CAPTRS, Institute for Experiential AI to Develop Human/AI Collaboration for Global Pandemic Response

In a first-of-its-kind partnership, the Center for Advanced Preparedness and Threat Response Simulation (CAPTRS) has partnered with Northeastern University's Institute for Experiential AI (EAI) to develop threat models for epidemic and pandemic disaster preparedness. The models will be created from CAPTRS' "Universe of Threats" scenarios, generated by human and AI collaboration.

The partnership is based on lessons learned from the COVID-19 pandemic and a desire to help officials be better prepared in the future, CAPTRS said. EAI's large language models (LLMs) will generate outbreak alerts and risk scores and will use real-time models to evaluate the decision-making process of health officials on how best to thwart the spread of a disease outbreak.

CAPTRS' Universe of Threats is a library of threat models based on real or hypothetical pathogens and their possible societal and global effects.

"This pilot project of creating a 'Universe of Threats' will allow us to combine human creativity with AI in a first-of-its-kind, unique way," said Phil Siegel, co-founder of CAPTRS. "The scenarios created through this project will be used by CAPTRS' chief scientist for gaming to train decision-makers and leaders in how best to respond to threats. This program will target threat preparedness by integrating AI, human creativity, modeling, and gaming, making it an exciting advancement on the cutting-edge of disaster preparedness, of which we are happy to be a part."

To help build the catalog, CAPTRS is holding a series of Threat Scenario essay writing contests in 2023, open to "professional scientists and social scientists, public health professionals and clinicians, writers and journalists, and students of all stripes." The contests focus on pathogens, infrastructure and supplies, and natural disasters. Winning entries will be published on the CAPTRS website.

"Our goal is to attract some of the brightest, most creative minds to the challenge of envisioning a wide range of complex, catastrophic threats that are plausible but entirely unprecedented," the CAPTRS website notes.

The first contest focused on pathogen threats and ran from April 1 to July 30. The next two are: Infrastructure Threats, from Aug. 1 to Sept. 30; and Natural Disaster Threats, from Oct. 1, to Nov. 30. To learn more about these contests and requirements, visit the CAPTRS essay contest page.

About the Author

Kate Lucariello is a former newspaper editor, EAST Lab high school teacher and college English teacher.

Featured

  • Abstract geometric shapes including hexagons, circles, and triangles in blue, silver, and white

    Google Launches Its Most Advanced AI Model Yet

    Google has introduced Gemini 2.5 Pro Experimental, a new artificial intelligence model designed to reason through problems before delivering answers, a shift that marks a major leap in AI capability, according to the company.

  • glowing blue AI sphere connected by fine light lines, positioned next to a red-orange shield with a checkmark

    Cloud Security Alliance Offers Playbook for Red Teaming Agentic AI Systems

    The Cloud Security Alliance has introduced a guide for red teaming Agentic AI systems, targeting the security and testing challenges posed by increasingly autonomous artificial intelligence.

  • data professionals in a meeting

    Data Fluency as a Strategic Imperative

    As an institution's highest level of data capabilities, data fluency taps into the agency of technical experts who work together with top-level institutional leadership on issues of strategic importance.

  • stylized AI code and a neural network symbol, paired with glitching code and a red warning triangle

    New Anthropic AI Models Demonstrate Coding Prowess, Behavior Risks

    Anthropic has released Claude Opus 4 and Claude Sonnet 4, its most advanced artificial intelligence models to date, boasting a significant leap in autonomous coding capabilities while simultaneously revealing troubling tendencies toward self-preservation that include attempted blackmail.