<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: henry_kang</title><link>https://news.ycombinator.com/user?id=henry_kang</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 13 May 2026 14:48:52 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=henry_kang" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by henry_kang in "Local AI needs to be the norm"]]></title><description><![CDATA[
<p>This feels increasingly true.<p>A lot of useful AI work is shifting from “knowing more” to “working with more context”, files, recordings, repos, screenshots, browsing history, etc.<p>Once that happens, memory and orchestration start mattering much more than raw model size.</p>
]]></description><pubDate>Wed, 13 May 2026 11:08:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48120403</link><dc:creator>henry_kang</dc:creator><comments>https://news.ycombinator.com/item?id=48120403</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48120403</guid></item><item><title><![CDATA[New comment by henry_kang in "Local AI needs to be the norm"]]></title><description><![CDATA[
<p>Yeah, we've recently made it public. You can check it out here: <a href="https://clipto.com" rel="nofollow">https://clipto.com</a><p>Be aware that it is still a beast that sucks in a lot of memory.<p>Oh, one more thing ;) remember to keep your Mac plugged in...</p>
]]></description><pubDate>Tue, 12 May 2026 06:00:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=48104739</link><dc:creator>henry_kang</dc:creator><comments>https://news.ycombinator.com/item?id=48104739</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48104739</guid></item><item><title><![CDATA[New comment by henry_kang in "Local AI needs to be the norm"]]></title><description><![CDATA[
<p>hhh, "one more thing"</p>
]]></description><pubDate>Tue, 12 May 2026 05:57:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48104721</link><dc:creator>henry_kang</dc:creator><comments>https://news.ycombinator.com/item?id=48104721</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48104721</guid></item><item><title><![CDATA[New comment by henry_kang in "Local AI needs to be the norm"]]></title><description><![CDATA[
<p>Actually you can do way more things than that. We have optimized it to process 2TB of high def videos on a M5 MBP in under 24 hours, including everything such as speech understanding, face recog, LLM and VLM. Super fun.</p>
]]></description><pubDate>Mon, 11 May 2026 13:54:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48095054</link><dc:creator>henry_kang</dc:creator><comments>https://news.ycombinator.com/item?id=48095054</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48095054</guid></item></channel></rss>