Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Clymer, Joshua, Juang, Caden, Field, Severin
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.05466