<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: andywidjaja</title><link>https://news.ycombinator.com/user?id=andywidjaja</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 04 Jun 2026 23:57:58 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=andywidjaja" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by andywidjaja in "Show HN: Patina, an AI that learns your judgment, not just your tasks"]]></title><description><![CDATA[
<p>I was drowning in 100+ messages per-day at work and existing AI tools just wouldn't cut it because of default sorts (e.g. recency, etc.), not by what actually matters to me.<p>I tried modeling it to think like me when responding to messages: belief graph with decay, trust scoring from behavior, and graduated autonomy to prevent AI from mis-categorizing my messages.  Went down the path of open source so everyone can try it with a provided demo data in the repo.  I'm just looking for feedback on the architecture, especially the belief decay and graduated autonomy concepts.<p>Thanks</p>
]]></description><pubDate>Thu, 04 Jun 2026 22:49:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48405735</link><dc:creator>andywidjaja</dc:creator><comments>https://news.ycombinator.com/item?id=48405735</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48405735</guid></item><item><title><![CDATA[Show HN: Patina, an AI that learns your judgment, not just your tasks]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/Sanctum-Origo-Systems/patina">https://github.com/Sanctum-Origo-Systems/patina</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48405624">https://news.ycombinator.com/item?id=48405624</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 04 Jun 2026 22:39:28 +0000</pubDate><link>https://github.com/Sanctum-Origo-Systems/patina</link><dc:creator>andywidjaja</dc:creator><comments>https://news.ycombinator.com/item?id=48405624</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48405624</guid></item><item><title><![CDATA[New comment by andywidjaja in "Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)"]]></title><description><![CDATA[
<p>Nice approach, the Rust performance and single-binary deployment are compelling. Question, how do you handle contradictory facts? If John moves from Stripe to Google, does the graph resolve that, or does it store both?</p>
]]></description><pubDate>Thu, 04 Jun 2026 13:26:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=48398326</link><dc:creator>andywidjaja</dc:creator><comments>https://news.ycombinator.com/item?id=48398326</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48398326</guid></item></channel></rss>