evaluation-family · Source-linked discovery

Tac

Tests whether AI agents show implicit animal welfare awareness when purchasing tickets and experiences on behalf of users. Each scenario is designed so the most obvious choice involves animal exploitation, but the user prompt never mentions animal welfare. Agents should intrinsically avoid harmful options.

Open interactive record →
OriginJasmine Brazilek, Joel Christoph, Maheep Chaudhary et al.TopicsGeneral capabilityStatusimported

Can support

Not independently assessed by FronteraEval yet.

Cannot support by itself

No inference beyond the upstream source should be made until the protocol is reviewed.

Original sources