<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: elias_junit</title><link>https://news.ycombinator.com/user?id=elias_junit</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 28 Aug 2026 07:56:03 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=elias_junit" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by elias_junit in "Show HN: The load-bearing vocabulary of Claude"]]></title><description><![CDATA[
<p>I think you should recognise machine text not only by a list of words, but also by format. Right now, when it handles any complexity of text so well, the only thing that can differ is the structure. Machine text differs from human text in that it is just well structured. It does not allow non-linear narration. And it very often repeats some known social media patterns.</p>
]]></description><pubDate>Fri, 28 Aug 2026 01:16:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=49473264</link><dc:creator>elias_junit</dc:creator><comments>https://news.ycombinator.com/item?id=49473264</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49473264</guid></item></channel></rss>