<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: lukethorham</title><link>https://news.ycombinator.com/user?id=lukethorham</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 07 Nov 2026 16:29:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=lukethorham" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by lukethorham in "A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost"]]></title><description><![CDATA[
<p>There’s a METR audit document which apparently describes various unreleased models. This is discussed in a YT video by Wes Roth. I have no firsthand knowledge about it.</p>
]]></description><pubDate>Sat, 07 Nov 2026 01:17:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=50400667</link><dc:creator>lukethorham</dc:creator><comments>https://news.ycombinator.com/item?id=50400667</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50400667</guid></item><item><title><![CDATA[New comment by lukethorham in "A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost"]]></title><description><![CDATA[
<p>I wonder if something like this is the undisclosed new approach from Anthropic that presumably has massive improvements by combining multiple models.   Leveraging decision models as much as possible seems logical for extra speed and token efficiency.</p>
]]></description><pubDate>Fri, 06 Nov 2026 20:43:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=50398239</link><dc:creator>lukethorham</dc:creator><comments>https://news.ycombinator.com/item?id=50398239</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50398239</guid></item></channel></rss>