Stanford Scientists Use AI to Generate Novel Viruses, Raising Biosecurity Concerns
ChuckDBrooks · x · 2026-08-08
Scientific American reports that scientists at Stanford University and the Arc Institute have used AI to successfully generate novel viruses not found in nature.
- Research Details: Using the genome of a bacteriophage (a virus that kills bacteria) called ΦX174 as a template, the team used two large language models trained on over 2 million bacteriophage genomes to generate entirely new virus genomes in a single pass.
- Efficacy: Lab tests showed that these AI-generated viruses can effectively kill antibiotic-resistant bacteria, demonstrating significant potential against "superbugs".
- Biosecurity Risks: While the technology could lead to new antimicrobial drugs, scientists warn it poses immense dangers to human health if misused. The findings were published in the journal Science.
More from Safety
- SecOPD Mitigates Adaptive Prompt Injection via On-Policy Distillation — Yibo Peng · 2026-08-27
- Inside the Anthropic Author Settlement: A Novelist's Perspective — rvp · 2026-08-27
- Long Read: AI Is Buying the Data of Dead Companies — rvp · 2026-08-27
- Robin Hanson: AI Claims of Danger vs Actual Harms — amcafee · 2026-08-27
- Age verification laws are building the internet's next identity layer for AI agents — provenauthority · 2026-08-26
- Idea: Blockchain-based prompt credentialing for AI models — Dsphar · 2026-08-26