<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Coding on Lanie: Faith, Tech, and Advocacy</title>
    <link>https://lanie.work/tags/coding/</link>
    <description>Recent content in Coding on Lanie: Faith, Tech, and Advocacy</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 23 Aug 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://lanie.work/tags/coding/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Ramp, Not the Shortcut</title>
      <link>https://lanie.work/advocacy/the-ramp-not-the-shortcut/</link>
      <pubDate>Sun, 23 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://lanie.work/advocacy/the-ramp-not-the-shortcut/</guid>
      <description>&lt;p&gt;There&amp;rsquo;s a conversation happening in the NVDA community right now about AI and the add-ons people are building with it. Some of it is careful and fair. Some of it isn&amp;rsquo;t.&lt;/p&gt;&#xA;&lt;p&gt;The word that keeps coming up is &amp;ldquo;vibe coding.&amp;rdquo; The idea is that someone types a prompt, takes whatever the AI gives them, and ships it without ever reading the code. The worry is fair. A screen reader sees everything. Passwords, bank details, letters from a doctor. Unvetted code is a serious risk, and I&amp;rsquo;m not here to argue with that.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
