What sort of maths are LLMs good at?

Re:What sort of maths are LLMs good at? by steinwinde on Wednesday August 12, 2026 @08:50AM (#49271636)

For a list of AI accomplishments in mathematics see https://mathoverflow.net/questions/502120/examples-for-the-u... - or a candidate list here: https://aimath.robertj1.com/ . Many have observed an affinity of AI to the search for counterexamples - or examples. Looking at afore lists, something much more sociological crosses my mind: There is a hunt for answering prominent, clearly stated problems. I'm not a mathematician, but is this mostly what progress in mathematics is about? How about stating worthwhile problems in the first place? What about theory building? Am I right saying this is equally important, but none of those utilizing AI for mathematics seem to be interested in such?

[ Parent | on HN ]

Re:What sort of maths are LLMs good at? by user43928 on Wednesday August 12, 2026 @09:32AM (#49272155)

I know nothing about mathematics, but are there not famous mathematicians like Terence Tao who utilize AI and are obviously interested in theory building?

[ Parent | on HN ]

Re:What sort of maths are LLMs good at? by robotpepi on Wednesday August 12, 2026 @03:00PM (#49277046)

Tao is a good example of a (extremely good) problem solver that doesn't build theory.

[ Parent | on HN ]

Re:What sort of maths are LLMs good at? by zmgsabst on Wednesday August 12, 2026 @05:55PM (#49279128)

You’re correct that those things are also what mathematics is about — but they’re less constrained, hence current LLMs aren’t as good at them.

However, your last question is incorrect: people are working on that, but there haven’t been hugely useful results.

But as an example, I’ve been slowly working on implementing frameworks for theory distillation — eg, take a corpus of science papers and derive a consistent model of the world from them, such as in Lean. (Or more specifically, a sheaf defining what consistent theories are possible.)

[ Parent | on HN ]