AI interfaces should go beyond a chatbot: generative UI is next. Here's a demo of a library for LLMs that I've been working on. It prompts models with a vocabulary of rich components described using natural language. Presented at Causal Islands Conference last week.

This has come out of some of our innovation work at Mozilla, for more: May open source this officially if there's community interest.

Open sourced here!

@rupert_parry @causalislands I think a lot of people miss that the reason the chatbot is so successful is that the power is in non one shot scenarios. If you provide a google style single shot prompt, you are throwing away the best part.

@causalislands No reason it needs to be either/or

@rupert_parry @causalislands this is very refreshing! are you using the ReAct pattern and giving it tools that correspond to each UI element?

@causalislands Exactly – the model is prompted with a simple schema of components, as you would prompt with actions in ReAct. The output is runtime-agnostic – in this case I’ve implemented the output schema with web components (but it could be React, Swift UI, etc).

@rupert_parry @hwk73 @causalislands And yet it got the carbonara wrong. It's with pecorino, not parmigiano

@rupert_parry @causalislands Love it!

@rupert_parry @causalislands That's cool :) Would be neat to pre-emptively generate UI for likely subqueries (e.g. a dropdown menu + slider for cost constraints, or allowing users to click "Rome" and add other nearby destinations).

@rupert_parry @Scobleizer @causalislands This is already available in @weweb_io for some time now.