AI biosecurity risk is moving faster in silico than in the lab
The dangerous part of AI-enabled biology is not one model suddenly becoming a lab scientist. It is the chain: information retrieval, biological design, procurement, synthesis, testing, and scale-up, where different systems can each remove friction. This review finds that frontier models already beat expert baselines on in-silico and screening-evasion benchmarks, while wet-lab execution still depends heavily on tacit knowledge. Its answer is defense in depth, with governance tied to capability thresholds across the full digital-to-physical workflow.