Hacker News Reader

Comment by heavyset_go | Hacker News Reader

Humans can reason, ML models just follow statistical correlations.

What is "reasoning" if not an emergent property of complicated enough statistical correlation systems, with some bells and whistles?

Reasoning is often purely symbolic.

You take symbol A and derive another symbol from it or combine multiple symbols to form new symbols.

You can approximate this through statistics but sometimes approximations aren't enough.

Modern ML models (the kind used in GPT) are Turing-complete afaik

A model takes a fixed length input and returns a fixed length output in finite time, it's not Turing complete

Just equip it with a paper tape, give it the current cell and state as input and use the output to decide whether to move the tape or write to it. I'm sure you could encode a universal TM in a handcrafted neural net this way.

Maybe it's cheating, but after all, this is the only way humans can do universal computation- we can't hold an infinite tape in our head either, and neither can a CPU, we have to give it sufficient scratch space to act as the tape.

Alternatively, perhaps there's a (very large) neural net that can prove things about Turing machines that aren't too large. It only has finite input and finite output (it's not Turing complete) but it can prove stuff about smallish Turing machines, providing the proofs aren't too long. That seems reasonable, because that's what humans do when we prove stuff about Turing machines! Perhaps neural nets could never actually do this, either they're fundamentally not capable or we never work out how to actually find one that does, but it seems possible?

But reasoning includes statistical correlations

Statistical correlations are a subset of reasoning in general

They aren't a subset of reasoning, they are data points that could be reasoned about (like whether it could be recognised as something known as a notion of <statistical correlation> and whether it make sense from a semantic point of view). Data points could be statistical or non-statistical, and it's the reasoning mind that distinguishes between the two alternatives based on other notions of the world phenomena that make statistics distinguished from non-statistics.

A method of producing statistical correlations is a product of a reasoning mind and could be thought of as a subset of reasoning (if by "subset" we assume "everything produced by a reasoning mind via an act of reasoning"), but in order to recognise this "subset" another reasoning mind should firstly internalise the notions of statistics that are external phenomena to an act of reasoning itself. And "the act of reasoning" isn't proven to be "just something that produces correlations", it's more than that and nobody knows what exactly it is. Otherwise AI would be solved long time ago.

Is that really how you reason, though? Do you think you really reason by having some kind of subconscious statistical computer in your brain somewhere?

Obviously not, a lot of reasoning boils down to modus ponens.

My understanding was that it does a limited form of reasoning via "train of thought." Maybe it can only transform the ideas in the ways it was trained with but when you break it down there are only so many primitives here.

Reply on news.ycombinator.com