Statements (21)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:affiliation |
gptkb:University_of_California,_Berkeley
gptkb:Machine_Intelligence_Research_Institute |
| gptkbp:doctoralAdvisor |
gptkb:Leonid_Gurvits
|
| gptkbp:education |
gptkb:University_of_California,_Berkeley
gptkb:University_of_Waterloo |
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:mathematics AI safety |
| gptkbp:knownFor |
work on AI alignment
co-founding the Center for Human-Compatible AI |
| gptkbp:nationality |
gptkb:Canadian
|
| gptkbp:notableWork |
research on logical uncertainty
work on Eliciting Latent Knowledge (ELK) |
| gptkbp:occupation |
gptkb:entrepreneur
gptkb:mathematician gptkb:AI_safety_researcher |
| gptkbp:website |
https://critch.com/
|
| gptkbp:bfsParent |
gptkb:Center_for_Applied_Rationality
|
| gptkbp:bfsLayer |
6
|
| https://www.w3.org/2000/01/rdf-schema#label |
Andrew Critch
|