[robotresearcher]

A state vector can represent a point in the state space of floating-point representation, a point in the state space of a hash function, or any other discrete space.

Vectors didn't go anywhere. The article is discussing which function to use to interpret a vector.

Is there a special meaning of 'vector' here that I am missing? Is it so synonymous in the ML context with 'multidimensional floating point state space descriptor' that any other use is not a vector any more?

[ummonk]

Keep in mind that this is the same field which uses multidimensional arrays that fail to obey tensor transformation laws (because ML requires the kind of nonlinear structure introduced by functions such as ReLU that requires a preferred basis and cannot be transformed between bases) but insists on calling them tensors.

[Firmwarrior]

The title probably makes a lot more sense in the context of where it was originally posted

I was as confused and annoyed as you were, though, since I don't have a machine learning background