Fabio Anza, an assistant professor in UMBC's Department of Physics, Quantum Science Institute and Cybersecurity Institute, has won an Amazon Research Award to develop Physics Co-Pilot—a scientific AI assistant that combines large language model orchestration with reliable computational algorithms to address critical bottlenecks in modern physics research.
Physics Co-Pilot takes a fundamentally different approach from current AI code generation systems. Rather than having language models write code—which can produce unreliable results—the system uses LLMs only for natural language understanding, while delegating all computational work to pre-written, validated algorithms.
Read more about his award and project here.