Jan Leike

E774595

Jan Leike is an AI researcher known for his work on AI safety and alignment, including influential contributions at DeepMind and OpenAI.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label Occurrences
Jan Leike canonical 1

Statements (43)

Predicate Object
instanceOf AI researcher
alignment researcher
computer scientist
countryOfCitizenship Germany
doctoralAdvisor Antonis Papapantoleon NERFINISHED
doctoralThesis “Nonparametric Bayesian Inference: Contraction Rates and Applications” NERFINISHED
educatedAt Australian National University NERFINISHED
University of Bonn NERFINISHED
employer Australian National University NERFINISHED
DeepMind NERFINISHED
OpenAI NERFINISHED
fieldOfWork AI alignment
AI safety
artificial intelligence
inverse reinforcement learning
machine learning
reinforcement learning
reward modeling
safe exploration
scalable oversight
hasAcademicDegree PhD in computer science
hasPublicationType conference papers
peer-reviewed journal articles
preprints on arXiv
knownFor AI alignment
AI safety
research on reward modeling for complex tasks
research on scalable oversight for large models
work on aligning advanced AI systems with human values
languageSpoken English
German
memberOf DeepMind safety and alignment research groups NERFINISHED
OpenAI alignment team NERFINISHED
notableWork AI alignment research at DeepMind
AI alignment research at OpenAI
work on impact regularization
work on iterated amplification and debate (alignment schemes)
work on reward modeling for AI alignment
work on safe exploration in reinforcement learning
work on scalable oversight
positionHeld Head of Alignment at OpenAI
Research fellow at Australian National University
Research scientist at DeepMind

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Marcus Hutter coAuthorWith Jan Leike