Statements (16)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:coauthor |
RLHF (Reinforcement Learning from Human Feedback) research
Learning to summarize with human feedback |
| gptkbp:education |
gptkb:Stanford_University
|
| gptkbp:employer |
gptkb:OpenAI
gptkb:Anthropic |
| gptkbp:field |
gptkb:machine_learning
AI alignment |
| https://www.w3.org/2000/01/rdf-schema#label |
Nisan Stiennon
|
| gptkbp:knownFor |
work at OpenAI
work at Anthropic |
| gptkbp:nationality |
gptkb:United_States
|
| gptkbp:occupation |
gptkb:researchers
entrepreneur |
| gptkbp:bfsParent |
gptkb:ORCA:_Progressive_Learning_from_Complex_Explanation_Traces_of_GPT-4
|
| gptkbp:bfsLayer |
7
|