The linked post demonstrates arbitrary re-ordering of image patches. Spatial continuity is not relevant to neural networks.

That's ridiculous, sorry. If that were so, we wouldn't have positional encodings in vision transformers.

It's not ridiculous if you understand how neural networks actually work. Your perception of the numbers has nothing to do w/ the logic of the arithmetic in the network.

Do you know what "positional encoding" means?

Completely irrelevant to the point being made.