The Reality of AI and Biorisk

TL;DR

This paper analyzes current research on AI-related biorisks, focusing on large language models and biological tools, highlighting gaps in methodology and the need for more rigorous empirical testing to assess potential threats.

Contribution

It provides a critical review of existing threat models related to AI and biorisk, emphasizing the nascent state of research and proposing directions for more rigorous empirical investigation.

Findings

Current AI models do not pose immediate biorisks.

Research in AI and biorisk is still in early, speculative stages.

More rigorous empirical methods are needed for threat assessment.

Abstract

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.