Obviously the following isn't a completely original take, but it's worth stating that AI coding is just a fundamentally different job than "traditional" or "manual" coding. The previous job was to spec something out to a comfortable degree without spending all of your time on a spec when there are so many unknowns that will come up during the engineering stage. Then, the job was to engineer at a snail's pace (compared to today) and adjust the spec.
Now, the job is to nail the spec and test HARD against that spec. Let the AI develop it and question it along the way to make sure it's not repeating itself all over the place (even this I'm sure is super necessary anymore...). Find a process that helps you feel comfortable doing this and you can get the engineering part done at lightning speed.
Both jobs are scary in different ways. I find this way more fun, however.
I don’t know that that's true. Iterating on the spec and development together as in traditional agile development seems to work well with AI. The pace is different (an iteration might be hours instead of weeks) and the human role is mostly as a combined architect/analyst/lead dev/product owner, but the issue that real requirements are rarely clear before software hits the hands of users doesn't go away just because an AI wiped more of the code.