[StellarScience]

I've been writing complex scientific UIs for more than two decades and still don't feel like I always get it right. We aim for "gradual reveal" and making the most common options easy to find and use, but it's hard to get that right for everyone.

Microsoft tried hiding less commonly-used menu options a decade or so with Office and it was so terrible they abandoned it - only to try the same approach with the Windows 11 Explorer menu.

I absolutely hate that rigid "Basic" vs. "Advanced" distinction, but one of our image processing UIs was so complicated a customer really pressed us to add that. We tried and tried and couldn't come up with something better, so we settled on an approach that I still feel is suboptimal.

So I welcome seeing what AI/LLMs may be able to contribute to the UI design space, and customizing per user based on their usage seems like an interesting experiment. But at the same time I'm skeptical that AI will really excel in this very human and subjective area.

[grouchy]

I agree that the basic vs. advanced or persona A vs. persona B distinction is usually too rigid.

What makes you skeptical that AI will excel at this?

[StellarScience]

The AI spreadsheet example in the linked article is interesting, but that occurs within a more specialized and constrained environment than general GUI design. I think of good UI design as involving a lot of human factors understanding combined with 2D spatial reasoning and layout, which I don't think AI is good at. (Today's article about Claude failing to reproduce an HTML layout to match a screen capture is one example of this: https://news.ycombinator.com/item?id=46183294 )

But my pessimism may be unfounded or based on ignorance. At some point AI will probably get better at these things as well, either with better LLMs or by augmenting LLMs with outboard spatial reasoning modules that they can interact with.