This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Jailbreaking (AIs)
•
Applied to
A Poem Is All You Need: Jailbreaking ChatGPT, Meta & More
by
Sharat Jacob Jacob
4d
ago
•
Applied to
Jailbreaking ChatGPT and Claude using Web API Context Injection
by
Jaehyuk Lim
12d
ago
•
Applied to
Interpreting the effects of Jailbreak Prompts in LLMs
by
Raemon
1mo
ago
•
Created by
Raemon
at
1mo