AGI Strategies

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 safe

Argues 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.
articleInterpretable Machine Learning· Microsoft Research· 2019· faithful paraphrase

Closest strategy neighbours

by jaccard overlap

Other 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.

  • Asma Ghandeharioun

    shared 1 · J=1.00

    Google DeepMind; 'Patchscopes' for LLM interpretability

  • Chris Olah

    Chris Olah

    shared 1 · J=1.00

    Anthropic interpretability co-founder; inventor of modern mech interp

  • Cynthia Rudin

    Cynthia Rudin

    shared 1 · J=1.00

    Duke professor; interpretable ML pioneer

  • David Bau

    shared 1 · J=1.00

    Northeastern; mechanistic interpretability of LLMs

  • Fernanda Viégas

    shared 1 · J=1.00

    Harvard; ex-Google PAIR; data visualization

  • Jacob Andreas

    Jacob Andreas

    shared 1 · J=1.00

    MIT NLP; language models as belief reports

Record last updated 2026-04-25.