<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: 45dsilicon</title><link>https://news.ycombinator.com/user?id=45dsilicon</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 28 Aug 2026 10:04:34 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=45dsilicon" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by 45dsilicon in "Show HN: Rebrain.gg – Doom learn, don't doom scroll"]]></title><description><![CDATA[
<p>the gap we kept hitting when building 45d was exactly this - there's a real difference between "AI that retrieves content" and "AI that understands how this specific person learns." the former is a better search engine. the latter is something new.<p>our learner model tracks 500+ signals per person - not just difficulty preferences but how they engage with confusion, where they disengage, what formats actually create retention for them specifically. the course structure changes as a result, not just the difficulty level.<p>curious what you found on the memory/context side. longitudinal context across sessions is where most AI tutors fall apart.</p>
]]></description><pubDate>Sat, 21 Feb 2026 16:59:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=47102471</link><dc:creator>45dsilicon</dc:creator><comments>https://news.ycombinator.com/item?id=47102471</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47102471</guid></item></channel></rss>