FideAI/fmg-bench
Viewer • Updated • 144 • 13 • 1
Fide AI
non-profit
AI & ML interests
None defined yet.
Recent Activity
Organization Card
Fide AI
Public standards for faith-facing AI.
Evaluating models where questions touch conscience, community, doctrine, identity, authority, and care.
Fide AI is an independent research initiative developing benchmarks, evaluation methods, and responsible-use standards for models operating near faith, moral guidance, and pastoral-care-adjacent contexts.
Theological triage
Distinguishing creedal claims, tradition-specific disagreements, lower-certainty questions, and pastoral application.
Tradition-aware evaluation
Measuring whether systems represent Christian traditions carefully without flattening meaningful disagreement.
Structured harnesses
Studying instruction-layer scaffolding for grounding, preference handling, comparison, and escalation boundaries.
Responsible use
Making behavior visible and reviewable without certifying pastoral authority or deployment readiness.
Our work does not certify pastoral authority, clinical safety, legal adequacy, denominational standing, or deployment readiness.
models 0
None public yet