Since automated coding systems can revise code and show the results much quicker than most human engineers can, writing detailed specs could be less necessary.
The bottleneck is still the person who has to evaluate the results.
The larger point is that building software is about making tons of decisions about how it works. Someone has to make those decisions. Either PMs will be happy letting machines make the decisions where they do not let programmers decide now. Or the PMs will have to make all the decisions before (spec) or after (evaluation + feedback look like you suggest).
