a hopeless fantasy. Absolutely staggering.    See Less