AI Safety Newsletter #52: An Expert Virology Benchmark
Summary
Researchers created the Virology Capabilities Test (VCT), a benchmark measuring how well AI systems can solve complex virology lab problems, and found that leading AI models like OpenAI's o3 now outperform human experts in specialized virology knowledge. This is concerning because virology knowledge has dual-use potential, meaning the same capabilities that could help prevent disease could also be misused by bad actors to develop dangerous pathogens.
Solution / Mitigation
The authors recommend that highly dual-use virology capabilities should be excluded from publicly-available AI systems, and know-your-customer mechanisms (verification processes to confirm who customers are and what they'll use the technology for) could ensure these capabilities remain accessible only to researchers in institutions with appropriate safety protocols. As a result of the paper, xAI has added new safeguards to their systems.
Classification
Affected Vendors
Related Issues
Original source: https://newsletter.safe.ai/p/ai-safety-newsletter-52-an-expert
First tracked: February 15, 2026 at 08:49 PM
Classified by LLM (prompt v3) · confidence: 92%