Does this hold if you first agree on a pool of words?
as in, both bot and human come up with a larger list, and you pull common suggestions into a pool that both subsequently pick a list from?
probably not, because I would imagine that's the tell, but I'm curious...
One of my favorite findings about LLM text detection is that if you make a random list of 100 words, it'll flag as human-generated.
But if you ask an LLM to make a random list of 100 words, it'll flag as AI-generated.