I use Gemini, and rarely ChatGPT (usually once or twice a day). I ask very narrow, pointed questions about something specific I would like an answer to. I typically will verify that the solution is good/accurate because I've been burned in the past by receiving what I'd characterize as a bad solution or "wrong" answer.

I think it's useful tool, but whenever I have a LLM attempt to develop an entire feature for me, the solution becomes to a pain to maintain (because I don't have the mental model around it or the solution has subtle issues).

Maybe people who are really deep into using AI are using Claude? Perhaps it's way better, I don't know.