<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: liquid_richie</title><link>https://news.ycombinator.com/user?id=liquid_richie</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 28 Oct 2026 11:15:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=liquid_richie" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by liquid_richie in "Introducing LFM3: Every Modality for Specialized Intelligence"]]></title><description><![CDATA[
<p>(I work at Liquid.) Probably, yes. Per the blog, the last 3.5T tokens of pre-training were a mid-training stage with a larger share of agentic traces and tool calls, and SFT covered tool calling and agentic traces too, because the text model is post-trained to live inside agent harnesses. With an empty system prompt it seems to assume it's in one. I'd try a short system prompt that says no tools are available, and if it still does it, a note on the Hugging Face model page would help the team.</p>
]]></description><pubDate>Tue, 27 Oct 2026 19:22:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50264392</link><dc:creator>liquid_richie</dc:creator><comments>https://news.ycombinator.com/item?id=50264392</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50264392</guid></item></channel></rss>