News for hackers. Stuff that matters.

A comment on Video generation models as world simulators. Parent comment

Re:Video generation models as world simulators by verticalscaler on Friday February 16, 2024 @12:20AM (#39393476)
A 3d model with object permanency is definitely a step in the right direction of something or other but for clarity let us dial back down the level of graphical detail.

A Pacman bot is not AGI. Might get it to eat all the dots correctly where as before if something scrolled off the screen it'd forget about it and glitch out - but you didn't fan any flames of consciousness into existence as of yet.

[ Parent | on HN ]
Re:Video generation models as world simulators by Solvency on Friday February 16, 2024 @09:13AM (#39397236)
Is a human that manages to eat all the skittles and walk without falling into deadly holes AGI? Why?
[ Parent | on HN ]
Re:Video generation models as world simulators by verticalscaler on Friday February 16, 2024 @10:38AM (#39398446)
Object permanence is a necessary but not sufficient condition for spatial reasoning but the definition of consciousness remains elusive unless you have some news to share.

A blind human is AGI. So is a drunk or clumsy one that falls into deadly holes. This is super cool and a step on the way to... something.. but even the authors don't claim it is somehow the whole ballgame.

[ Parent | on HN ]