Table of Contents

Introduction to AI Safety, Ethics and Society

0.1

Preface

0.1

Preface

1.1

Overview of Catastrophic AI Risks

1.1

Overview of Catastrophic AI Risks

1.2

Malicious Use

1.2

Malicious Use

1.3

AI Race

1.3

AI Race

1.4

Organizational Risks

1.4

Organizational Risks

1.5

Rogue AIs

1.5

Rogue AIs

1.6

Discussion of Connections Between Risks

1.6

Discussion of Connections Between Risks

2.1

AI Fundamentals

2.1

AI Fundamentals

2.2

Artificial Intelligence & Machine Learning

2.2

Artificial Intelligence & Machine Learning

2.3

Deep Learning

2.3

Deep Learning

2.4

Scaling Laws

2.4

Scaling Laws

2.5

Speed of AI Development

2.5

Speed of AI Development

2.6

AI Fundamentals Conclusion

2.6

AI Fundamentals Conclusion

3.1

Single Agent Safety

3.1

Single Agent Safety

3.2

Monitoring

3.2

Monitoring

3.3

Robustness

3.3

Robustness

3.4

Alignment

3.4

Alignment

3.5

Systemic Safety

3.5

Systemic Safety

3.6

Safety and General Capabilities

3.6

Safety and General Capabilities

3.7

Conclusion

3.7

Conclusion

4.1

Safety Engineering

4.1

Safety Engineering

4.2

Risk Decomposition

4.2

Risk Decomposition

4.3

Nines of Reliability

4.3

Nines of Reliability

4.4

Safe Design Principles

4.4

Safe Design Principles

4.5

Component Failure Accident Models and Methods

4.5

Component Failure Accident Models and Methods

4.6

Systemic Factors

4.6

Systemic Factors

4.7

Tail Events and Black Swans

4.7

Tail Events and Black Swans

4.8

Conclusion

4.8

Conclusion

5.1

Complex Systems

5.1

Complex Systems

5.2

Introduction to Complex Systems

5.2

Introduction to Complex Systems

5.3

Complex Systems for AI Safety

5.3

Complex Systems for AI Safety

5.4

Conclusion

5.4

Conclusion

6.1

Beneficial AI and Machine Ethics

6.1

Beneficial AI and Machine Ethics

6.2

Law

6.2

Law

6.3

Fairness

6.3

Fairness

6.4

The Economic Engine

6.4

The Economic Engine

6.5

Wellbeing

6.5

Wellbeing

6.6

Preferences

6.6

Preferences

6.7

Happiness

6.7

Happiness

6.8

Social Welfare Functions

6.8

Social Welfare Functions

6.9

Moral Uncertainty

6.9

Moral Uncertainty

7.1

Collective Action Problems

7.1

Collective Action Problems

7.2

Game Theory

7.2

Game Theory

7.3

Cooperation

7.3

Cooperation

7.4

Conflict

7.4

Conflict

7.5

Evolutionary Pressures

7.5

Evolutionary Pressures

7.6

Conclusion

7.6

Conclusion

8.1

Governance

8.1

Governance

8.2

Growth

8.2

Growth

8.3

Distribution

8.3

Distribution

8.4

Corporate Governance

8.4

Corporate Governance

8.5

National Governance

8.5

National Governance

8.6

International Governance

8.6

International Governance

8.7

Compute Governance

8.7

Compute Governance

8.8

Conclusion

8.8

Conclusion

9.1

App. A: Normative Ethics

9.1

App. A: Normative Ethics

Citation:
Dan Hendrycks. Introduction to AI Safety, Ethics and Society. Taylor & Francis, (forthcoming). ISBN: 9781032798028. URL: www.aisafetybook.com

Cookies Notice: This website uses cookies to identify pages that are being used most frequently. This helps us analyze data about web page traffic and improve our website. We only use this information for the purpose of statistical analysis and then the data is removed from the system. We do not and will never sell user data. Read more about our cookie policy on our privacy policy. Please contact us if you have any questions.

© 2024 Center for AI Safety

Built by Osborn Design Works