<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Elixir, Agents, and AX/UX]]></title><description><![CDATA[All about Elixir, AI Agents, User Experience, and Agent Experience]]></description><link>https://boothiq.hashnode.dev</link><image><url>https://cdn.hashnode.com/uploads/logos/69a34cc6a7428b958d518765/db9b4318-bab9-4b5a-ad4a-85e24783b82e.svg</url><title>Elixir, Agents, and AX/UX</title><link>https://boothiq.hashnode.dev</link></image><generator>RSS for Node</generator><lastBuildDate>Fri, 20 Nov 2026 17:03:42 GMT</lastBuildDate><atom:link href="https://boothiq.hashnode.dev/rss.xml" rel="self" type="application/rss+xml"/><language><![CDATA[en]]></language><ttl>60</ttl><item><title><![CDATA[150,000 Lines of Vibe Coded Elixir: The Good, The Bad, and The Ugly]]></title><description><![CDATA[TL;DR: Good: AI is great at Elixir. It gets better as your codebase grows. Bad: It defaults to defensive, imperative code. You need to be strict about what…]]></description><link>https://boothiq.hashnode.dev/150-000-lines-of-vibe-coded-elixir-the-good-the-bad-and-the-ugly</link><guid isPermaLink="true">https://boothiq.hashnode.dev/150-000-lines-of-vibe-coded-elixir-the-good-the-bad-and-the-ugly</guid><category><![CDATA[Elixir]]></category><category><![CDATA[vibe coding]]></category><dc:creator><![CDATA[John from BoothIQ]]></dc:creator><pubDate>Sat, 28 Feb 2026 20:18:30 GMT</pubDate><content:encoded><![CDATA[<p><a href="https://getboothiq.com/blog/150k-lines-vibe-coded-elixir-good-bad-ugly">https://getboothiq.com/blog/150k-lines-vibe-coded-elixir-good-bad-ugly</a></p>
<p><strong>TL;DR:</strong></p>
<ul>
<li><p><strong>Good:</strong> AI is great at Elixir. It gets better as your codebase grows.</p>
</li>
<li><p><strong>Bad:</strong> It defaults to defensive, imperative code. You need to be strict about what good Elixir looks like.</p>
</li>
<li><p><strong>Ugly:</strong> It can’t debug concurrent test failures. It doesn’t understand that each test runs in an isolated transaction, or that processes have independent lifecycles. It spirals until you step in.</p>
</li>
<li><p><strong>Bottom Line:</strong> Even with the drawbacks, the productivity gains are off the charts. I expect it will only get better.</p>
</li>
</ul>
]]></content:encoded></item></channel></rss>