Ask HN: Why coding assistants are so bad at UI?

A developer reports that AI coding assistants struggle with UI development, citing issues like ignoring specified frameworks, missing patterns, and misplacing elements, despite performing well on pure code. The user notes that while multimodal agents exist, current tools often fail to produce accurate visual layouts without extremely detailed instructions.

On one hand they can't see. Haven't seen a "give me an svg unicorn" test since a while, but I guess their performance hasn't changed a lot. If you give broad prompts, then that will result usually in some garbage. As an anecdata, a few weeks ago I was creating some UI with libSDL for an embedded project with Claude, and I was quite impressed with the result. Granted, I specified everything I could think about: I instructed it page by page, iterating button by button and label by label. 1. Did not use the UI framework currently being used in the web app; 2. Did not see the pattern, I always use header, but it skipped; 3. Wrong placement of elements, e.g. one element should have been on the left pane, instead it put it on the top right and so on. I agree that on pure code they are OK, but I thought maybe I am missing something? That is incorrect for most modern agents, which support multimodal inputs and are trained as such as it is an inherent requirement for things such as computer vision. There's a reason OpenAI didn't release Codex-only variants of GPT 5.4 and up.