Contemporary AI foundation models increase biological weapons risk

TL;DR

This paper argues that contemporary AI foundation models significantly increase biological weapons risks by enabling nonexperts to perform complex tasks, challenging previous safety assessments and highlighting the need for better evaluation methods.

Contribution

It demonstrates that advanced AI models can guide nonexperts in biological tasks, undermining assumptions that such development requires tacit knowledge and exposing safety assessment flaws.

Findings

AI models can guide recovery of poliovirus from synthetic DNA

Current models can assist nonexperts in complex biological tasks

Safety assessments underestimate biosecurity risks of AI models

Abstract

The rapid advancement of artificial intelligence has raised concerns about its potential to facilitate biological weapons development. We argue existing safety assessments of contemporary foundation AI models underestimate this risk, largely due to flawed assumptions and inadequate evaluation methods. First, assessments mistakenly assume biological weapons development requires tacit knowledge, or skills gained through hands-on experience that cannot be easily verbalized. Second, they rely on imperfect benchmarks that overlook how AI can uplift both nonexperts and already-skilled individuals. To challenge the tacit knowledge assumption, we examine cases where individuals without formal expertise, including a 2011 Norwegian ultranationalist who synthesized explosives, successfully carried out complex technical tasks. We also review efforts to document pathogen construction processes, highlighting how such tasks can be conveyed in text. We identify "elements of success" for biological weapons development that large language models can describe in words, including steps such as acquiring materials and performing technical procedures. Applying this framework, we find that advanced AI models Llama 3.1 405B, ChatGPT-4o, and Claude 3.5 Sonnet can accurately guide users through the recovery of live poliovirus from commercially obtained synthetic DNA, challenging recent claims that current models pose minimal biosecurity risk. We advocate for improved benchmarks, while acknowledging the window for meaningful implementation may have already closed.