I get the feeling that either I'm using LLMs wrong, or everyone else is.
Outside of enthusiastic use of Tab and some one-off scripts, I don't really tell it to write code. Instead I ask vague questions about the codebase and its inner workings.
Reading other people's code has always been my Achilles' heel - particularly if it's a huge project and has a lot of undocumented conventions. LLMs are brilliant at explaining this sort of stuff.
Shit, I know people that don't code that are asking LLMs for advice about personal matters. As far as AI companies are concerned, as long as you're using their product and are paying them for it, who cares what you're actually asking it for.
You're not using them wrong at all. Part of the reason LLMs are good at writing code is that they're good at understanding code. You're just not using the full menu of capabilities -- which is totally fine.