AI-made viruses could be the future of medicine

August 25, 2026

AI Summary

5 min read

In early 2024, a Stanford researcher named Brian woke up at 6 a.m. to find that his colleague Samuel, who had pulled an all-nighter, had just gotten the first batch of results from an unusual experiment. They had trained an AI model not on the internet's text, but on DNA sequences—the four-letter genetic language of A, C, G, and T. After training, they asked the model to generate entirely new viral genome sequences, introduced those sequences into bacteria roughly 300 times, and waited. Sixteen of those AI-designed viruses worked. When Brian presented the data at his lab meeting, the room spontaneously broke into applause—the first time that had ever happened.

How to make a virus from scratch

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of Short Wave

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:23) **AI Trained on DNA to Design New Viruses** - NPR's Regina Barber and Katie Harlow introduce the story: scientists are using AI to create viruses, but these are designed to infect bacteria, not humans.
2 (00:58) **How the AI Learns the Language of DNA** - The researchers fed the AI DNA sequences, which are written in a four-letter alphabet (A, C, G, T), allowing the model to learn patterns in genetic language.
3 (02:13) **First Results: A Lab Breakthrough** - Lead researcher Brian (a Stanford scientist and former Facebook employee) describes the excitement when the first batch of results came in.
4 (04:42) **How the Experiment Worked** - The process: AI trained on DNA is asked to generate new genomic sequences, which are then inserted into bacteria, turning them into factories that produce the new viruses.
5 (05:04) **Short-Term Goal: Fighting Drug-Resistant Infections** - In the near term, researchers hope to use this technology to create tailor-made viruses to combat drug-resistant bacterial infections in humans.
6 (06:11) **Long-Term Vision: Treating Complex Diseases** - Looking decades ahead, researcher Brian imagines using AI to design much more complex biological systems, potentially addressing formidable diseases like Alzheimer's or cancer.
7 (07:06) **Expert Concerns: Lack of Governance** - Tom Ingallsby, director of the Johns Hopkins Center for Health Security, agrees the work is a big breakthrough but warns that safety is not guaranteed as the technology becomes more widely available.

+ Full timestamped outline available in the app

Show Notes

The era of AI-generated viruses is here. Some scientists are using AI to design viruses that can attack bacteria. The hope is that these tailor-made viruses can fight drug-resistant bacterial infections in people. And longer-term, Brian Hie, the Stanford researcher spearheading this project, hopes that AI can help create more complicated biological systems to treat formidable diseases. But some experts warn that placed in the wrong hands, this technology could create the next pandemic.

Interested in more AI-related research? Email us your question at [email protected].

Support public media with NPR+ and enjoy perks for over 25 podcasts like this one. This show’s perks include sponsor-free listening. Learn more at plus.npr.org.

See pcm.adswizz.com for information about our collection and use of personal data for sponsorship and to manage your podcast sponsorship preferences.

NPR Privacy Policy