This. I use LLM for work, primarily to help create extremely complex nested functions.
I don’t count on LLM’s to create anything new for me, or to provide any data points. I provide the logic, and explain exactly what I want in the end.
I take a process which normally takes 45 minutes daily, test it once, and now I have reclaimed 43 extra minutes of my time each day.
It’s easy and safe to test before I apply it to real data.
It’s missed the mark a few times as I learned how to properly work with it, but now I’m consistently getting good results.
Other use cases are up for debate, but I agree when used properly hallucinations are not much of a problem. When I see people complain about them, that tells me they’re using the tool to generate data, which of course is stupid.