The Alignment Problem: How Can Artificial Intelligence Learn Human Values?

Christian, Brian

ISBN 10: 1786494337 / ISBN 13: 9781786494337

Published by Atlantic Books, 2021

About this Item

main edition. 496 pages. 7.80x5.08x1.34 inches. In Stock.

Seller Inventory # __1786494337

Bibliographic Details

• Title: The Alignment Problem: How Can Artificial Intelligence Learn Human Values?
• Publisher: Atlantic Books
• Publication Date: 2021
• Language: English
• ISBN 10: 1786494337
• ISBN 13: 9781786494337
• Binding: Paperback
• Condition: Brand New
• Weight: 0.46 kilograms

About this title

Synopsis

How do we prevent AI working against us?

'Vital reading. This is the book on artificial intelligence we need right now.' Mike Krieger, cofounder of Instagram

Artificial intelligence is rapidly dominating every aspect of our modern lives influencing the news we consume, whether we get a mortgage, and even which friends wish us happy birthday. But as algorithms make ever more decisions on our behalf, how do we ensure they do what we want? And fairly?

This conundrum - dubbed 'The Alignment Problem' by experts - is the subject of this timely and important book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, bestselling author Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics. If we stand by, we face a future with unregulated algorithms that propagate our biases - and worse - violate our most sacred values. Urgent and fascinating, this is an accessible primer to the most important issue facing AI researchers today.