<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: couldaidothis</title><link>https://news.ycombinator.com/user?id=couldaidothis</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 07 Nov 2026 16:27:21 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=couldaidothis" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by couldaidothis in "A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost"]]></title><description><![CDATA[
<p>Yeah exactly - very interesting that Luna is calibrated so poorly despite working better on easier problems.</p>
]]></description><pubDate>Fri, 06 Nov 2026 21:04:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=50398512</link><dc:creator>couldaidothis</dc:creator><comments>https://news.ycombinator.com/item?id=50398512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50398512</guid></item><item><title><![CDATA[New comment by couldaidothis in "A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost"]]></title><description><![CDATA[
<p>I think OpenAI and Anthropic have both been doing similar "routing" approaches for a while. Wasn't OpenAI one of the first to have a small model start responding to you for the first several tokens so that you got an instant response while the big model became available?<p>Similarly, Grok has been routing to Opus internally for a little while now I think.</p>
]]></description><pubDate>Fri, 06 Nov 2026 21:03:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=50398496</link><dc:creator>couldaidothis</dc:creator><comments>https://news.ycombinator.com/item?id=50398496</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50398496</guid></item></channel></rss>