GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ramesh, Govind, Dou, Yao, Xu, Wei
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.13077