评估AI提升生化风险的潜在威胁，提出需更严谨的研究方法。
The Reality of AI and Biorisk
- 分析两类AI生化风险：大模型获取信息与生物工具合成新生物体
- 现有研究多为推测性，缺乏方法学成熟度和透明度
- 当前技术尚不构成即时风险，需加强实证研究以确保可靠性
为准确且有信心地回答‘AI模型或系统是否会增加生化风险’这一问题，必须具备健全的理论威胁模型以及可靠的验证方法。本文分析了现有关于两大AI与生化风险威胁模型的研究：1）大语言模型（LLMs）带来的信息获取与规划能力；2）人工智能赋能的生物工具（BTs）在合成新型生物产物中的应用。研究发现，现有相关研究尚处于初级阶段，大多具有推测性质，方法学成熟度与透明度不足。现有文献表明，当前的LLMs与BTs并未构成直接风险，但亟需进一步工作来发展严谨的方法，以理解未来模型可能带来的生化风险。论文最后提出建议，推动实证研究扩展，以更精准地聚焦生化风险，并确保研究结果的严谨性与有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。