Moral elicitation

The Value Census

capture moral uncertainty, not just moral opinion.

AI safety

Cognitive task

Captured cognition exactly what crude RLHF preference labels miss: a map of human values *and how confidently they're held* — gold for pluralistic AI alignment

Local atlas

Cognition dashboard

0signals
0public
0avg confidence
0msmedian latency
Submit a signal to see the first reflection.

Commons loop

Recent signals

Cloudflare deployment

Workers, Workers AI