<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: sanju3026</title><link>https://news.ycombinator.com/user?id=sanju3026</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 03 Jul 2026 07:04:52 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sanju3026" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by sanju3026 in "Show HN: Live face swap and outfit try-on in the browser"]]></title><description><![CDATA[
<p>Doing this entirely client side in the browser with low enough latency for live video is highly impressive. Are you running optimized WebGPU under the hood or is a lot of the heavy lifting being offloaded asynchronously to a server?</p>
]]></description><pubDate>Wed, 01 Jul 2026 19:56:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=48752269</link><dc:creator>sanju3026</dc:creator><comments>https://news.ycombinator.com/item?id=48752269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48752269</guid></item><item><title><![CDATA[New comment by sanju3026 in "Ask HN: Secure wrapper for coding agents?"]]></title><description><![CDATA[
<p>I believe you're looking for Era. It uses libkrun for local microVM isolation and was built specifically to solve the "LLM hallucinated a destructive bash command" problem without the overhead of a massive VM.<p>Another one that handles this gracefully is Yolobox, which uses rootless Podman. Both are actively maintained and cut through the noise of the thousands of generic wrapper repos out there right now.</p>
]]></description><pubDate>Tue, 30 Jun 2026 14:38:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48733327</link><dc:creator>sanju3026</dc:creator><comments>https://news.ycombinator.com/item?id=48733327</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48733327</guid></item></channel></rss>