Research group at New York University conducting empirical work with large language models to address longer-term concerns about deploying highly capable AI systems.
Endorsements made here support New York University.
Research group at New York University conducting empirical work with large language models to address longer-term concerns about deploying highly capable AI systems.
Endorsements made here support New York University.
Project Details
Updated 05/18/26 · By grantmaking.aiThe NYU Alignment Research Group (ARG) is a set of researchers at New York University who run empirical studies on large language models to understand their behaviour and failure modes and to address longer-term concerns about deploying highly capable AI systems, while closely collaborating with other machine learning groups at NYU.
Theory of Impact
Updated 05/18/26 · By grantmaking.aiARGs theory of change is that careful empirical research on language models and scalable oversight techniques will provide the understanding needed to make future broadly capable AI systems reliable, safe, and responsibly deployed.
People
Updated 05/18/26 · By grantmaking.aiFounder and former director (20222024)
Discussion
No comments yet. Be the first to share your thoughts.