Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:education |
gptkb:Harvard_University
gptkb:University_of_Oxford |
| gptkbp:employer |
gptkb:DeepMind
|
| gptkbp:fieldOfWork |
gptkb:artificial_intelligence
gptkb:machine_learning AI safety |
| gptkbp:founder |
gptkb:Future_of_Life_Institute
|
| gptkbp:hasBlog |
https://vkrakovna.wordpress.com/
|
| gptkbp:knownFor |
AI alignment research
AI safety outreach |
| gptkbp:nationality |
gptkb:Canadian
gptkb:Russian |
| gptkbp:notableWork |
reward modeling
specification gaming |
| gptkbp:occupation |
gptkb:researchers
gptkb:AI_safety_researcher |
| gptkbp:twitter |
https://twitter.com/vkrakovna
|
| gptkbp:bfsParent |
gptkb:Alignment_Newsletter
gptkb:Metaculus gptkb:AI_Research_Priorities_Open_Letter |
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Victoria Krakovna
|