[ellis-bell]

you might be able to do something like "predict the next prime number" or "predict the next zero of the Riemann zeta function".

you could try something like this for statements in a formal axiomatic system, but know that you're running up against things like the halting problem / entscheidungsproblem / godel incompleteness. so it may be possible to train a neural net to decide the veracity of a statement and do so more quickly than a human might, but you would inevitably be running up against things that are truly undecidable in nature. which is not like go or chess where although they are difficult, they are decidable.

[sanxiyn]

I am not sure how math is unlike chess. Chess has three outcomes: win, loss, draw. That seems exactly like math, having true, false, undecidable.

[gjulianm]

Yes, but it isn't useful. A conversation also has three outcomes (neutral, you like the person more, or less) and yet it doesn't make conversations similar to chess.

[whatshisface]

Chess and math are both searches over countably infinite trees.

[gjulianm]

And a conversation is a search over a countably infinite tree too.

My point is that even though some things have technical similarities, in practice they are very different challenges.

[whatshisface]

Math and chess are both very easy to check. Proof checkers and chess rule checkers both exist. "Conversation checkers" do not.

[ellis-bell]

chess is actually not very easy to check.

chess is in exp, the class of problems requiring exponential time to solve and exponential time to check. unlike p vs np we do know that exp \neq p.