Artificial Superintelligence: Coordination & Strategy
- MDPI - Multidisciplinary Digital Publishing Institute 2020
- 1 electronic resource (206 p.)
Open Access
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.
Creative Commons
English
9783039218554 9783039218547
Искусственный интеллект
strategic oversight multi-agent systems autonomous distributed system artificial superintelligence safe for design adaptive learning systems explainable AI ethics scenario mapping typologies of AI policy artificial intelligence design for values distributed goals management scenario analysis Goodhart’s Law specification gaming AI Thinking VSD AI human-in-the-loop value sensitive design future-ready forecasting AI behavior AI arms race AI alignment blockchain artilects policy making on AI distributed ledger AI risk Bayesian networks artificial intelligence safety conflict AI welfare science moral and ethical behavior scenario network mapping policymaking process human-centric reasoning antispeciesism AI forecasting transformative AI ASILOMAR judgmental distillation mapping terraforming pedagogical motif AI welfare policies superintelligence artificial general intelligence supermorality AI value alignment AGI predictive optimization AI safety technological singularity machine learning holistic forecasting framework simulations existential risk technology forecasting AI governance sentiocentrism AI containment