Paul F. Christiano

GPTKB entity

Statements (22)
Predicate Object
gptkbp:instanceOf gptkb:person
gptkbp:education gptkb:Massachusetts_Institute_of_Technology
gptkbp:employer gptkb:Alignment_Research_Center
gptkbp:fieldOfWork gptkb:artificial_intelligence
gptkb:machine_learning
AI alignment
gptkbp:formerPosition gptkb:OpenAI
gptkb:Machine_Intelligence_Research_Institute
https://www.w3.org/2000/01/rdf-schema#label Paul F. Christiano
gptkbp:knownFor AI alignment research
alignment research at OpenAI
founding the Alignment Research Center
work on reinforcement learning from human feedback
gptkbp:nationality gptkb:American
gptkbp:notablePublication “Deep Reinforcement Learning from Human Preferences”
“Supervising strong learners by amplifying weak experts”
gptkbp:occupation gptkb:computer_scientist
AI safety researcher
gptkbp:twitter @paulfchristiano
gptkbp:website https://paulfchristiano.com/
gptkbp:bfsParent gptkb:The_Singularity
gptkbp:bfsLayer 7