AI Safety, Alignment & Existential Risk
The Alignment Problem: Machine Learning and Human Values
Brian Christian · 2020 · W. W. Norton
Traces the technical and philosophical history of trying to make machine-learning systems behave the way their builders intend.
Cover image: Open Library.
Summary
“When the systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem.”
This book explores the issues that arise when artificial intelligence systems, particularly machine learning, are deployed. It describes how these data-trained systems increasingly make decisions for humans, raising concerns about their behavior. The author explains that when these systems do not perform as intended, it can lead to ethical and existential risks, a phenomenon termed "the alignment problem." The book investigates the growth of machine learning, the challenges it presents, and efforts by researchers to address these issues before potential dangers escalate.
Summary based on the publisher's page ↗
Read it
This book isn't free to read online. You can borrow it free with a library card, or buy it from the publisher.
About the author
Brian Christian
Brian Christian is an author whose books have been translated into multiple languages.
Source: Publisher page ↗