Artificial Superintelligence: Coordination & StrategyRoman V. Yampolskiy, Allison Duettmann 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. |
Common terms and phrases
accessed achieve agents AI-ALS AI-ALS from Vendor analysis approach Artificial Intelligence Available online axioms behavior Bostrom combined common compared complex computational considered contribute coordination create CrossRef decisions discussed distributed educational effective Ethics example existing experts factors failure Figure forecasting framework further future global goals governance groups High-level higher human ideally implementation important increase indicators interest International issues judgmental learning limited Low-level lower difference machine mapping means methods Mid-level moral node optimization organizations original paper-based Post-test performance planning policymakers political possible potential prediction presented probability problem progress proposed questions reduce risk safety scenario similar simulated social society solutions specific stakeholders strategic students who scored suffering suggest superintelligence techniques theory topic understand University values