<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: wontonaroo</title><link>https://news.ycombinator.com/user?id=wontonaroo</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 09 Apr 2026 15:22:02 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=wontonaroo" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by wontonaroo in "Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)"]]></title><description><![CDATA[
<p>Firstly congratulations on your effort.<p>How does the graph component of your database perform compared to Kuzu?   Do you have any benchmarks.<p>For RAG I've tried Qdrant, Meilisearch, and Kuzu.   At the moment I wouldn't consider HelixDB because of HelixQL.   Wondering why you didn't use OpenCypher?<p>At the moment you have this system which is aimed to support AI/LLM systems but by creating HelixQL you do not have an AI coding friendly query language.<p>With OpenCypher even older cheap models can generate queries.  Or maybe some GraphQL layer.</p>
]]></description><pubDate>Thu, 15 May 2025 22:00:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=43999780</link><dc:creator>wontonaroo</dc:creator><comments>https://news.ycombinator.com/item?id=43999780</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43999780</guid></item><item><title><![CDATA[New comment by wontonaroo in "AI assisted search-based research works now"]]></title><description><![CDATA[
<p>I used Google AI Studio instead of Google Gemini App because it provides references to the search results.<p>Google AI Studio gave me an exact answer of 2227 as a possible answer and linked to these comments because there is a comment further down which claims that is the exact answer.   The comment was 2 hours old when I did the prompt.<p>It also provided a code example of how to find it using the python nfl data library mentioned in one of the comments here.</p>
]]></description><pubDate>Tue, 22 Apr 2025 06:55:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=43759680</link><dc:creator>wontonaroo</dc:creator><comments>https://news.ycombinator.com/item?id=43759680</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43759680</guid></item></channel></rss>