Vasisht Duddu

@vasishtduddu

Distinguished Postdoc Fellow @ Vector Institute | PhD @UWaterloo | AI safety, security and privacy

following
followers

Better oversight methods versus more evaluator organizations for frontier AI

The post invites collaborators to develop oversight that can scale, including ways to verify AI agents’ behavior and study collusion and covert communication in systems with multiple agents.

4 Sources, 38d ago, first seen 38d ago

Featured in

Better oversight methods versus more evaluator organizations for frontier AI

Featured in

Better oversight methods versus more evaluator organizations for frontier AI