Evaluating Frontier Models for Dangerous Capabilities
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.
Code (1)
Similar Papers 제목 키워드 기반
PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for w…
Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations
We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approa…
Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs
Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that even robustly safeguarded models can be use…
Frontier AI Regulation: Managing Emerging Risks to Public Safety
Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable founda…
Sandbagging in a Simple Survival Bandit Problem
Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify risks before deployment. However, it has been recognised that if AI agent…