<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Recommendation on Dylan Ler</title><link>http://dylanler.github.io/tags/recommendation/</link><description>Recent content in Recommendation on Dylan Ler</description><generator>Hugo -- 0.133.0</generator><language>en-us</language><lastBuildDate>Fri, 02 Oct 2026 20:40:00 -0700</lastBuildDate><atom:link href="http://dylanler.github.io/tags/recommendation/index.xml" rel="self" type="application/rss+xml"/><item><title>Hidden gems, wisdom of crowds, and agent swarms</title><link>http://dylanler.github.io/posts/hidden-gem-swarm/</link><pubDate>Fri, 02 Oct 2026 20:40:00 -0700</pubDate><guid>http://dylanler.github.io/posts/hidden-gem-swarm/</guid><description>People call a place a hidden gem when it is good and still obscure. A best-of list, a chain, or a crowd repeating the same tip is what ends the label. An ugly room, cash only, and a non-English menu are how people search. They are not proof.
This note turns that observation into a score, then checks the score on a synthetic swarm. It is a design, not a fit to restaurant ratings, and not a user study.</description></item></channel></rss>