AI's coding abilities take care of the mundane so I can focus on the more interesting bits. Plus, it sharpens your code review skills - you have to review the results and adjust as necessary.
Really want to know what these "more interesting bits" are that GPT-5-thinking and other models of this calibre cannot do. Unless of course you choose to do them even though these models can in fact do them, in which case, please do share regardless.