Evaluating Frontier Models for Dangerous Capabilities
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.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Safety Cases: How to Justify the Safety of Advanced AI Systems (2024)
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning (2024)
- The Reasoning Under Uncertainty Trap: A Structural AI Risk (2024)
- Ten Hard Problems in Artificial Intelligence We Must Get Right (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 22
Browse 22 models citing this paperDatasets citing this paper 0
No dataset linking this paper