EconFaithAI · Map

The case

Open-source benchmark scoring how much a model performs personhood — used by schools, procurement officers, and regulators.

Why it scores the way it does

Solution Fit 6 / 10
Translates academic to procurement; tangential to UX directly
Stakeholder Fit 7 / 10
Academics and industry orgs natural builders
Feasibility 8 / 10
Academic benchmarks exist; conversion buildable
Urgency 8 / 10
CA procurement EO opens window

Current landscape

Status: ● Active
Academic: AnthroScore (2024), AnthroBench, HeartBench, Godspeed Anthropomorphism scale. None translated to procurement-grade scoring.

References (3)

Related

SAME PROBLEM (Anthropomorphism)
SAME STAKEHOLDER (Investors)

Click any text or score to edit. Esc to cancel.