04271nam 2201057z- 450 991040408420332120240301181825.03-03921-854-9(CKB)4100000011302296(oapen)https://directory.doabooks.org/handle/20.500.12854/41358(EXLCZ)99410000001130229620202102d2020 |y 0engurmn|---annantxtrdacontentcrdamediacrrdacarrierArtificial Superintelligence: Coordination & StrategyMDPI - Multidisciplinary Digital Publishing Institute20201 electronic resource (206 p.)3-03921-855-7 Attention in the AI safety community has increasingly started to include strategic considerations of coordination between relevant actors in the field of AI and AI safety, in addition to the steadily growing work on the technical considerations of building safe AI systems. This shift has several reasons: Multiplier effects, pragmatism, and urgency. Given the benefits of coordination between those working towards safe superintelligence, this book surveys promising research in this emerging field regarding AI safety. On a meta-level, the hope is that this book can serve as a map to inform those working in the field of AI coordination about other promising efforts. While this book focuses on AI safety coordination, coordination is important to most other known existential risks (e.g., biotechnology risks), and future, human-made existential risks. Thus, while most coordination strategies in this book are specific to superintelligence, we hope that some insights yield “collateral benefits” for the reduction of other existential risks, by creating an overall civilizational framework that increases robustness, resiliency, and antifragility.Artificial Superintelligencestrategic oversightmulti-agent systemsautonomous distributed systemartificial superintelligencesafe for designadaptive learning systemsexplainable AIethicsscenario mappingtypologies of AI policyartificial intelligencedesign for valuesdistributed goals managementscenario analysisGoodhart’s Lawspecification gamingAI ThinkingVSDAIhuman-in-the-loopvalue sensitive designfuture-readyforecasting AI behaviorAI arms raceAI alignmentblockchainartilectspolicy making on AIdistributed ledgerAI riskBayesian networksartificial intelligence safetyconflictAI welfare sciencemoral and ethical behaviorscenario network mappingpolicymaking processhuman-centric reasoningantispeciesismAI forecastingtransformative AIASILOMARjudgmental distillation mappingterraformingpedagogical motifAI welfare policiessuperintelligenceartificial general intelligencesupermoralityAI value alignmentAGIpredictive optimizationAI safetytechnological singularitymachine learningholistic forecasting frameworksimulationsexistential risktechnology forecastingAI governancesentiocentrismAI containmentYampolskiy Romanauth1278170Duettmann AllisonauthBOOK9910404084203321Artificial Superintelligence: Coordination & Strategy3012755UNINA