<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: floriangoebel</title><link>https://news.ycombinator.com/user?id=floriangoebel</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 06 Apr 2026 02:40:56 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=floriangoebel" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by floriangoebel in "Caveman: Why use many token when few token do trick"]]></title><description><![CDATA[
<p>Wouldn't this increase your token usage because the tokenizer now can't process whole words, but it needs to go letter by letter?</p>
]]></description><pubDate>Sun, 05 Apr 2026 10:35:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47648015</link><dc:creator>floriangoebel</dc:creator><comments>https://news.ycombinator.com/item?id=47648015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47648015</guid></item></channel></rss>