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.

通过对 Gemini 1.0 模型进行新的 “危险能力” 评估，我们在先前研究的基础上，为了了解新 AI 系统所带来的风险，必须了解它的能力和无能力。我们的评估涵盖四个方面：（1）说服和欺骗；（2）网络安全；（3）自我扩散；以及（4）自我推理。在我们评估的模型中，我们没有发现强大的危险能力的证据，但我们标记了早期的预警信号。我们的目标是推动危险能力评估的严谨科学，为未来模型做好准备。