<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Work on Dave Peters</title><link>https://davejpeters.net/work/</link><description>Recent content in Work on Dave Peters</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 25 May 2026 13:45:25 -0400</lastBuildDate><atom:link href="https://davejpeters.net/work/index.xml" rel="self" type="application/rss+xml"/><item><title>Opencode Mentor</title><link>https://davejpeters.net/work/opencode-mentor/</link><pubDate>Mon, 25 May 2026 13:45:25 -0400</pubDate><guid>https://davejpeters.net/work/opencode-mentor/</guid><description>&lt;h2 id="the-problem"&gt;The problem&lt;a class="anchor" href="#the-problem"&gt;#&lt;/a&gt;&lt;/h2&gt;&#10;&lt;p&gt;Most coding assistants optimize for producing code quickly. That can be useful, but it creates a tension for someone who is still developing programming judgment: the task can be finished before the learner has understood the problem.&lt;/p&gt;&#10;&lt;p&gt;Opencode Mentor explores a different goal. I want an assistant that helps me explain a boundary, recognize a tradeoff, debug an assumption, and gradually need less help. The configuration calls that approach &lt;strong&gt;MAI — Mentor AI Infrastructure&lt;/strong&gt;.&lt;/p&gt;</description></item></channel></rss>