AI & Advanced Computing
Maarten Sap

-
Program
AI Safety Science
-
Institution
Carnegie Mellon University
-
Location
USA
Dr. Maarten Sap, Assistant Professor at Carnegie Mellon University’s Language Technologies Department and part-time researcher at the Allen Institute for AI, leads the project. Known for his work on social intelligence in NLP systems, Sap has been recognized at major NLP and AI conferences and extensively covered in the press. His academic journey includes a PhD from the University of Washington and a postdoctoral stint at AI2. Supporting him is Dr. Neubig, a core NLP and machine learning expert, whose extensive research output includes significant contributions to AI evaluations and code generation agents.
The OpenAgentSafety project introduces a novel framework for testing AI agent safety through simulations that include user interactions and tool usage.