Statements (19)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:affiliation |
gptkb:Alignment_Research_Center
gptkb:LessWrong |
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning AI safety |
| https://www.w3.org/2000/01/rdf-schema#label |
TurnTrout
|
| gptkbp:knownFor |
research on corrigibility
research on reward modeling research on value learning |
| gptkbp:nationality |
gptkb:American
|
| gptkbp:notableFor |
work on AI alignment
posts on LessWrong |
| gptkbp:occupation |
AI alignment researcher
|
| gptkbp:realName |
Alex Turner
|
| gptkbp:targetUser |
gptkb:TurnTrout
|
| gptkbp:website |
https://www.lesswrong.com/users/turntrout
|
| gptkbp:bfsParent |
gptkb:LessWrong_2.0
|
| gptkbp:bfsLayer |
7
|