<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: hnretards</title><link>https://news.ycombinator.com/user?id=hnretards</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 05 Jun 2026 02:14:57 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=hnretards" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by hnretards in "Embarrassingly simple self-distillation improves code generation"]]></title><description><![CDATA[
<p>I've been doing something even better than this for years using only Mistral 7b.<p>My local running Mistral 7b is a 100x better at modern JavaScript than any model on the market, mainly just from RAG on my own code samples.<p>That's basically what they are describing with "post-training", the TLDR is that code especially of a certain style is vastly simpler than written language.<p>You really don't need a huge model or data centers etc. you just need a small but good model like Mistral 7b and literally a few good samples.<p>But you guys keep doing you lol. A bunch of non-devs trying to solve code is pretty funny to watch.</p>
]]></description><pubDate>Sat, 04 Apr 2026 21:38:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47643722</link><dc:creator>hnretards</dc:creator><comments>https://news.ycombinator.com/item?id=47643722</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47643722</guid></item></channel></rss>