Comment Re:We see this problem + AI is a tool, not a relig (Score -1) 120
I've been a developer for about 20 years. I've done desktop, web, and mobile (Android). I've worked with assembler, C/C++, Perl, Kotlin, etc. I do miss doing a lot of it by hand (I'm still doing some for now).
It seems to me the issue on the code + unit tests is that you:
(1) Need to do TDD with red/green refactor -- so it can't cheat by optimizing the test code to pass the written code.
(2) Need to have different agents for each
I'm still learning a lot of this, but that's what seems to be the direction to go from all I've researched so far.