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?

As far as I remember the secret is to log in as admin and change the ownership of the files to yourself, then change permissions and then do whatever the f you want with the files.