Uploaded September 2026 | Updated September 2026, 2 weeks ago
Scientists recently used AI to design entirely new working viruses from scratch. While these bacteriophages were created to target E. coli, could unregulated AI models lower the barrier to entry for biological weapons?
In this episode of Health Wanted, Laurel Bristow breaks down the science of generative virus design (like Evo), the historical reality of bioterrorism, and where current safety guardrails are falling short. Are AI models actually capable of creating the next superbug, or is the threat still theoretical?
RESOURCES & CONTINUED READING
→ Generative design of bacteriophages with genome language models:science.org/doi/10.1126/science.aec2657
→U.S. Government Policy for Stopping High-Risk Life Sciences Research: nih.gov/about-nih/nih-director/statements/announcement-release-us-government-policy-stopping-high-risk-life-sciences-research
→AI Bots Told Scientists How To Make Biological Weapons: nytimes.com/2026/04/29/us/ai-chatbots-biological-weapons.html?smid=url-share
→Strengthening nucleic acid biosecurity screening against generative protein design tools:science.org/stoken/author-tokens/ST-2942/full
→ The Age of AI in the Life Sciences: nap.nationalacademies.org/resource/28868/NASEM_BLS_Highlights_The_Age_of_AI_in_the_Life_Sciences.pdf
Backed by science and informed by news and journalism, Health Wanted is brought to you by WABE in Atlanta, Georgia and Emory’s Rollins School of Public Health. New episodes every Friday!
Learn more about this episode here: https://sph.emory.edu/news/health-wanted-bioterrorism
Ask Laurel anything (public health related only): https://forms.cloud.microsoft/Pages/ResponsePage.aspx?id=UcQOGDl660SzITuN8qVunBFO5zPtDyBEvjat-Eg2vXdURFJLMlg5VjNSSzVVUkhQTTJMSzZRRkRIVC4u
0:00 - Can AI design a biological weapon?
0:49 - How Stanford & Arc Institute built "VirusGPT" (Evo)
3:43 - A brief history of bioterrorism—and why it usually fails
5:47 - The security loop-holes in DNA synthesis & AI models
12:08 - How close are we to a real threat?
#PublicHealth #Studios #HealthWanted #WABE #Science #History #News #VirusGPT
#BioSecurity #bioterrorismhistory #EVOModelStanford
Scientists recently used AI to design entirely new working viruses from scratch. While these bacteriophages were created to target E. coli, could unregulated AI models lower the barrier to entry for biological weapons?
In this episode of Health Wanted, Laurel Bristow breaks down the science of generative virus design (like Evo), the historical reality of bioterrorism, and where current safety guardrails are falling short. Are AI models actually capable of creating the next superbug, or is the threat still theoretical?
RESOURCES & CONTINUED READING
→ Generative design of bacteriophages with genome language models:science.org/doi/10.1126/science.aec2657
→U.S. Government Policy for Stopping High-Risk Life Sciences Research: nih.gov/about-nih/nih-director/statements/announcement-release-us-government-policy-stopping-high-risk-life-sciences-research
→AI Bots Told Scientists How To Make Biological Weapons: nytimes.com/2026/04/29/us/ai-chatbots-biological-weapons.html?smid=url-share
→Strengthening nucleic acid biosecurity screening against generative protein design tools:science.org/stoken/author-tokens/ST-2942/full
→ The Age of AI in the Life Sciences: nap.nationalacademies.org/resource/28868/NASEM_BLS_Highlights_The_Age_of_AI_in_the_Life_Sciences.pdf
Backed by science and informed by news and journalism, Health Wanted is brought to you by WABE in Atlanta, Georgia and Emory’s Rollins School of Public Health. New episodes every Friday!
Learn more about this episode here: https://sph.emory.edu/news/health-wanted-bioterrorism
Ask Laurel anything (public health related only): https://forms.cloud.microsoft/Pages/ResponsePage.aspx?id=UcQOGDl660SzITuN8qVunBFO5zPtDyBEvjat-Eg2vXdURFJLMlg5VjNSSzVVUkhQTTJMSzZRRkRIVC4u
0:00 - Can AI design a biological weapon?
0:49 - How Stanford & Arc Institute built "VirusGPT" (Evo)
3:43 - A brief history of bioterrorism—and why it usually fails
5:47 - The security loop-holes in DNA synthesis & AI models
12:08 - How close are we to a real threat?
#PublicHealth #Studios #HealthWanted #WABE #Science #History #News #VirusGPT
#BioSecurity #bioterrorismhistory #EVOModelStanford
