AI is great for offloading problems that you don't want to solve, but you want done. The key is finding what problems you find important to solve yourself.

At this point, roughly all the code I push is generated by AI. I find the code itself to be mostly an implementation detail of what I'm trying to do. However, I do not trust AI to write sustainable software that I can easily extend in ways that I know the project should eventually head.

I have found using openspec (no affiliation, just enjoy the tool) to be useful for raising my interface to projects up a layer of abstraction, from code to natural language. I use my agent to help me author specifications before firing it off to implement something. The key for me has been exercising the discipline of reading every single word of the specifications, and making sure that it aligns with my understanding and intent. This is where I have moved my attention now.

I think this has parallels with AI in art contexts. I think AI can be nice for getting to the part of art that you actually enjoy doing. Maybe you like making films, but the part that brings you joy is creating story boards. Recording, scripting, editing, etc. are chores to you, and maybe you don't have the resources to find people to fill those roles. AI can help you focus on the part that matters to you.

In the case of knitting, OP seems to find value in doing something with their hands, and sees the problem solving portion of it as a bonus. The latter can be inhibitive though; some may not push through that wall, and just not get the benefits of making something with their hands. I think AI is reasonable in this case, because they're not offloading the part that brings them joy.