[OutOfHere]

Even if two random vectors don't have high cosine similarity, and I have not had this issue in 3000 dimensions, the cosine similarity is still usable in relative terms, i.e. relative to other items in the dataset. This keeps it useful.

[acjohnson55]

Makes sense. I'm guessing it's one of those things where there's significant info in the magnitude of the exponent, in terms of relative similarity?