I like the craft but I enjoy making products more. Working for 5 years on some tool chain/libraries has been great in terms of “technical” satisfaction but it would have been even more rewarding to build successful products with all that.

And I think this is really the best of both worlds because AI coding works best when you give it constrains and without my toolchain the AI is generating crap code I wouldn’t ever want to read but using the libs I wrote and know I can constrain it to write decent code that works “at scale” . The more opinionated the tools/libraries the better outcome you can expect.

Another great usage of AI is for refactoring. Before AI you could have a great idea how to make the library better/more ergonomic but the sheer amount of refactoring would make you just eat the debt and basically live with your own “slop”. Now with AI you can produce the reference design for the refactoring (I.e let’s make all these functions actually methods) and the job is done in minutes/hours. This inevitably leads to better designed software.