AGI Strategies

strategy tag

Agent foundations.

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

also known as: embedded agency

People on the record.

2

Abram Demski

MIRI researcher; embedded agency

endorses

Argues that 'embedded' reasoning, where an agent is a physical computation inside its world rather than a Cartesian observer, is the root of unresolved alignment problems.

Classical decision theory implicitly assumes a Cartesian boundary between agent and environment. Embedded agents lack this boundary, and that is where most alignment problems hide.
blogEmbedded Agency· AI Alignment Forum· 2018· faithful paraphrase

Scott Garrabrant

MIRI researcher; logical induction, Cartesian frames

endorses

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