Coherent Extrapolated Volition
GPTKB entity
Statements (13)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:concept
|
| gptkbp:aims_to |
align AI with human values
|
| gptkbp:focuses_on |
collective human preferences
|
| https://www.w3.org/2000/01/rdf-schema#label |
Coherent Extrapolated Volition
|
| gptkbp:is_a |
gptkb:physicist
|
| gptkbp:is_related_to |
Friendly AI
|
| gptkbp:is_used_in |
AI safety discussions
|
| gptkbp:issues |
long-term outcomes
|
| gptkbp:proposed_by |
gptkb:Eliezer_Yudkowsky
|
| gptkbp:related_to |
gptkb:Artificial_Intelligence
Future of Humanity |
| gptkbp:bfsParent |
gptkb:Singularity_Institute_for_Artificial_Intelligence
|
| gptkbp:bfsLayer |
5
|