More guidance is needed on how to efficiently prompt an LLM to generate a correct UI. Describing the appearance, placement and behavior of UI elements for this is quite time-consuming. The contrast with server-side code generation is stark.
UI design (not implementation) is an area where “describe it with a programming language” has historically not worked. So much of what makes a UI good or bad is determined reactively after seeing the initial prototype. Those refinements are rarely based on an encoded set of principles that found their way into a training set, and the code used to implement such refinements was varied enough that models and humans both struggle to infer its intentions after the fact.
nacozarina · · focus · HN ↗
max__dev · · focus · HN ↗
zbentley · · focus · HN ↗