Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models
In this working paper, the authors evaluate whether artificial intelligence systems with broad scientific knowledge could enable the development of biological and chemical weapons, including through modified systems lacking safety measures.
Sunishchal Dev, Charles Teague, Kyle Brady, Ying-Chiang Jeffrey Lee, Sarah L. Gebauer, Henry Alexander Bradley, Grant Ellison, Bria Persaud, Jordan Despanie, Barbara Del Castello, Alyssa Worland, Michael Miller, Dawid Maciorowski, Adrian Salas, Dave Nguyen, James Liu, Jason Johnson, Andrew Sloan, Will Stonehouse, Travis Merrill, Thomas Goode, Greg McKelvey, Jr., Ella Guest