<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: marlott</title><link>https://news.ycombinator.com/user?id=marlott</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 12 Sep 2026 07:54:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=marlott" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by marlott in "The Bitter Lesson Is Misunderstood"]]></title><description><![CDATA[
<p>Thanks a lot for the detailed reply! Makes a lot of sense now. I'm working on similar problems, and have dabbled with this kind of approach.</p>
]]></description><pubDate>Thu, 04 Sep 2025 01:13:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=45122318</link><dc:creator>marlott</dc:creator><comments>https://news.ycombinator.com/item?id=45122318</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45122318</guid></item><item><title><![CDATA[New comment by marlott in "The Bitter Lesson Is Misunderstood"]]></title><description><![CDATA[
<p>Interesting! Could you give an example with a bit more specific detail here? I take it there's some kind of work output, like a report, in a semi-structured format, and the goal is to automate creation of these. And you would provide a UX that lets them explain what they want the system to create?</p>
]]></description><pubDate>Wed, 03 Sep 2025 23:39:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=45121592</link><dc:creator>marlott</dc:creator><comments>https://news.ycombinator.com/item?id=45121592</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45121592</guid></item><item><title><![CDATA[New comment by marlott in "AI agents: Less capability, more reliability, please"]]></title><description><![CDATA[
<p>which Google UI?</p>
]]></description><pubDate>Mon, 31 Mar 2025 19:47:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=43539049</link><dc:creator>marlott</dc:creator><comments>https://news.ycombinator.com/item?id=43539049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43539049</guid></item><item><title><![CDATA[New comment by marlott in "Claude 3.7 Sonnet and Claude Code"]]></title><description><![CDATA[
<p>Interesting - can you elaborate a little on what you mean by agentic search here?</p>
]]></description><pubDate>Mon, 24 Feb 2025 20:23:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=43164503</link><dc:creator>marlott</dc:creator><comments>https://news.ycombinator.com/item?id=43164503</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43164503</guid></item><item><title><![CDATA[New comment by marlott in "Probably pay attention to tokenizers"]]></title><description><![CDATA[
<p>Interesting! So you basically got a LM to rephrase the search phrase/keys into the style of the target documents, then used that in the RAG pipeline? Did you do an initial search first to limit the documents?</p>
]]></description><pubDate>Wed, 23 Oct 2024 20:46:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=41929136</link><dc:creator>marlott</dc:creator><comments>https://news.ycombinator.com/item?id=41929136</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41929136</guid></item></channel></rss>