AGI Strategies

person

Scott Garrabrant

MIRI researcher; logical induction, Cartesian frames

Machine Intelligence Research Institute researcher who developed logical inductors (a formalism for assigning probabilities to mathematical statements over time) and Cartesian frames (a model of agent–environment boundaries).

current Research Fellow, Machine Intelligence Research Institute

Strategy positions

Agent foundationsendorses

Reformulate decision theory and embedded agency before behavioural training can be trusted

Argues robust alignment requires foundational work on what agency, embeddedness, and self-reference even mean before behavioral training methods can be trusted.

Logical inductors approximate well-calibrated probabilistic reasoning over computable statements: the bookmaker is gradually unable to extract money from the market over time.
§ paperLogical Induction· MIRI· 2016· faithful paraphrase

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Scott Garrabrant's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

  • Abram Demski

    shared 1 · J=1.00

    MIRI researcher; embedded agency

Record last updated 2026-04-25.