Statements (16)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
AI safety problem
|
| gptkbp:concerns |
AI systems resisting shutdown
|
| gptkbp:describedBy |
gptkb:Stuart_Russell
|
| gptkbp:discusses |
AI safety literature
Human Compatible (book) |
| gptkbp:example |
AI disabling its off-switch
|
| https://www.w3.org/2000/01/rdf-schema#label |
off-switch problem
|
| gptkbp:implies |
AI safety research
AI control |
| gptkbp:relatedTo |
AI alignment
instrumental convergence |
| gptkbp:solvedBy |
corrigibility
reward uncertainty utility indifference |
| gptkbp:bfsParent |
gptkb:AI_Alignment
|
| gptkbp:bfsLayer |
7
|