兰德：人工智能对国家安全和公共安全的评估报告（英文版）（12页）.pdf

1、ANTON SHENKEvaluating Artificial Intelligence for National Security and Public SafetyInsights from Frontier Model Evaluation Science DayConference Proceedings2ables,thresholds for dangerous AI capabilities,and voluntary risk management policies for scaling AI capabilities.The workshop proceedings sy

2、nthesize insights from these sessions,outline the complexities of eval-uating AI for dangerous capabilities,and highlight the collaborative effort required to formulate effec-tive policy.Track 1:Chemistry and Biology The chemistry and biology(chem-bio)track illu-minated the intersection of AI with c

3、hem-bio risks,incorporating insights from evaluations of general-purpose and domain-specific models.This section details lessons learned from completed model evalu-ations,needs and priorities for subsequent rounds of evaluations,and considerations for wet lab validation of model outputs.Lessons Lear

4、ned from Completed Model EvaluationsEmbracing Complexity in Chem-Bio Model Assessments This session highlighted the persistence of threat actors and the complex evolution of chem-bio threats.During the discussion,one participant observed a potential limitation of existing evaluation meth-ods,suggest

5、ing that marking an entire task as failed because of early setbacks might not fully capture the resilience and adaptability of threat actors.This cri-tique posits that a more nuanced approach accounting for threat progression and troubleshootingsuch as knowing the proportion of sub-steps that succee

6、dcould provide a more comprehensive and continu-ous understanding of the threat landscape.Tabletop exercises were proposed to explore the dynamics of troubleshooting and iteration further;however,their effectiveness in this context remains to be tested.Navigating the Complexities of Dual-Use Dangers