[Arkhaine_kupo]

Why ask a human being who might have the exact knowledge you are looking for when you can ask the "dumb machine of making things up and getting things wrong" instead.

Now being serious, LLMs are nondeterministic loosy compression algorithm which return "what a plausible answer to that question would be". They have no world model, no truth verification and formally will be excellent while having no verifiable content.

[doodlesarefun]

Yeah, but despite that they work pretty good lately if what you're asking is verifiable, like searching for the name of a book.

[Arkhaine_kupo]

If you think of it as lossy compression algorithm that makes sense.

"There is a book about a boy in a magical school, with friends, who fights a big bad and its called ..."

should have Harry Potter as the highest possible response. But that is not the answer based on a truth model, just a statistical average. You could have been looking for Earthsea series. Or it could have the heat turned up and decide to go for a hallucinated answer over the statistically most likely token.

If you want a verifiable answer your best options would be to have the heat turned to 0, but that means it cannot create new responses. Or if you have heat, to ask 4 times and sample the avg. But at that point what is the advantage over just googling it?

And one shooting your answer and hoping its the bell curve answer is going to have decent results but its also proveably going to fail in a non insignificant number of cases

[eru]

> If you want a verifiable answer your best options would be to have the heat turned to 0, [...]

I don't see how that helps? If you just want the same answer multiple times in a row, you could just write down the seed of your pseudorandom number generator?

> And one shooting your answer and hoping its the bell curve answer is going to have decent results but its also proveably going to fail in a non insignificant number of cases

Setting the temperature to 0 doesn't guarantee you get a good answer either.