arXiv:2403.13793cs.LG
Evaluating Frontier Models for Dangerous Capabilities
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
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.
To quote Ludovic Peran, our amazing safety lead: Literature has identified self-proliferation as dangerous capability of models, and details about how to define it and example of form it can take have been openly discussed by GDM (https://arxiv.org/pdf/2403.13793). Current Gemma…
alekandreevView on HNParent context