Coding with AI assistants is just a completely different skill that one should not measure from the perspective of comparing it to the way human programmers write code. Mostly everything that we have: programming languages, frameworks, principles of software development in teams, agile/clean code/TDD/DRY and other debatable or well accepted practices — all this exists to overcome limitations of human mind. AI does not have them and have others.

What I found to be useful for complex tasks is to use it as a tool to explore that highly-dimensional space that lies behind the task being solved. It rarely can be described as giving a prompt and coming back for a result. For me it's usually about having winding conversations, writing lists of invariants and partial designs and feeding them back in a loop. Hallucinations and mistakes become a signal that shows whether my understanding of the problem does or does not fit.