AI for Engineering vs Art
I've been coding pretty intently on something in my off hours (I'm excited to share more once it takes shape). Like the carpenters I watch on YouTube working almost exclusively with hand tools, this is very much a labor of love, so I'm being very deliberate with when, where and why I use AI. I've very sparingly offloaded the soulless, non-creative, non-gratifying code to Claude in the same way the carpenters I watch will occasionally use a power drill when they need 32 precise holes.
What I haven't accounted for was, as I've been working on this, my daughter taking a keen interest in watching me code. She's enjoyed watching me iterate, refine, expand - and she's asked with a lot of curiosity about design-thinking that goes into building something from the ground up - or, more precisely, as things have gone from generic to specific.
To simplify the principles, I related things to grammar: Describing our weekend to a friend we can quickly and succinctly encapsulate a lot of activities by saying "I verbed, I verbed objects, I verbed objects adjectively, and I adverbly verbed objects adjectively, etc." That may not be the most gratifying description of our weekend, but it captures the important structures for what we'd described and we can use those structures in infinite ways. Once we establish those structures, we can get increasingly specific.
As we talked about it, I was thinking about how much of what we build, software or otherwise, starts with a generic structure that becomes more refined. A house starts with a foundation and a frame. However, there are many things that only establish the generics in reverse - when we dissect something to understand it better: Poets don't structurally lay out their poems with grammatical terms serving as generic placeholders. They write in ways to best capture the emotion or meaning. But when we dissect the poem to better understand its effect upon us, we see those structures reveal themselves. Same goes for dissecting music, stories, and other art forms.
Which takes me to the question I'm actively thinking about lately: Can Art be defined as Specifics-first and dissected into Generics, while Engineering be seen as Generics-first and refined into Specifics? And is that why, when we start either effort in the wrong way, we see problems? Specifics-first engineering will lead to maintenance problems, problems of scale, duplication, etc. And creating Art by starting with Generics makes it feel engineered, artificial, inauthentic.
Finally, is that where we the line is for when it's best to incorporate AI? Engineering - use AI as part of your generics, build and refine from there. Art - create with human specificity first, and then use AI sparingly to help with whenever mechanical refinements are needed (editing, continuity checks, etc.)
