<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Software Engineering on MacWorks</title><link>https://macworks.dev/tags/Software-engineering/</link><description>Recent content in Software Engineering on MacWorks</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 28 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://macworks.dev/tags/Software-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Teaching programming when AI can finish the exercises</title><link>https://macworks.dev/notes/jane-street-ai-intern-training/</link><pubDate>Mon, 28 Sep 2026 00:00:00 +0000</pubDate><guid>https://macworks.dev/notes/jane-street-ai-intern-training/</guid><description>AI can solve beginner exercises, so Jane Street is shifting intern training toward design, testing, and code review. Exactly right.</description></item><item><title>Lauren Tan’s pstack: verify first, then parallelize</title><link>https://macworks.dev/notes/lauren-tan-pstack/</link><pubDate>Mon, 28 Sep 2026 00:00:00 +0000</pubDate><guid>https://macworks.dev/notes/lauren-tan-pstack/</guid><description>Verification comes first; Cloud Agents offer a way to parallelize beyond local git worktrees. These capabilities should be built into agent harnesses.</description></item><item><title>Coding agents make software engineering harder?</title><link>https://macworks.dev/notes/coding-agents-make-engineering-harder/</link><pubDate>Sat, 26 Sep 2026 00:00:00 +0000</pubDate><guid>https://macworks.dev/notes/coding-agents-make-engineering-harder/</guid><description>Doing anything well is hard. What counts as good is relative, and everyone has access to the same tools.</description></item></channel></rss>