Preface: Introduction to AI Safety and Security |
Acknowledgments |
Editor |
Contributors |
Concerns of Luminaries / Part I: |
Why the Future Doesn't Need Us / Bill JoyChapter 1: |
The Deeply Intertwined Promise and Peril of GNR / Ray KurzweilChapter 2: |
The Basic AI Drives / Stephen M. OmohundroChapter 3: |
The Ethics of Artificial Intelligence / Nick Bostrom and Eliezer YudkowskyChapter 4: |
Friendly Artificial Intelligence: The Physics Challenge / Max TegmarkChapter 5: |
MDL Intelligence Distillation: Exploring Strategies for Safe Access to Superintelligent Problem-Solving Capabilities / K. Eric DrexlerChapter 6: |
The Value Learning Problem / Nate SoaresChapter 7: |
Adversarial Examples in the Physical World / Alexey Kurakin and Ian J. Goodfellow and Samy BengioChapter 8: |
How Might AI Come About?: Different Approaches and Their Implications for Life in the Universe / David BrinChapter 9: |
The MADCOM Future: How Artificial Intelligence Will Enhance Computational Propaganda, Reprogram Human Culture, and Threaten Democracy … and What can be Done About It / Matt ChessenChapter 10: |
Strategic Implications of Openness in AI Development / Nick BostromChapter 11: |
Responses of Scholars / Part II: |
Using Human History, Psychology, and Biology to Make AI Safe for Humans / Gus BekdashChapter 12: |
AI Safety: A First-Person Perspective / Edward FrenkelChapter 13: |
Strategies for an Unfriendly Oracle AI with Reset Button / Olle HäggströmChapter 14: |
Goal Changes in Intelligent Agents / Seth Herd and Stephen J. Read and Randall O'Reilly and David J. JilkChapter 15: |
Limits to Verification and Validation of Agentic Behavior / David J. JilkChapter 16: |
Adversarial Machine Learning / Phillip Kuznetsov and Riley Edmunds and Ted Xiao and Humza Iqbal and Raul Puri and Noah Golmant and Shannon ShihChapter 17: |
Value Alignment via Tractable Preference Distance / Andrea Loreggia and Nicholas Mattei and Francesca Rossi and K. Brent VenableChapter 18: |
A Rationally Addicted Artificial Superintelligence / James D. MillerChapter 19: |
On the Security of Robotic Applications Using ROS / David Portugal and Miguel A. Santos and Samuel Pereira and Micael S. CouceiroChapter 20: |
Social Choice and the Value Alignment Problem / Mahendra PrasadChapter 21: |
Disjunctive Scenarios of Catastrophic AI Risk / Kaj SotalaChapter 22: |
Offensive Realism and the Insecure Structure of the International System: Artificial Intelligence and Global Hegemony / Maurizio TinnirelloChapter 23: |
Superintelligence and the Future of Governance: On Prioritizing the Control Problem at the End of History / Phil TorresChapter 24: |
Military AI as a Convergent Goal of Self-Improving AI / Alexey Turchin and David DenkenbergerChapter 25: |
A Value-Sensitive Design Approach to Intelligent Agents / Steven Umbrello and Angelo F. De BellisChapter 26: |
Consequentialism, Deontology, and Artificial Intelligence Safely / Mark WalkerChapter 27: |
Smart Machines ARE a Threat to Humanity / Kevin WarwickChapter 28: |
Index |
Preface: Introduction to AI Safety and Security |
Acknowledgments |
Editor |