Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899014757> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2899014757 abstract "It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior--social norms and laws. But human laws and norms are complex and culturally varied systems, in many cases agents will have to learn the rules. This requires autonomous agents to have models of how human rule systems work so that they can make reliable predictions about rules. In this paper we contribute to the building of such models by analyzing an overlooked distinction between important rules and what we call silly rules--rules with no discernible direct impact on welfare. We show that silly rules render a normative system both more robust and more adaptable in response to shocks to perceived stability. They make normativity more legible for humans, and can increase legibility for AI systems as well. For AI systems to integrate into human normative systems, we suggest, it may be important for them to have models that include representations of silly rules." @default.
- W2899014757 created "2018-11-09" @default.
- W2899014757 creator A5000711679 @default.
- W2899014757 creator A5071066840 @default.
- W2899014757 creator A5076757561 @default.
- W2899014757 date "2018-11-03" @default.
- W2899014757 modified "2023-10-14" @default.
- W2899014757 title "Legible Normativity for AI Alignment: The Value of Silly Rules" @default.
- W2899014757 cites W1484113995 @default.
- W2899014757 cites W1556726625 @default.
- W2899014757 cites W1985340978 @default.
- W2899014757 cites W1985728544 @default.
- W2899014757 cites W1992154343 @default.
- W2899014757 cites W2061562262 @default.
- W2899014757 cites W211005570 @default.
- W2899014757 cites W2115749907 @default.
- W2899014757 cites W2132046663 @default.
- W2899014757 cites W2135479081 @default.
- W2899014757 cites W2403984353 @default.
- W2899014757 cites W2486481829 @default.
- W2899014757 cites W2576798161 @default.
- W2899014757 cites W2750866482 @default.
- W2899014757 cites W3122602001 @default.
- W2899014757 hasPublicationYear "2018" @default.
- W2899014757 type Work @default.
- W2899014757 sameAs 2899014757 @default.
- W2899014757 citedByCount "0" @default.
- W2899014757 crossrefType "posted-content" @default.
- W2899014757 hasAuthorship W2899014757A5000711679 @default.
- W2899014757 hasAuthorship W2899014757A5071066840 @default.
- W2899014757 hasAuthorship W2899014757A5076757561 @default.
- W2899014757 hasConcept C111472728 @default.
- W2899014757 hasConcept C112698675 @default.
- W2899014757 hasConcept C119857082 @default.
- W2899014757 hasConcept C13687954 @default.
- W2899014757 hasConcept C138885662 @default.
- W2899014757 hasConcept C144024400 @default.
- W2899014757 hasConcept C144133560 @default.
- W2899014757 hasConcept C154945302 @default.
- W2899014757 hasConcept C17744445 @default.
- W2899014757 hasConcept C190253527 @default.
- W2899014757 hasConcept C199539241 @default.
- W2899014757 hasConcept C2776291640 @default.
- W2899014757 hasConcept C2779332521 @default.
- W2899014757 hasConcept C41008148 @default.
- W2899014757 hasConcept C44725695 @default.
- W2899014757 hasConceptScore W2899014757C111472728 @default.
- W2899014757 hasConceptScore W2899014757C112698675 @default.
- W2899014757 hasConceptScore W2899014757C119857082 @default.
- W2899014757 hasConceptScore W2899014757C13687954 @default.
- W2899014757 hasConceptScore W2899014757C138885662 @default.
- W2899014757 hasConceptScore W2899014757C144024400 @default.
- W2899014757 hasConceptScore W2899014757C144133560 @default.
- W2899014757 hasConceptScore W2899014757C154945302 @default.
- W2899014757 hasConceptScore W2899014757C17744445 @default.
- W2899014757 hasConceptScore W2899014757C190253527 @default.
- W2899014757 hasConceptScore W2899014757C199539241 @default.
- W2899014757 hasConceptScore W2899014757C2776291640 @default.
- W2899014757 hasConceptScore W2899014757C2779332521 @default.
- W2899014757 hasConceptScore W2899014757C41008148 @default.
- W2899014757 hasConceptScore W2899014757C44725695 @default.
- W2899014757 hasOpenAccess W2899014757 @default.
- W2899014757 hasRelatedWork W120051529 @default.
- W2899014757 hasRelatedWork W1838030805 @default.
- W2899014757 hasRelatedWork W2011313675 @default.
- W2899014757 hasRelatedWork W2073806160 @default.
- W2899014757 hasRelatedWork W2170980741 @default.
- W2899014757 hasRelatedWork W2286396146 @default.
- W2899014757 hasRelatedWork W2462226469 @default.
- W2899014757 hasRelatedWork W2500539358 @default.
- W2899014757 hasRelatedWork W2548110806 @default.
- W2899014757 hasRelatedWork W2735332299 @default.
- W2899014757 hasRelatedWork W2778796877 @default.
- W2899014757 hasRelatedWork W2942273265 @default.
- W2899014757 hasRelatedWork W2958320508 @default.
- W2899014757 hasRelatedWork W3121551939 @default.
- W2899014757 hasRelatedWork W3125203539 @default.
- W2899014757 hasRelatedWork W3164667201 @default.
- W2899014757 hasRelatedWork W3212153928 @default.
- W2899014757 hasRelatedWork W998841614 @default.
- W2899014757 hasRelatedWork W2471267854 @default.
- W2899014757 hasRelatedWork W3140638215 @default.
- W2899014757 isParatext "false" @default.
- W2899014757 isRetracted "false" @default.
- W2899014757 magId "2899014757" @default.
- W2899014757 workType "article" @default.