MIT Technology Review has scheduled an October 16 discussion with Samuel King about research on using AI models to design bacteriophages, according to an event listing published October 9.
The conversation matters because the underlying research describes laboratory-tested, AI-generated designs for complete bacteriophage genomes, a step beyond narrower protein or gene design claims, according to the Broad Institute publication page.
MIT Technology Review's listing says the live event will feature senior AI reporter James O'Donnell interviewing King, identified there as a bioengineering PhD candidate at Stanford University and the Arc Institute, at 18:30 BST on October 16, with registration required.
The listing characterizes King's work as using a generative AI model in 2025 to propose genetic blueprints for microscopic viruses and says it is "not yet an example of AI-generated life," adding that "that could be next." The listing is an announcement for a planned conversation, not the interview itself.
The primary document available is the Broad Institute publication page for a paper titled "Generative design of bacteriophages with genome language models," which lists Samuel King, Claudia Driscoll, David Li, Daniel Guo, Aditi Merchant, Garyk Brixi, Max Wilkinson and Brian Hie as authors. According to that page, the work was published in Science (New York, N.Y.). The page says the researchers "report the first generative design of complete bacteriophage genomes using genome language models" and that they generated viable bacteriophages with target host tropism using the phage ΦX174 as a design template.
The abstract says experimental testing yielded 16 phages with diverse fitness profiles in laboratory conditions. It also says cryo-electron microscopy confirmed that one generated phage used an evolutionarily distant DNA packaging protein in its capsid. The same abstract says a cocktail of generated phages rapidly overcame ΦX174-resistant strains, which the authors said demonstrated a path toward AI-generated phage therapies against rapidly evolving bacterial pathogens.
The available material does not include the full Science paper text, methods section, evaluation setup or quantitative baselines beyond the abstract-level claims reproduced on the Broad Institute page. That means this report cannot assess model configuration, training data, comparison against non-AI design methods or how often proposed genomes failed. It also does not establish any use outside laboratory conditions.