<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: ChimpWithHat</title><link>https://news.ycombinator.com/user?id=ChimpWithHat</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 06 Oct 2026 02:07:58 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ChimpWithHat" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ChimpWithHat in "Agents don't need memory, they need documentation"]]></title><description><![CDATA[
<p>I partially agree, way too many people are cargo culting overly complex AI workflows with little empirical data. My framing is a bit different though, I consider code the spec and actually keep a decent amount of docs for higher level concepts. So far this is working well for me across Claud and Codex.</p>
]]></description><pubDate>Sun, 04 Oct 2026 22:21:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=49958522</link><dc:creator>ChimpWithHat</dc:creator><comments>https://news.ycombinator.com/item?id=49958522</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49958522</guid></item></channel></rss>