person
Abram Demski
MIRI researcher; embedded agency
MIRI researcher who co-authored the 'Embedded Agency' sequence outlining gaps in classical decision theory when an agent is part of the environment it reasons about.
current Research Fellow, Machine Intelligence Research Institute
Strategy positions
Agent foundationsendorses
Reformulate decision theory and embedded agency before behavioural training can be trustedArgues 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.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Abram Demski's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.