Ongoing / MARS V
Aligning AIs Via External Incentives
Extending revealed-preference methods to isolate how external incentives change model choices.
With Peter Salib, Simon Goldstein, Cole Niblett
This MARS V project at the Cambridge AI Safety Hub extends the revealed-preferences and incentive-sensitivity line toward tighter experimental isolation.
This project is being developed with Peter Salib, Simon Goldstein, and Cole Niblett.