[jeremy151]

I think for me, I'm still learning how to make these tools operate effectively. But even only a few months in, it has removed most all the annoying work and lets me concentrate on the stuff that I like. At this point, I'll often give it some context, tell it what to make and it spits out something relatively close. I look it over, call out like 10 things, each time it says "you're right to question..." and we do an iteration. After we're thru that, I tell it to write a comprehensive set of unit tests, it does that, most of them fail, it fixes them, and them we usually have something pretty solid. Once we have that base pattern, I can have it pattern and extend variants after the first solid bit of code. "Using this pattern for style and approach, make one that does XYZ instead."

But what I really appreciate is, I don't have to do the plug and chug stuff. Those patterns are well defined, I'm more than happy to let the LLM do that and concentrate on steering whether it's making a wise conceptual or architectural choice. It really seems to act like a higher abstraction layer. But I think how the engineer uses the tool matters too.