[ditchfieldcaleb]

Neural nets (particularly RNNs) can emulate arbitrary turing machines, so therefore are capable of said logical processing. LLMs might have to be coaxed into doing this, but with enough trying you can get them to be more rational/logical rules focused.

Give it a go - I'm sure you can come up with some math problem that is un-google-able. Use chain-of-thought prompting to have it solve a quintic polynomial or something.

I think this (being the result I imagine you'll get when you try the above) demonstrates that LLMs have learned the capability for general reasoning, even if they don't always automatically use it.

To be fair - neither do we.

[cwillu]

Obviously not exhaustive of possible approaches, but https://www.lesswrong.com/posts/DTLRw6ZstkdghEgqA/chatgpt-vs... was my attempt to get chatgpt to play a simple inductive reasoning game.

[ditchfieldcaleb]

Not the brightest, but a valiant attempt for a lower-iq...entity, I'd say.