Researchers in value alignment theory
This page lists researchers in AI alignment.
Eliezer Yudkowsky (founder, MIRI)
Nick Bostrom (founder, FHI)
Benja Fallenstein (MIRI; parametric polymorphism, the Procrastination Paradox, and numerous other developments in Vingean reflection.)
Patrick LaVictoire (MIRI; modal agents)
StuartArmstrong (FHI; Utility indifference)
Paul Christiano (UC Berkeley, approval-directed agents, previously proposed a formalization of indirect normativity)
StuartRussell (UC Berkeley; author of Artificial Intelligence: A Modern Approach; previously published on theories of reflective optimality; currently interested in inverse reinforcement learning.)
Jessica Taylor (MIRI, reflective oracles)
Andrew Critch (MIRI)
ScottGarabant (MIRI, logical probabilities)
Nate Soares (previously MIRI researcher, now Executive Director at MIRI)
Children:
- Nick Bostrom
Nick Bostrom, secretly the inventor of Friendly AI
Parents:
- AI alignment
The great civilizational problem of creating artificially intelligent computer systems such that running them is a good idea.