<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: eugmai86</title><link>https://news.ycombinator.com/user?id=eugmai86</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 19 Jun 2026 11:17:27 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=eugmai86" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[MCP Solves the Plug, Not the Trust Boundary]]></title><description><![CDATA[
<p>Article URL: <a href="https://vectoralix.com/blog/mcp-has-a-tool-selection-problem">https://vectoralix.com/blog/mcp-has-a-tool-selection-problem</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48500828">https://news.ycombinator.com/item?id=48500828</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 12 Jun 2026 07:11:23 +0000</pubDate><link>https://vectoralix.com/blog/mcp-has-a-tool-selection-problem</link><dc:creator>eugmai86</dc:creator><comments>https://news.ycombinator.com/item?id=48500828</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48500828</guid></item><item><title><![CDATA[New comment by eugmai86 in "Amazon EC2 M9g and M9gd instances powered by new AWS Graviton5 processors"]]></title><description><![CDATA[
<p>The most interesting part for me is not the top-end 192 core size, but the small/medium sizes.<p>Looks like m9g.large is about 9% more expensive than m8g.large on-demand, at least in Vantage’s current data.<p>If the “up to 25% compute improvement” holds for real web/database workloads, that is a pretty reasonable perf/$ trade. The usual caveat is that small SaaS apps are often bottlenecked on DB, storage, or network long before raw CPU.</p>
]]></description><pubDate>Wed, 10 Jun 2026 19:24:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=48481345</link><dc:creator>eugmai86</dc:creator><comments>https://news.ycombinator.com/item?id=48481345</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48481345</guid></item><item><title><![CDATA[New comment by eugmai86 in "Kahan Summation Algorithm"]]></title><description><![CDATA[
<p>Nice example of an algorithm that is simple enough to explain in a few lines, but still changes how you think about floating point errors.</p>
]]></description><pubDate>Tue, 09 Jun 2026 18:53:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=48465798</link><dc:creator>eugmai86</dc:creator><comments>https://news.ycombinator.com/item?id=48465798</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48465798</guid></item><item><title><![CDATA[New comment by eugmai86 in "Spherical Voronoi Diagram"]]></title><description><![CDATA[
<p>Nice visualization. Putting the cells directly on the sphere makes the nearest-neighbor idea much easier to understand.<p>On a flat map I always have to ask myself how much of what I’m seeing is geometry and how much is projection distortion</p>
]]></description><pubDate>Mon, 08 Jun 2026 19:01:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48449911</link><dc:creator>eugmai86</dc:creator><comments>https://news.ycombinator.com/item?id=48449911</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48449911</guid></item><item><title><![CDATA[New comment by eugmai86 in "Show HN: CoreMCP – MCP Server for On-Prem DBs"]]></title><description><![CDATA[
<p>Thanks!</p>
]]></description><pubDate>Wed, 27 May 2026 19:20:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48299159</link><dc:creator>eugmai86</dc:creator><comments>https://news.ycombinator.com/item?id=48299159</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48299159</guid></item></channel></rss>