Hacker Newsnew | past | comments | ask | show | jobs | submit | pxheller's commentslogin

I feel like using sequential transformers generating code feels like a brute-force solution for UI generation.

The "obvious" path forward for frontend assistants is to move away from raw code generation toward some domain-specific language. UI is inherently structural - it should be expressed through component hierarchies that implement pre-defined design guidelines (with colors, margins, border radius etc being defined outside of the core model, and applied as a kind of theme to the model's output).

If we define the UI as a composition of VStacks/HStacks and predefined components, we can use diffusion models to generate the layout, and consistently apply the 'theme' afterwards. It's a much cleaner abstraction than asking an LLM to hallucinate valid CSS classes.


This is great! I really like the style of shadcn/ui.

Recently I’ve been using ChatGPT to convert shadcn components to JinjaX. Will definitely give yours a try!


Didn't know JinjaX, interesting.

FYI, I have Jinja macros available: https://basecoatui.com/installation/#install-macros


Still working on RunGen.AI – a platform to deploy any LLM or Image model from HuggingFace by just pasting a link.

Still a lot of work to do, but solves a real pain I had while building my previous side project


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: