<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>NP-Curious on Ash&#39;s Blog</title>
    <link>https://ashvardanian.com/tags/np-curious/</link>
    <description>Recent content in NP-Curious on Ash&#39;s Blog</description>
    <image>
      <title>Ash&#39;s Blog</title>
      <url>https://ashvardanian.com/ashvardanian.com.jpg</url>
      <link>https://ashvardanian.com/ashvardanian.com.jpg</link>
    </image>
    <generator>Hugo -- 0.139.2</generator>
    <language>en</language>
    <lastBuildDate>Tue, 28 Oct 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://ashvardanian.com/tags/np-curious/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Scaling Elections with GPUs and Mojo across Nvidia and AMD 🔥</title>
      <link>https://ashvardanian.com/posts/scaling-elections/</link>
      <pubDate>Tue, 28 Oct 2025 00:00:00 +0000</pubDate>
      <guid>https://ashvardanian.com/posts/scaling-elections/</guid>
      <description>Taking the computationally expensive Schulze voting method from theory to practice on GPUs — exploring parallel algorithms, hardware optimizations, and why Mojo surprised me.</description>
    </item>
    <item>
      <title>Before AI&#39;s Kepler Moment - Are LLMs the Epicycles of Intelligence?</title>
      <link>https://ashvardanian.com/posts/llm-epicycles/</link>
      <pubDate>Thu, 02 Oct 2025 00:00:00 +0000</pubDate>
      <guid>https://ashvardanian.com/posts/llm-epicycles/</guid>
      <description>Like Ptolemaic astronomers stacking circles to predict planetary motion, we stack transformer layers to approximate intelligence—accurate yet awaiting our Kepler moment.</description>
    </item>
    <item>
      <title>USearch Molecules: 28 Billion Chemical Embeddings on AWS ⚗️</title>
      <link>https://ashvardanian.com/posts/usearch-molecules/</link>
      <pubDate>Mon, 20 Nov 2023 00:00:00 +0000</pubDate>
      <guid>https://ashvardanian.com/posts/usearch-molecules/</guid>
      <description>Indexing 28 billion chemical embeddings from 7 billion molecules using optimized Jaccard distance kernels, achieving 99% recall at 3,700 QPS on AWS Open Data.</description>
    </item>
    <item>
      <title>Combinatorial Stable Marriages for DBMS Semantic Joins 💍</title>
      <link>https://ashvardanian.com/posts/searching-stable-marriages/</link>
      <pubDate>Tue, 18 Jul 2023 00:00:00 +0000</pubDate>
      <guid>https://ashvardanian.com/posts/searching-stable-marriages/</guid>
      <description>Replacing billion-entry preference lists with vector search indexes makes the Nobel Prize-winning Stable Marriage algorithm scale to real-world dating and database joins.</description>
    </item>
  </channel>
</rss>
