The Reality of AI and Biorisk
It addresses biorisk concerns for policymakers and researchers, but is incremental as it reviews and critiques existing literature without new findings.
This paper analyzes existing research on AI and biorisk threat models, such as large language models and AI-enabled biological tools, finding that current studies are nascent and speculative, with no immediate risk identified, and recommends more rigorous empirical work.
To accurately and confidently answer the question 'could an AI model or system increase biorisk', it is necessary to have both a sound theoretical threat model for how AI models or systems could increase biorisk and a robust method for testing that threat model. This paper provides an analysis of existing available research surrounding two AI and biorisk threat models: 1) access to information and planning via large language models (LLMs), and 2) the use of AI-enabled biological tools (BTs) in synthesizing novel biological artifacts. We find that existing studies around AI-related biorisk are nascent, often speculative in nature, or limited in terms of their methodological maturity and transparency. The available literature suggests that current LLMs and BTs do not pose an immediate risk, and more work is needed to develop rigorous approaches to understanding how future models could increase biorisks. We end with recommendations about how empirical work can be expanded to more precisely target biorisk and ensure rigor and validity of findings.