Eliezer Yudkowsky and others' Berkeley AI safety organization — focused on foundational mathematical research for creating provably safe artificial general intelligence — one of the earliest dedicated AI safety organizations.
Creates the institutional infrastructure for AI alignment research — MIRI's early work on decision theory, logical uncertainty, and agent foundations established AI safety as a research discipline before mainstream AI labs took it seriously.
Discussing
Ask anything about MIRI — their ideas, influences, contradictions, legacy.
Sign in to start a conversation.