[bongodongobob]

I don't think that's true. They clearly group related things together and seem to be able to create concepts that aren't specifically in the training data. For example, it will figure out the different features of a face, eyes, nose, mouth even if you don't explicitly tell it what those are. Which is why they are so cool.

[zeusk]

Most of that magic comes from embedding no? which is clustering things by their relation in some N-dimensional space

[bongodongobob]

Exactly. It figures that out on its own. That's what "understanding" looks like in this context, imo.

[mewpmewp2]

They are cool, but then you are also cool.