A common dynamic I observe with AI: it feels most impressive when you don’t know much about the subject, don’t care or don’t have a clear idea of what the you want.
This applies across design, code, legal, and more. If I don’t know code very well, every piece of code it writes feels very impressive.
Once you know what something should feel or look like, it becomes almost impossible to guide AI there. And you definitely can’t one-shot it.
overcooking
you've seen this: someone ships a dashboard that shows every number with a sparkline, every action has a confirmation modal, every empty state has an animated illustration and a tagline. individually each decision made sense to someone. together it feels like chaos. nothing is in focus.
that's overcooking. not one bad decision in isolation, but the accumulation of reasonable ones that no one said no to.
AI makes this worse as the cost of adding dropped to near zero. it can build a feature, even a whole new concept in minutes. so people do. and then they do it again. the thing that started with a clear purpose slowly becomes a collection of additions that are each justifiable but collectively incoherent.
the root problem is that most "new ideas" aren't new. they're repackaging of something that already exists at a more fundamental level. a new sticker on an old concept. it feels like progress because something changed, with a new word and skin – but the thinking didn't go deeper, it just duplicated itself into confusion.
the whole has a core. you feel it once you understand the whole system. everything in it are related and balanced. when you overload it, that gravity weakens. not because any one thing is wrong – but because attention is finite and you force it everywhere.
what we need aren't more tools that make more slop. it's seeing through the chaos, and returning to what the thing actually is, and cutting everything that doesn't serve that. that's harder now, not easier. because there's always something else you could add with one more prompt.
on subtraction
adding is easy. someone asks for a feature, you build it. user hits a bug, you patch it. flow feels blocked, you add a shortcut. new trendy idea, you add a new concept. repeat until you have 50 buttons and no one knows where to start.
the hard part isn't building anymore. it's choosing:
- what to make – and what to leave out
- how to make it – so it strengthens the system instead of fragmenting it
- what to remove – even when it works, if it doesn't belong
addition is momentum. subtraction takes conviction.
you have to see the whole, not just the parts. you have to believe that fewer things, done right, will carry more weight than a hundred things scattered.
most products don't die from missing features. they die from accumulation. from losing clarity. from becoming everything and meaning nothing.
think slower, then act fast. slow down after the burst. tie it all back. so the foundation can carry what comes next.
keep focused, and simplify.
Instead of getting carried away, it's nice to be carried back instead. What's the essence of this? What's the core? Where's the epicenter? Have we slipped away from that?
Good questions to ask when making the first version of anything. If you're on to something, the footprint, the surface area, is usually quite small.
If it feels too big, get back to those initial questions.