[AnotherGoodName]

I've used LLMs to try to help digest some advanced maths. Eg. "Explain the number field seive with lots of numeric examples".

Yes the numeric examples often don't work. The consequences of this though are similar to a failed web search. As in it's not a big deal and when it does work it's very helpful.

Maths is one of those things with so much objectivity that even the LLM usually realizes it has failed to create a numeric example. "Here the numeric example breaks down since we cannot find a congruence of squares in this example without finding more B-smooth numbers in step 1". Ok that's a shame, i would have loved to see an end to end numeric example.

I think people get too hung up on any possibility of LLMs not being perfect while still being extremely helpful.

[lomase]

A LLM can't "realize" anything. Unless you are saying that LLMs are aware.

[AnotherGoodName]

It's a term i used to explain that in 'thinking' mode LLMs will read their own output and call out things like incorrect math statements before posting to the user.

Now you probably want a debate about the term 'thinking' mode but i cbf with that. It's pretty clear what was meant and semantic arguments suck. Don't do that.

[lomase]

I want people to use correct terms, i don't think that is unreasonable.

[chaps]

I'm all for avoiding anthropomorphism of these things, but what word (or set of words) would you use instead?