2. I used to engage small purpose-built DSL's, languages, and systems because they were easy to adopt. Now they're at a strong disadvantage for lack of AI coverage.
3. I focus a lot more on value to the customer; opportunity is now the limiting factor, so I have the product manager hat on most of the time. So I actually do less coding, pruning almost everything that I used to do just to see if I could.
4. I do try harder problems and techniques, because with AI I can typically get to a MVP I can validate and iterate (i.e., it minimizes the stage where nothing is really working). Sometimes it works, and sometimes it just gets blocked; it's more like hunting than gardening or building.
Overall, it's made skills matter less and opportunity/connections matter more, and those are mostly outside my control. That makes it generally de-powering because though I can do much more, the value of what I can do is diminished by a larger factor.