Artificial Superintelligence: Coordination & Strategy
- ISBN-10
- 3039218549
- ISBN-13
- 9783039218547
- Category
- Technology & Engineering
- Pages
- 206
- Language
- English
- Published
- 2020-04-30
- Publisher
- MDPI
- Authors
- Roman V. Yampolskiy, Allison Duettmann
Description
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.
Get the book
Other editions
Similar books
-
Superintelligence: Paths, Dangers, Strategies
By Nick BostromGood, Irving John. 1965. “Speculations Concerning the First Ultraintelligent Machine.” In Advances in Computers, edited by Franz L. Alt and Morris Rubinoff, 6:31–88. New York: Academic Press. Good, Irving John. 1970.
-
Artificial Superintelligence Handbook II: Cognitive AI
By Rob SmithIt takes a brand new way of thinking about artificial intelligence because today's AI systems and infrastructure will not support a true human level cognitive superintelligence, In this edition of the Superintelligence Handbook, I discuss ...
-
The Psychology of Artificial Superintelligence
By Joachim DiederichThis book explores the psychological impact of advanced forms of artificial intelligence.
-
The Ethics of Superintelligent Design: A Christian View of the Theological and Moral Implications of Artificial Superintelligence
By Paul GolataThe Ethics of Superintelligent Design critically examines and challenges some of the most important trajectories of ASI while upholding the authority and inerrancy of the Bible, the supernatural creation account, a realistic view of the ...
-
Artificial Superintelligence Handbook IV: Dimensional Cognitive Artificial General Intelligence
By Rob SmithThis is the 4th and final book in the Artificial Superintelligence Handbook series and details the design of a Dimensional Cognitive Artificial General Intelligence as the final stage in the progression from designing and building narrow AI ...
-
The Artificial Superintelligence Handbook
By Rob SmithThe other nice thing about the world is that one day someone may find what you leave behind and be inspired to create something life saving and earth changing. That is what this book is.
-
Human Compatible: Artificial Intelligence and the Problem of Control
By Stuart Jonathan RussellA leading artificial intelligence researcher lays out a new approach to AI that will enable people to coexist successfully with increasingly intelligent machines.
-
Asi: Artificial Superintelligence
By Krikor KaraoghlanianIn this book, we explore the theoretical foundations, technical challenges, ethical considerations, current state, and future implications of ASI.
-
Artificial Superintelligence: Coordination & Strategy
By Allison Duettmann, Roman YampolskiyWhile 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.
-
The Myth of Artificial Intelligence: Why Computers Can't Think the Way We Do
By Erik J. LarsonAI reasons from statistical correlations across data sets, while common sense is based heavily on conjecture. Erik Larson argues that hyping existing methods will only hold us back from developing truly humanlike AI.