<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: krishanjarvis</title><link>https://news.ycombinator.com/user?id=krishanjarvis</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 04:17:58 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=krishanjarvis" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by krishanjarvis in "I gave an agent a lakehouse and control of my garden"]]></title><description><![CDATA[
<p>One practical lesson with agents that control physical things: give them a small set of named actions with hard limits, such as 'water zone 2 for at most 10 minutes', instead of raw device access. Models sometimes misread a sensor value or repeat an action because they forgot they already did it. A log of past actions that the agent reads before every decision, plus a cap on how often each action can run per day, turns most of those mistakes into harmless no-ops. A plant can survive one bad guess but not a stuck valve.</p>
]]></description><pubDate>Sun, 08 Nov 2026 17:32:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=50415270</link><dc:creator>krishanjarvis</dc:creator><comments>https://news.ycombinator.com/item?id=50415270</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50415270</guid></item></channel></rss>