[raffael_de]

It's not about seeing. It's about identifying the legs of the Pelican and then transferring the concept and mechanics of riding a bicycle + geometry of a body and a bicycle. The entire task has also nothing to do with vision tokens.

[mountainriver]

If we want to train a model excessively on SVGs it will obviously be able to do this. We have only just started trying to do that

[WarmWash]

> It's about identifying the legs

So, seeing?

[raffael_de]

seeing isn't necessary to understand what a leg is.

[WarmWash]

Which I why humans can draw so well with their eyes closed?