[dinvlad]

I know right? To me it feels like cheating in an exam, where I ask a know-it-all who gives a straight answer without me understanding it, but then it turns out that the know-it-all didn’t know it very well either, but just appeared confident, so we both failed the exam.

[lakySK]

If you treat LLMs as know-it-alls and just copy the output, then your expectations of the current generation of LLMs are too high.

That doesn’t mean they’re not useful though.

[dinvlad]

OK let’s say if I don’t, how can I make sure what I get is correct, even after a few iterations?

[hxugufjfjf]

You ask it to explain its reasoning step by step. This has also proven to yield more accurate results. Look into Chain of Thought

[dinvlad]

It’s not very good at explaining stuff though. One example: ask it to explain a subtle joke, and it will keep failing in funny ways.

This is not surprising though, as these kinds of models (LLMs) were specifically optimized for generation, not explanation.

[hxugufjfjf]

It's extremely good at explaining technical things like solving programming problems.