I haven’t been in development for nearly 20 years now, but I assumed it worked like that:
You generate unit tests for a very specific function of rather limited magnitude, then you let AI generate the function. How could this work otherwise?
Bonus points if you let the AI divide your overall problem into smaller problems of manageable magnitudes. That wouldn’t involve code generation as such…
Am I wrong with this approach?
I use Windows 11 without an MS account and with Classic Shell. You can hardly tell a difference. I will continue using it. Because I can’t be bothered not to. It also came with my computer (well, W10 did but the upgrade worked painlessly).