<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: dgoet</title><link>https://news.ycombinator.com/user?id=dgoet</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 21 Apr 2026 16:39:46 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dgoet" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dgoet in "Show HN: How I Topped the HuggingFace Open LLM Leaderboard on Two Gaming GPUs"]]></title><description><![CDATA[
<p>Fantastic. Really gets me thinking.<p>If more than two repetitions of the “thinking organ” leads to worse results (I think that’s what you’ve said in other comments), would it be possible to get better results by slicing and dicing some of the early-layer “preparatory organs” between the thinking organs?<p>Maybe that would still require fine tuning to “evolve” an intermediary organ that would allow for multiple repetitions.</p>
]]></description><pubDate>Wed, 11 Mar 2026 00:11:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47330397</link><dc:creator>dgoet</dc:creator><comments>https://news.ycombinator.com/item?id=47330397</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47330397</guid></item></channel></rss>