Table of Contents

Introduction to AI Safety, Ethics and Society

0.1

Preface

Read Section
0.1
Preface
Read
Section

1.1

Overview of Catastrophic AI Risks

Read Section
1.1
Overview of Catastrophic AI Risks
Read
Section

1.2

Malicious Use

Read Section
1.2
Malicious Use
Read
Section

1.3

AI Race

Read Section
1.3
AI Race
Read
Section

1.4

Organizational Risks

Read Section
1.4
Organizational Risks
Read
Section

1.5

Rogue AIs

Read Section
1.5
Rogue AIs
Read
Section

1.6

Discussion of Connections Between Risks

Read Section
1.6
Discussion of Connections Between Risks
Read
Section

2.1

AI Fundamentals

Read Section
2.1
AI Fundamentals
Read
Section

2.2

Artificial Intelligence & Machine Learning

Read Section
2.2
Artificial Intelligence & Machine Learning
Read
Section

2.3

Deep Learning

Read Section
2.3
Deep Learning
Read
Section

2.4

Scaling Laws

Read Section
2.4
Scaling Laws
Read
Section

2.5

Conclusion

Read Section
2.5
Conclusion
Read
Section

3.1

Single Agent Safety

Read Section
3.1
Single Agent Safety
Read
Section

3.2

Monitoring

Read Section
3.2
Monitoring
Read
Section

3.3

Robustness

Read Section
3.3
Robustness
Read
Section

3.4

Alignment

Read Section
3.4
Alignment
Read
Section

3.5

Systemic Safety

Read Section
3.5
Systemic Safety
Read
Section

3.6

Safety and General Capabilities

Read Section
3.6
Safety and General Capabilities
Read
Section

3.7

Conclusion

Read Section
3.7
Conclusion
Read
Section

4.1

Safety Engineering

Read Section
4.1
Safety Engineering
Read
Section

4.2

Risk Decomposition

Read Section
4.2
Risk Decomposition
Read
Section

4.3

Nines of Reliability

Read Section
4.3
Nines of Reliability
Read
Section

4.4

Safe Design Principles

Read Section
4.4
Safe Design Principles
Read
Section

4.5

Component Failure Accident Models and Methods

Read Section
4.5
Component Failure Accident Models and Methods
Read
Section

4.6

Systemic Factors

Read Section
4.6
Systemic Factors
Read
Section

4.7

Tail Events and Black Swans

Read Section
4.7
Tail Events and Black Swans
Read
Section

4.8

Conclusion

Read Section
4.8
Conclusion
Read
Section

5.1

Complex Systems

Read Section
5.1
Complex Systems
Read
Section

5.2

Introduction to Complex Systems

Read Section
5.2
Introduction to Complex Systems
Read
Section

5.3

Complex Systems for AI Safety

Read Section
5.3
Complex Systems for AI Safety
Read
Section

5.4

Conclusion

Read Section
5.4
Conclusion
Read
Section

6.1

Beneficial AI and Machine Ethics

Read Section
6.1
Beneficial AI and Machine Ethics
Read
Section

6.3

Fairness

Read Section
6.3
Fairness
Read
Section

6.4

The Economic Engine

Read Section
6.4
The Economic Engine
Read
Section

6.5

Wellbeing

Read Section
6.5
Wellbeing
Read
Section

6.6

Preferences

Read Section
6.6
Preferences
Read
Section

6.7

Happiness

Read Section
6.7
Happiness
Read
Section

6.8

Social Welfare Functions

Read Section
6.8
Social Welfare Functions
Read
Section

6.9

Moral Uncertainty

Read Section
6.9
Moral Uncertainty
Read
Section

7.1

Collective Action Problems

Read Section
7.1
Collective Action Problems
Read
Section

7.2

Game Theory

Read Section
7.2
Game Theory
Read
Section

7.3

Cooperation

Read Section
7.3
Cooperation
Read
Section

7.4

Conflict

Read Section
7.4
Conflict
Read
Section

7.5

Evolutionary Pressures

Read Section
7.5
Evolutionary Pressures
Read
Section

7.6

Conclusion

Read Section
7.6
Conclusion
Read
Section

8.1

Governance

Read Section
8.1
Governance
Read
Section

8.2

Timelines

Read Section
8.2
Timelines
Read
Section

8.3

Distribution

Read Section
8.3
Distribution
Read
Section

8.4

Compute Governance

Read Section
8.4
Compute Governance
Read
Section

8.5

Corporate Governance

Read Section
8.5
Corporate Governance
Read
Section

8.6

National Governance

Read Section
8.6
National Governance
Read
Section

8.7

International Governance

Read Section
8.7
International Governance
Read
Section

8.8

Conclusion

Read Section
8.8
Conclusion
Read
Section

9.1

Acknowledgements

Read Section
9.1
Acknowledgements
Read
Section