Davide Grossi has received funding from ARIA (Advanced Research + Invention Agency) as part of the Safeguarded AI programme; an £59 million initiative aimed at developing the safety standards needed for transformational AI. Davide joins an international consortium led by the University of Warwick, with funding covering an 18-month project and a one-year postdoc position at the University of Groningen.

The project will focus on one of the central challenges in AI safety: aggregating diverse and often conflicting human perspectives. The team will develop a framework for aggregating human safety specifications for AI systems, with the goal of contributing to a “gatekeeper AI” that mitigates risks posed by AI agents. The core technology involves novel methods in the tradition of social choice theory to elicit and aggregate stakeholder preferences regarding acceptable risk thresholds and safety conditions.

Read more about the ARIA programme.