Table of Contents: :: Library Catalog

Saved in:

Bibliographic Details
Main Authors:	Phuong, Mary, Aitchison, Matthew, Catt, Elliot, Cogan, Sarah, Kaskasoli, Alexandre, Krakovna, Victoria, Lindner, David, Rahtz, Matthew, Assael, Yannis, Hodkinson, Sarah, Howard, Heidi, Lieberum, Tom, Kumar, Ramana, Raad, Maria Abi, Webson, Albert, Ho, Lewis, Lin, Sharon, Farquhar, Sebastian, Hutter, Marcus, Deletang, Gregoire, Ruoss, Anian, El-Sayed, Seliem, Brown, Sasha, Dragan, Anca, Shah, Rohin, Dafoe, Allan, Shevlane, Toby
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2403.13793
Tags:	Add Tag No Tags, Be the first to tag this record!

Table of Contents:

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations cover four areas: (1) persuasion and deception; (2) cyber-security; (3) self-proliferation; and (4) self-reasoning. We do not find evidence of strong dangerous capabilities in the models we evaluated, but we flag early warning signs. Our goal is to help advance a rigorous science of dangerous capability evaluation, in preparation for future models.

Similar Items