One challenge is, are those decisions making tangible differences?

We won't know until the code being produced especially greenfields hits any kind of maturity 5 years+ atleast?

It's not that challenging, the answer is, it depends.

It's like a junior dev writing features for a product everyday vs a principle engineer. The junior might be adding a feature with O(n^2) performance while principle has seen this before and writes it O(log n).

If the feature never reaches significance, the "better" solution doesn't matter, but it might!

The principle may write once and it is solid and never touched, but the junior might be good enough to never need coming back to, same with a llm and the right operator.

What? Of course it makes a difference when I direct it away from a bad solution towards a good solution. I know as soon as I review the output and it has done what I asked, or it hasn't and I make a correction. Why would I need to wait 5 years? That makes no sense, I can see the output.

If you're using LLM's and you don't know what good/bad output looks like then of course you're going to have problems, but such a person would have the same problems without the LLM...