Research publications
Our work on AI evaluations, manipulation, security, and multi-agent risks.
Browse publicationsPlease direct all media inquiries to contact@apartresearch.com
Apart Research is a nonprofit working on independent AI safety research and evaluations. Its work examines model behavior, capabilities, and risks through empirical evaluations and technical investigation.
Apart tests general-purpose AI models for harmful manipulation, one of the systemic risks under the EU AI Act.
Alongside its research, Apart runs Sprints and Fellowships that help researchers develop early ideas, collaborate, and work toward publications.
Our work on AI evaluations, manipulation, security, and multi-agent risks.
Browse publicationsOur mission, team, board members, and advisors in one place.
About ApartNews from Apart and its programs.
Latest news