<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Debugging on philliant</title><link>https://philliant.com/tags/debugging/</link><description>Recent content in Debugging on philliant</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 philip mathew hern</copyright><lastBuildDate>Thu, 26 Mar 2026 06:31:57 -0700</lastBuildDate><atom:link href="https://philliant.com/tags/debugging/index.xml" rel="self" type="application/rss+xml"/><item><title>the danger of trusting the ai agent</title><link>https://philliant.com/posts/20260326-the-danger-of-trusting-the-ai-agent/</link><pubDate>Thu, 26 Mar 2026 06:31:57 -0700</pubDate><guid>https://philliant.com/posts/20260326-the-danger-of-trusting-the-ai-agent/</guid><description>i share a real failure mode where an ai agent created and then deleted files while debugging, leaving a clean git tree but low confidence. the lesson for me is simple: ai should accelerate the work i own and understand, while domain-specific decisions stay with the people accountable for that domain.</description></item></channel></rss>