Hacker News Reader

Comment by tylerhou | Hacker News Reader

LLMs are decent at explaining up to undergrad mathematics but that is because they are parroting / plagiarizing the hundreds of human-written books that have been written for the express purpose of teaching undergrads. LLMs are actually fairly terrible at explaining higher mathematics; humans are much better.

View on HN

They are definitely doing more than parroting. When learning mathematics, it's not uncommon to have some little misunderstanding that just isn't covered by a written explanation because it's "obvious" unless you happen to have misunderstood it that particular way. When that happens, you could look up the topic in 5 books on the subject and not make progress (never mind that you have to search through them to get to roughly the right point). LLMs are genuinely good at challenges like this - they make mistakes, but they can still identify and correct your misunderstanding with a bit of back and forth.

A good human on the subject will do better, and I'm not claiming the LLM has "understanding" in any philosophical sense. But it's more useful than something that just regurgitates material.

> it's not uncommon to have some little misunderstanding that just isn't covered by a written explanation because it's "obvious" unless you happen to have misunderstood it that particular way... LLMs are genuinely good at challenges like this

For undergrad math, sure, and again, I think it's often because on some random corner of the internet someone else had a very similar misunderstanding. On the other hand, when I ask for clarifications on niche topics that have few examples on the internet LLMs (even Opus 5) often confidently cite irrelevant papers / results or simply hallucinate.

I think you're desperate to think that LLMs cannot make any sort of deduction by themselves: they must have just remembered someone else doing it. But I've definitely had conversations where they've had insights that can't be explained by that. Yes, I've had plenty of hallucinations too, but it's worth it, for me at least, overall.

Having said that, I wouldn't attempt to learn a whole topic with an LLM, that would be frustrating.

I am not desperate; I just have enough expertise and work in a niche-enough field to recognize that LLMs just are bullshit machines.

See https://claude.ai/share/6431ccd9-f4f8-4052-8996-b046d1ea1f76 for an example that I ran into just now.

We all run into hallucinations like in your example, but that doesn't mean that the AI cannot make connections between different areas of knowledge it has, and combine them usefully to something new that wasn't there before. Like Navier Stokes, for example. I've had it make plenty of such connections in my own research, giving me new results I didn't have before.

Sure. But it was a bitch to get access to a good maths textbook- either you forked out a lot of money, got a library loan (we had to renew ours every 7 days), etc. With an LLM there's good breadth of knowledge so if can quickly hop across topics rather than follow the progression proscribed by the author. There's also no element of judgement/ego etc etc.

They don't parrot if you know what to ask for. You can name for examples, name your own thoughts and observations and these things will often quote something related or the fact that a famous mathematician has also made this observation some point in time which then lead to the study of something else.

I am not going to study a whole book just so I can find the answer to a couple things I might never need. I like to focus on a few areas, learn everything I need to understand it, know if there are any dependencies and see what is there to discover and then move on.

I know many people get joy from learning knowledge that is not directly applicable and might never be applicable. And I know that the academic spirit would be to learn these things. But my time is seriously finite and I am not using math in my life in any fashion whatsoever other than occasional curiosity.

Reply on news.ycombinator.com