<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Abliteration on skulldc</title><link>https://skulldc.net/tags/abliteration/</link><description>Recent content in Abliteration on skulldc</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 03 Nov 2026 20:25:49 +0000</lastBuildDate><atom:link href="https://skulldc.net/tags/abliteration/index.xml" rel="self" type="application/rss+xml"/><item><title>Heretic changes language model behavior without training, refusal removal by default</title><link>https://skulldc.net/2026/11/heretic-changes-language-model-behavior-without-training-refusal-remov/</link><pubDate>Tue, 03 Nov 2026 20:25:49 +0000</pubDate><guid>https://skulldc.net/2026/11/heretic-changes-language-model-behavior-without-training-refusal-remov/</guid><description>An AGPL-3.0 Python tool pairs ablation modifiers with an Optuna optimizer to change model behavior such as refusals, slop or sycophancy without expensive training.</description></item></channel></rss>