<?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>Machine-Learning on Hanh Pham's Blog</title><link>https://hanh.me/tags/machine-learning/</link><description>Recent content in Machine-Learning on Hanh Pham's Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 23 Oct 2026 10:15:41 +0700</lastBuildDate><atom:link href="https://hanh.me/tags/machine-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>An Uncensored Model Is Not a Free Model</title><link>https://hanh.me/posts/uncensored-models-are-a-policy-surface/</link><pubDate>Tue, 06 Oct 2026 15:00:00 +0700</pubDate><guid>https://hanh.me/posts/uncensored-models-are-a-policy-surface/</guid><description>Removing refusal behavior from an open model is technically easy. The hard part is proving what changed, containing the new failure modes, and keeping an agent with tools inside a safe boundary.</description></item></channel></rss>