News for hackers. Stuff that matters.
Re:Can AI do maths yet? Thoughts from a mathematician by portaouflop on Tuesday December 24, 2024 @01:47AM (#42500129)
A human researcher that is basically right 40%-95% of the time would probably an Einstein level genius.

Just assume that the LLM is wrong and test their assumptions - math is one of the few disciplines where you can do that easily

Re:Can AI do maths yet? Thoughts from a mathematician by rednerrus on Tuesday December 24, 2024 @12:46PM (#42503481)
It's pretty easy to test when it makes coding mistakes as well. It's also really good at "Hey that didn't work, here's my error message."
Re:Can AI do maths yet? Thoughts from a mathematician by amanda99 on Tuesday December 24, 2024 @05:22PM (#42505363)
I think you are imagining a different class of "questions".

To clarify, I was doing research on applied math. My field is not analysis, but I needed to prove some bounds on certain messed up expressions (involving special functions, etc), and analyze an ODE that's not analytically solvable. I used the COT model a fair bit.

I would ask ChatGPT for hints/ideas/direction in proving various bounds, asking it for theorems or similar results in literature. This is exactly the kind of thing where a researcher would go "yeah this looks like X" or "I think I saw something like this in (book/article name)", or just know a method; or alternatively say they have no clue. ChatGPT most often will confidently give me a "solution", being right 10% of the time (when there's a pretty standard way to do it that I didn't see/know).

On the whole it was quite useful.