RSSAmplifier

andpalmier's blog · Nov 17, 2024

The subtle art of jailbreaking LLMs

0
Sign in to vote or save

This page cannot be shown here. You can still read it on the original site — the toolbar below keeps your place in the directory.

Introduction # Lately, my feed has been filled with posts and articles about jailbreaking Large Language Models. I was completely captured by the idea that these models can be tricked into doing almost anything but only as long as you ask the right way, as if it were a strange manipulation exercise with a chatbot: “In psychology, manipulation is defined as an action designed to influence or…

Read on /posts/jailbreaking-llms/

Comments

Nothing yet. Say the first thing.

    Sign in to join the conversation.