Login
From:
chats-lab.github.io
(Uncensored)
subscribe
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
https://chats-lab.github.io/persuasive_jailbreaker/
links
backlinks
Roast topics
Find topics
Find it!
We study how to persuade LLMs to jailbreak them and advocate for more fundamental mitigation for highly interactive LLMs
