I just ctrl+F this page for "markov" and: You could have replied to me directly, and no, im not over 30. It shouldn't be part of your argument.
Hmm.. what's the link between being over 30 and suggesting markov chains?
There isn't one, OP is attempting to prematurely discredit anyone who scrutinizes this "AI" as out of their depth with new technologies.
If the context window is finite, then LLMs actually are Markov chains. It's just that they're a much more efficient way of representing transition probabilities than storing them all in a giant lookup table.
What's a LLM? It isn't a logic learning machine, right? Or a load linked Markov
You mean, a large language model?
Aren't pretty much all post-docs in the field over 30?