<?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>Evolution on Dylan Ler</title><link>http://dylanler.github.io/tags/evolution/</link><description>Recent content in Evolution on Dylan Ler</description><generator>Hugo -- 0.133.0</generator><language>en-us</language><lastBuildDate>Fri, 02 Oct 2026 20:55:00 -0700</lastBuildDate><atom:link href="http://dylanler.github.io/tags/evolution/index.xml" rel="self" type="application/rss+xml"/><item><title>Does the harness evolve first, or the model?</title><link>http://dylanler.github.io/posts/harness-vs-brain/</link><pubDate>Fri, 02 Oct 2026 20:55:00 -0700</pubDate><guid>http://dylanler.github.io/posts/harness-vs-brain/</guid><description>In this toy, the harness evolves first while the brain is primitive. Past a capacity threshold the brain takes over. A greedy brain that edits the tool it thinks is worst can lock in a worse limb than blind selection keeps.
This is a synthetic evolutionary simulation, not a user study and not a test of a real language model. The controller is a small lookup table. Code, protocol, and the raw series: dylanler/harness-vs-brain.</description></item></channel></rss>