Book Summary of “Human Compatible”

Introduction

Final stage of human evolution due to intentional enfeeblement and perpetual entertainment (from WALL-E)

Chapter 1. If We Succeed

How Did We Get Here

What Happens Next?

What Went Wrong?

Chapter 2. Intelligence in Humans and Machines

Intelligence

Computers

Intelligent Computers

Chapter 3. How Might AI Progress in The Future?

Chapter 4. Misuses of AI

Surveillance, Persuasion, and Control

Lethal Autonomous Weapon

Eliminating Work as We Know It

Usurping Other Human Roles

Chapter 5. Overly Intelligent AI

The Gorilla Problem

The King Midas Problem

Fear and Greed: Instrumental Goals

Intelligence Explosions

Chapter 6. The Not-So-Great AI Debate

Denial

Deflection

Tribalism

Can’t we just…

The Debate, Restarted

Chapter 7. AI: A Different Approach

Principles for Beneficial Machines

Reasons for Optimism

Reasons for Caution

Chapter 8. Provable Beneficial AI

Mathematical Guarantees

Learning Preferences from Behavior

Assistance Games

Requests and Instructions

Wireheading

Recursive Self-Improvement

Chapter 9. Complications: Us

Different Humans

Many Humans

Nice, Nasty, and Envious Humans

Stupid, Emotional Humans

Do Humans Really Have Preferences?

Chapter 10. Problem Solved?

Beneficial Machines

Governance of AI

Misuse

Enfeeblement and Human Autonomy

Appendix A: Searching for Solutions

Appendix B: Knowledge and Logic

Appendix C: Uncertainty and Probability

Appendix D: Learning From Experience

Hi, I am from the Earth. And you?