<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: sdingi</title><link>https://news.ycombinator.com/user?id=sdingi</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 02 Sep 2026 10:05:43 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sdingi" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by sdingi in "Can I run AI locally?"]]></title><description><![CDATA[
<p>When running models on my phone - either through the web browser or via an app - is there any chance it uses the phone's NPU, or will these be GPU only?<p>I don't really understand how the interface to the NPU chip looks from the perspective of a non-system caller, if it exists at all. This is a Samsung device but I am wondering about the general principle.</p>
]]></description><pubDate>Fri, 13 Mar 2026 17:41:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47367357</link><dc:creator>sdingi</dc:creator><comments>https://news.ycombinator.com/item?id=47367357</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47367357</guid></item></channel></rss>