Why would you doubt neurons play a roll in intelligence when we've seen so much success in emulating human intelligence with artificial neural networks? It might have been an interesting argument 20 years ago. It's just silly now.
Is it?
These networks are capable of copying something, yes. Do we have a good understanding of what that is?
Not really, no. At least I don’t. I’m sure lots of people have a much better understanding than I do, but I think its hard to know exactly whats going on.
People dismiss the stochastic parrot argument because of how impressive big neural nets are, but it doesn’t really invalidate that argument. Is a very, very, very good parrot that learns from everyone at once doing basically the same as what we do? I’d argue no, at least not fully. It’s absorbed aspects of us extremely well/is a very weird, sophisticated mirror, yes, and is copying something somehow, probably in a way reminiscent of how we copy. Is it basically the same as what we’re doing when we think? Partially? Fully? Not at all?
A typical engineer would say “good enough”. That type of response is valuable in a lot of contexts, but I think the willingness to apply it to these models is pretty reckless, even if it’s impossible to easily “prove” why.
To be clear on the exact statement you made, I think you’re right/it’s pretty clear neurons play some very important role/potentially capture a ton of what we consider intelligence, but I don’t think anyone really knows what exactly is being captured/what amount of thought and experience they’re responsible for.
Anyway, thank you for a great answer and conversation throughout this thread.
Regards neural networks, parroting and the emulation of intelligence (or the difference between an emulation and the "real thing"):
Well, somewhat like you say, we cannot propose a valid comparison from one to the other without an understanding of one (consciousness) or both. It's fascinating that there are some open, valid and pressing questions about what / how the output of this new wave of software is concretized (from foundational, semi-statistical algorithms in this case.)
Yes, I do agree neurons have something to do with the "final output". But this is a subsection of the problem - organic neurons is-an/are order(s) of magnitude in complexity beyond what the tricky "parrot" is up to. Moreso, these components perform very different functionally - the known functions of the neuron compared to ANN, backprop etc. The entire stack.)
P.S: One interesting theory I like to simulate and/or entertain is that every organic cell in the body has something to do with the final output of consciousness.
And yeah, are definitely a lot of open questions related to all of this. Love how its brought so many deep questions into focus.
It would explain why most "experts" didn't see GTP-4's abilities coming. Many of them expected that it would take a major algorithm or technology improvement to do "real intelligent" things, because they fundamentally misunderstood intelligence.