Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bova, Paolo, Di Stefano, Alessandro, Han, The Anh
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence Computers and Society Multiagent Systems General Economics Economics Applications
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.15433