i wonder if you could use a bayesian classifier, like the first anti-spam measures used, to automatically classify these submissions.

Kind of off-topic - but why is there always so much focus amongst AI-bros on how good or whether or not LLMs are good at building UI? My shallow assumptions were that the reason is because that's what LLMs are particularly bad at.

But lately I've kind of gotten the sense that a lot of people seem to mostly be building UI stuff with LLMs. Weird.