Tootfinder

I realize that one element of this is cop PR: “See! Those other guys are worse! We’re not so bad!!” This in no way lessens the wonder and the horror of the situation.

DOJ Staffer Who Threw Sandwich at D.C. Cop Fired, Charged With Felony Assault (Nikki McCann Ramirez/Rolling Stone)
https://www.rollingstone.com/politics/politics-news/doj-employee-threw-sandwich-dc-cop-charged-assault-1235407854/
http://www.memeorandum.com/250814/p88#a250814p88

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
Chen Xiong, Pin-Yu Chen, Tsung-Yi Ho
https://arxiv.org/abs/2506.00781 ht…

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance by tricking the target LLMs into answering harmful and risky responses, are becoming an urgent concern. The practice of red-teaming for LLMs is to proactively explore potential risks and error-prone instances before the release of frontier AI technology. This …