<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: kombinatori</title><link>https://news.ycombinator.com/user?id=kombinatori</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 12 Oct 2026 00:39:04 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=kombinatori" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by kombinatori in "Build your own decision model"]]></title><description><![CDATA[
<p>Indeed. Token masking just limits the costs associated with using an LLM. It therefore also limits the accuracy by limiting the amount of compute available.<p>But LLMs can mimick decision models, and I wouldn't be surprized if some labs are doing it this way at the moment.</p>
]]></description><pubDate>Sun, 11 Oct 2026 07:03:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=50040438</link><dc:creator>kombinatori</dc:creator><comments>https://news.ycombinator.com/item?id=50040438</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50040438</guid></item></channel></rss>