Statements (61)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
concept
|
| gptkbp:alsoKnownAs |
gptkb:Superintelligent_AI
|
| gptkbp:benefit |
technological progress
|
| gptkbp:challenge |
gptkb:orthogonality_thesis
AI ethics AI alignment research AI safety research AI governance AI forecasting AI policy corrigibility AI regulation AI transparency control problem instrumental convergence AI arms race AI boxing AI catastrophic risk AI containment AI dual use AI existential risk mitigation AI global coordination AI interpretability AI misuse AI risk assessment AI robustness AI security AI superalignment AI value learning goal specification value alignment problem |
| gptkbp:containsScenario |
singularity
intelligence explosion AI takeover friendly AI unfriendly AI |
| gptkbp:debatedBy |
gptkb:Bill_Gates
gptkb:Elon_Musk gptkb:Geoffrey_Hinton gptkb:Ray_Kurzweil gptkb:Stephen_Hawking gptkb:Yoshua_Bengio gptkb:Max_Tegmark gptkb:Nick_Bostrom gptkb:Demis_Hassabis gptkb:Sam_Altman gptkb:Stuart_Russell |
| gptkbp:describedBy |
gptkb:Nick_Bostrom
gptkb:Superintelligence:_Paths,_Dangers,_Strategies |
| gptkbp:hasProperty |
autonomous decision making
intelligence surpassing human level self-improvement capability |
| https://www.w3.org/2000/01/rdf-schema#label |
Machine Super Intelligence
|
| gptkbp:relatedTo |
gptkb:artificial_intelligence
gptkb:Artificial_General_Intelligence |
| gptkbp:riskFactor |
existential risk
|
| gptkbp:studiedIn |
ethics
philosophy of mind AI safety |
| gptkbp:bfsParent |
gptkb:Shane_Legg
|
| gptkbp:bfsLayer |
6
|