> I realized then that the humor of those early markov generations was the ridiculousness. The point where, a few words or sentences in, you realized it was all nonsense. LLM's these days are too good for that - the text they generate is sometimes wrong, but rarely nonsense in a humorous way.

This is the biggest challenge I run into when I see LLM Generated nonsense.

So much stuff that ChatGPT spits out is close enough to true that Brandolini is laughing.

But it's also that it's borrowing on stuff that's already there so it can't really get that 'creative' either.