<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: kmchandy</title><link>https://news.ycombinator.com/user?id=kmchandy</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 17 Aug 2026 09:34:45 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=kmchandy" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by kmchandy in "VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO"]]></title><description><![CDATA[
<p>The paper makes a clear claim: "it provides an important
and concrete proof: on well-constrained, verifiable reasoning tasks, first-tier performance is no longer the exclusive
domain of ultra-large models" And that's exciting.</p>
]]></description><pubDate>Tue, 23 Jun 2026 14:36:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48645661</link><dc:creator>kmchandy</dc:creator><comments>https://news.ycombinator.com/item?id=48645661</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48645661</guid></item></channel></rss>