<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: k08200</title><link>https://news.ycombinator.com/user?id=k08200</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 30 Jun 2026 21:27:24 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=k08200" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by k08200 in "Why did one day of AI cost more than a month of servers?"]]></title><description><![CDATA[
<p>A big part of the cost explosion is using the frontier model for tasks that don't need to be done. I tried using the gpt-4o and much cheaper models, and the cheaper ones were more accurate in my three — paying for the reasoning depth that I don't use. The other half is asking the model to do what deterministic rules should be. Calls that don't are the cheapest. Starting with profiling what calls the larger model really needs.</p>
]]></description><pubDate>Mon, 29 Jun 2026 14:35:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=48719817</link><dc:creator>k08200</dc:creator><comments>https://news.ycombinator.com/item?id=48719817</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48719817</guid></item><item><title><![CDATA[Show HN: Klorn–I built an email firewall because every AI inbox made mine louder]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/k08200/klorn">https://github.com/k08200/klorn</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48719602">https://news.ycombinator.com/item?id=48719602</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 29 Jun 2026 14:18:44 +0000</pubDate><link>https://github.com/k08200/klorn</link><dc:creator>k08200</dc:creator><comments>https://news.ycombinator.com/item?id=48719602</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48719602</guid></item></channel></rss>