alt Hacker NewsWe don't have a reward function for "human understanding". We reward the appearance of understanding. We define goals that we cannot conceive of reaching without something like understanding happening. There is something happening, but it is alien and counter-intuitive - it makes bizarre mistakes that betray it - and we don't know what it is. I'm pretty sure it is not human understanding.
Replies
> We reward the appearance of understanding.
Which is exactly what happens with human evolution and development. Sure, we can say LLMs don’t have “human” understanding - which is something we can’t really define anyway - as long as we’re not trying to claim LLMs don’t have understanding at all. The latter is a much higher bar.
> We define goals that we cannot conceive of reaching without something like understanding happening.
Functionally speaking, that is understanding. Again if you want to go past a functional definition, that’s a bar which no one can clear right now.
> we cannot conceive..
That is it. We cannot concieve it because we are new to it. Just like we would think of Stackoverflow as intelligent if we are fresh off the jungle and are not aware of how Internet works. Because without know that, we cannot conceive how Stackoverflow can produce answers without it "understanding"