Generative Models: What do they know? Do they know things? Let's find out

Re:Generative Models: What do they know? Do they know things... by qingcharles on Friday February 23, 2024 @09:11PM (#39488495)

Essentially similar perhaps to the 3D engine that a human brain runs that generates a single "3D" image from two 2D cameras (eyes) and fills in missing objects in blind spots, etc.

[ Parent | on HN ]

Re:Generative Models: What do they know? Do they know things... by tsimionescu on Saturday February 24, 2024 @12:34AM (#39489386)

Note that while having two eyes helps build a more accurate 3D image, people with one eye still see in 3D. Eye movement is at least as important a part of 3D vision as stereoscopy.

[ Parent | on HN ]

Re:Generative Models: What do they know? Do they know things... by dougmwne on Saturday February 24, 2024 @05:43PM (#39495810)

And apparently 3D renders can be inferred from only 2d images like in these image gen models, so even without video or parallax, brains could probably model the world in 3D.

[ Parent | on HN ]

Re:Generative Models: What do they know? Do they know things... by daxfohl on Saturday February 24, 2024 @12:35PM (#39493385)

I remember a wittgenstein thing asking to think of a tree or something, and then point to the place in your head where that thought exists. It's kind of like that.

[ Parent | on HN ]