Trouble is, that last 10% of the task is what takes most of the time.
That, and the work to be done after release, is where you'll reap the benefits of good design and good coding: troubleshooting, lifecycle updates, data mining and reporting, changes to external interfaces and integrations. Requirements from users and for reporting and integrations change all the time. With a poor design, those changes are difficult and expensive to implement.
I wonder how well AIs do at such jobs, and would like to compare it to my own code. My code is a horrible mess that is hard to understand for anyone, let alone maintain or change it. But it works, and I can code fast. I used to write a lot proof-of-concept code or emergency code (when companies needed something on short notice to comply with regulations for instance), but I never had much of a hand in writing code for properly maintained production systems. Is AI code of the same quality: functional but poorly structured?
I don't do a lot of coding anymore, but I've got a private project coming up and I might give AI a shot at it. Should be fun!
Only God can make random selections.