<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: haris599</title><link>https://news.ycombinator.com/user?id=haris599</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 29 Jul 2026 12:22:51 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=haris599" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by haris599 in "Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models"]]></title><description><![CDATA[
<p>Can you simply ensemble the outputs of all N models for each token? I'm curious how that compares to explicitly routing each token to a different model.</p>
]]></description><pubDate>Fri, 24 Jul 2026 06:06:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=49031726</link><dc:creator>haris599</dc:creator><comments>https://news.ycombinator.com/item?id=49031726</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49031726</guid></item></channel></rss>