<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Generative UI on Nan Xiao | 肖楠</title>
    <link>https://nanx.me/tags/generative-ui/</link>
    <description>Recent content in Generative UI on Nan Xiao | 肖楠</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Wed, 09 Sep 2026 11:39:00 +0000</lastBuildDate>
    <atom:link href="https://nanx.me/tags/generative-ui/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>shinygenui: Generative UI for Shiny</title>
      <link>https://nanx.me/blog/post/shinygenui/</link>
      <pubDate>Wed, 09 Sep 2026 11:39:00 +0000</pubDate>
      <guid>https://nanx.me/blog/post/shinygenui/</guid>
      <description>Sketched user interface skeletons. Procedurally generated with p5.brush.skeleton. It’s my pleasure to share that shinygenui is now on CRAN. It brings generative UI to Shiny: the developer defines a catalog of components, and a language model builds and updates an interface as users describe what they need.&#xA;You can install it with:&#xA;install.packages(&amp;quot;shinygenui&amp;quot;) Or get the development version from GitHub:&#xA;pak::pak(&amp;quot;nanxstats/shinygenui&amp;quot;) Apparently, language models are unsupervised multitask learners, but that’s so 2019.</description>
    </item>
  </channel>
</rss>
