person
Rich Caruana
Microsoft Research; interpretable ML
Microsoft Research senior principal researcher; pioneer of interpretable machine learning via Generalized Additive Models with Interactions (GA²Ms / EBM).
current Senior Principal Researcher, Microsoft Research
Strategy positions
Interpretability betendorses
Mechanistic interpretability is necessary and sufficient to know models are safeArgues high-stakes ML applications, health, criminal justice, finance, should default to interpretable models that practitioners can audit by hand, not opaque deep nets.
Black-box models are not appropriate for high-stakes decisions. We have interpretable models that match black-box accuracy in many of these domains; using them is a matter of choice, not capability.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Rich Caruana's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.