How can we improve the alignment of Al systems with human values? CS PhD candidate Silviu Pitis seeks to address this challenge with the support of an OpenAl Superalignment Fast Grant.
A new paper by MScAC alumna Aparna Balagopalan demonstrates why labelling data with normative prompts can yield better outcomes in machine learning models. Its co-authors include Assistant Professor, Status-Only Marzyeh Ghassemi and CS graduate student David Madras.
