<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: pokebear</title><link>https://news.ycombinator.com/user?id=pokebear</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 18 May 2026 09:34:05 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=pokebear" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by pokebear in "Show HN: Torrix, self hosted, LLM Observability,(no Postgres, no Redis)"]]></title><description><![CDATA[
<p>This is really cool! Since this can be hosted directly in my local machine, I would love to give it a try. I use gpt models a lot. Would let you know how it goes.</p>
]]></description><pubDate>Wed, 13 May 2026 20:18:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48126931</link><dc:creator>pokebear</dc:creator><comments>https://news.ycombinator.com/item?id=48126931</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48126931</guid></item><item><title><![CDATA[New comment by pokebear in "Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model"]]></title><description><![CDATA[
<p>This is really cool to see the push for tiny models</p>
]]></description><pubDate>Wed, 13 May 2026 20:14:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48126882</link><dc:creator>pokebear</dc:creator><comments>https://news.ycombinator.com/item?id=48126882</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48126882</guid></item></channel></rss>