<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>C. Denison | TSG Lab – Technical Safety &amp; Governance Lab</title><link>https://tsglab.github.io/author/c.-denison/</link><atom:link href="https://tsglab.github.io/author/c.-denison/index.xml" rel="self" type="application/rss+xml"/><description>C. Denison</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 01 Jun 2024 00:00:00 +0000</lastBuildDate><image><url>https://tsglab.github.io/media/logo.svg</url><title>C. Denison</title><link>https://tsglab.github.io/author/c.-denison/</link></image><item><title>Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models</title><link>https://tsglab.github.io/publication/sycophancy-to-subterfuge/</link><pubDate>Sat, 01 Jun 2024 00:00:00 +0000</pubDate><guid>https://tsglab.github.io/publication/sycophancy-to-subterfuge/</guid><description/></item><item><title>Sleeper Agents: Training Deceptive LLMs That Persist Through Safety Training</title><link>https://tsglab.github.io/publication/sleeper-agents/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://tsglab.github.io/publication/sleeper-agents/</guid><description/></item></channel></rss>