定义生物人工智能模型的危险能力（英）

JASPREET PANNU, SARAH L. GEBAUER, HENRY ALEXANDER BRADLEY, DULANI WOODS, DONI BLOOMFIELD, ALLISON BERKE, GREG MCKELVEY, JR., ANITA CICERO, TOM INGLESBYDefining Hazardous Capabilities of Biological AI ModelsExpert Convening to Inform Future Risk AssessmentConference ProceedingsFor more information on this publication, visit www.rand.org/t/CFA3649-1.About RANDRAND is a research organization that develops solutions to public policy challenges to help make communities throughout the world safer and more secure, healthier and more prosperous. RAND is nonprofit, nonpartisan, and committed to the public interest. To learn more about RAND, visit www.rand.org.Research IntegrityOur mission to help improve policy and decisionmaking through research and analysis is enabled through our core values of quality and objectivity and our unwavering commitment to the highest level of integrity and ethical behavior. To help ensure our research and analysis are rigorous, objective, and nonpartisan, we subject our research publications to a robust and exacting quality-assurance process; avoid both the appearance and reality of financial and other conflicts of interest through staff training, project screening, and a policy of mandatory disclosure; and pursue transparency in our research engagements through our commitment to the open publication of our research findings and recommendations, disclosure of the source of funding of published research, and policies to ensure intellectual independence. For more information, visit www.rand.org/about/research-integrity.RAND’s publications do not necessarily reflect the opinions of its research clients and sponsors.Published by the RAND Corporation, Santa Monica, Calif.© 2025 RAND Corporation is a registered trademark.Limited Print and Electronic Distribution RightsThis publication and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to its webpage on rand.org is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research products for commercial purposes. For information on reprint and reuse permissions, visit www.rand.org/about/publishing/permissions.CF-A3649-1 iii About These Conference Proceedings Artificial intelligence (AI) models are used increasingly in biological research. Many AI models, such as general-purpose large language models, contain some degree of biological knowledge (including knowledge regarding pathogens). Developers are also creating AI models that are able to carry out an array of increasingly sophisticated tasks, either under human guidance or autonomously, including by vesting some models with biological capabilities (e.g., the ability to design novel proteins with specific functions). Identifying which biological AI capabilities pose significant potential risk to global public health