<?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[You have to beat the models at something]]></title><description><![CDATA[<blockquote>
<p dir="auto">I think it’s more useful to look at the tasks models <em>haven’t</em> gotten better at over time, and the tasks that are hard for them get better at in principle. The two best examples of these are:</p>
<ol>
<li>Deep familiarity with the codebase</li>
<li>Technical communication</li>
</ol>
</blockquote>
]]></description><link>https://forum.ieu.app/topic/fc06c372-0f88-46f5-b531-571a1658554c/you-have-to-beat-the-models-at-something</link><generator>RSS for Node</generator><lastBuildDate>Sun, 06 Sep 2026 01:59:35 GMT</lastBuildDate><atom:link href="https://forum.ieu.app/topic/fc06c372-0f88-46f5-b531-571a1658554c.rss" rel="self" type="application/rss+xml"/><pubDate>Tue, 01 Sep 2026 15:45:08 GMT</pubDate><ttl>60</ttl></channel></rss>