I think back to the first version of ChatGPT and I would pick it up once in a while, ask it something or chat with it, and then be like... this is cool but I don't know wtf I would use it for, now I use a GPT at least a couple of times a day. Granted, the LLMs have obviously become considerably more capable, but I do believe part of it is I've also learned how to use them and what to use them for, I'm at the point now where I can generally predict the output of what I'm asking for - I don't know if that's the norm (it mostly gives me exactly what I want) I do know how I use them today and how I used them when they first came out is quite different. I guess all that is to say, imo how you prompt them really matters, and that takes time to learn.