[Nathanba]

Really interesting how this goes against my intuition. I would have imagined that it's infinitely easier to analyze a camera stream of the real world, then generate a polygonal representation of what you see (like you would do for a videogame) and then make AI decisions for that geometry. Instead the way that AI is going they rather skip it all and work directly on pixel data. Understanding of 3d geometry, perspective and physics is expected to evolve naturally from the training data.

[rasmusfaber]

Another instance of the bitter lesson: http://www.incompleteideas.net/IncIdeas/BitterLesson.html

[stravant]

> then generate a polygonal representation of what you see

It's really not that surprising since, to be honest, meshes suck.

They're pretty general graphs but to actually work nicely they have to have really specific topological characteristics. Half of the work you do with meshes is repeatedly coaxing them back into a sane topology after editing them.

[boppo1]

Do we have anything better than meshes that is as generally useful though?