When we have really fast *and* good models it will be able to generate a GUI on ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		joegibbs 3 months ago \| parent \| context \| favorite \| on: Three Years from GPT-3 to Gemini 3 When we have really fast and good models it will be able to generate a GUI on the fly. It could probably be done now with a fine-tune on some kind of XML-based UI schema or something. I gave it a try but couldn't figure it out entirely, consistency would be an issue too.

in-silico 3 months ago [–]

Google is already doing this with Gemini:

https://research.google/blog/generative-ui-a-rich-custom-vis...

I don't know if/when it will actually be in consumers hands, but the tech is there.

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