AI Is Learning to Write Genetic Code
AI models have demonstrated the ability to generate complete viable bacteriophage genomes, a dual-use breakthrough that intensifies the intersection of AI safety and biosecurity risk.
Summary written by editorial AI · Source link below
This sort of research is both exciting and terrifying: The two models in question were told to generate complete genomes for a viable bacteriophage—a type of virus able to infect and replicate itself inside bacteria, destroying them from the inside. Using an existing bacteriophage as an example—ΦX174 (pronounced “fie-ex-1-7-4”), known for its ability to infect and destroy E. coli bacteria—the models generated about 700,000 potential designs, of which the researchers picked 285 that looked most p
Editorial Analysis
AI-generated viable genetic code blurs the line between digital and biological threats, expanding the dual-use risk surface that enterprise security and governance teams must eventually address.
Include AI-enabled biosecurity scenarios in strategic threat horizon scanning, particularly for organisations in life sciences or critical infrastructure.
AI can now generate viable virus genomes from scratch—a dual-use development that expands the threat landscape beyond traditional cyber risk.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at Schneier on Security in a new tab.
More from the AI Security Desk
- OWASP Flags Top AI Skill Risks in New Security Blueprint21 Aug
- OpenAI Adds Controls That Should've Been There Already21 Aug
- More Incidents of AIs Going Rogue in Cybersecurity Challenges21 Aug
- COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense21 Aug
- EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models21 Aug