AI Dynamics

Global AI News Aggregator

LLMs as Character Simulators: Understanding Jailbreak Prompting Techniques

Character simulation starting with a classic that encapsulates the idea of LLMs as roleplay simulators some of the best original jailbreaks simply ask GPT to simulate a character that possessed undesirable traits this forms the basis for how to think about prompting LLMs

→ View original post on X — @alexalbert__,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *