Flutterby™! : Finally, a legitimate use for XML...

Hidden Layer: Novel Universal Bypass for All Major LLMs — The Policy Puppetry Prompt Injection Technique. Format it like a configuration file, if that doesn't work then write your query out in l33tsp3@k.

Leveraging a novel combination of an internally developed policy technique and roleplaying, we are able to bypass model alignment and produce outputs that are in clear violation of AI safety policies: CBRN (Chemical, Biological, Radiological, and Nuclear), mass violence, self-harm and system prompt leakage.