Totally agree with the thrust of this article, but wonder a bit about some details and the LLMs. Will look into measure of distance for vectors of binary or categorical (discrete) values.
The problem is that only the distance "is it the same thing or not?" makes sense. That is, there is no concept of "closer"/"further" that would make sense. And the use of meaningless one leads, of course, to nonsense.
Totally agree with the thrust of this article, but wonder a bit about some details and the LLMs. Will look into measure of distance for vectors of binary or categorical (discrete) values.
The problem is that only the distance "is it the same thing or not?" makes sense. That is, there is no concept of "closer"/"further" that would make sense. And the use of meaningless one leads, of course, to nonsense.