Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mallen, Alex, Griffin, Charlie, Wagner, Misha, Abate, Alessandro, Shlegeris, Buck
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.12480