Nearly a decade ago, the U.S Department of Veterans Affairs and the Department of Energy launched the MVP-CHAMPION initiative, not for sports, but as a data-driven strategy for improving healthcare outcomes for veterans and others. Silvia Crivelli of Lawrence Berkeley National Laboratory turned her skills in computational biology toward this new field, especially the problem of identifying veterans at high risk for suicide. As she and her colleagues worked on this challenge, large language models and the notion of foundation models emerged. Now her team is focused on a more comprehensive challenge: a foundation model for medicine and healthcare.

• Silvia Crivelli is a staff scientist in the applied computing for scientific discovery group at Lawrence Berkeley National Laboratory, where she's worked for more than 25 years. Her research applies artificial intelligence to medicine and healthcare with the goal of combining biomolecular and clinical data. She works on the MVP-CHAMPION research initiative between the U.S. Department of Veterans Affairs and the Department of Energy, focuses on precision medicine for veterans and the broader population.

Foundation models-- LLMs or LLM-like tools-- are a compelling idea for advancing scientific discovery and democratizing computational science. But there's a big gap between these lofty ideas and the trustworthiness of current models.

Youngsoo Choi of Lawrence Livermore National Laboratory and his colleagues are thinking about to how to close this chasm. They're engaging with questions such as: What are the essential characteristics that define a foundation model? And how do we make sure that scientists can rely on their results?

In this conversation we discuss a position paper that Youngsoo and his colleagues wrote to outline these questions and propose starting points for consensus-based answers and the challenges in building foundation models that are robust, reliable and generalizable. That paper also describes the Data-Driven Finite Element Method, or DD-FEM, a tool that they've developed for combining the power of AI and large datasets with physics-based simulation.

Youngsoo Choi is a staff scientist at Lawrence Livermore National Laboratory (LLNL) and a member of the lab's Center for Applied Scientific Computing (CASC), which focuses on computational science research for national security problems. Youngsoo completed his Ph.D. in computational and mathematical engineering at Stanford University and carried out postdoctoral research at Stanford and Sandia National Laboratories before joining Livermore in 2017.

• Steven Wilson is a postdoctoral researcher in Christopher Muhich's research group at Arizona State University, where he completed both his undergraduate degree in 2020 and his Ph.D. in 2024. He was a DOE CSGF recipient from 2021 to 2024 and completed practicum research at Pacific Northwest National Laboratory (PNNL). He is also CEO of PsaiForge, a quantum chemistry software startup that he cofounded with Muhich.