Skip to main content
Thumbnail for The alignment problem : how can machines learn human values?

The alignment problem : how can machines learn human values?

Christian, Brian, 1984-2021
Books
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 book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics.
Author:
Imprint:
London : Atlantic Books, 2021.
Collation:
x, 476 pages ; 20 cm
Notes:
Originally published: New York: W.W. Norton & Company, Inc., 2021.Includes bibliographical references and index.
Audience:
Specialized.
ISBN:
9781786494337 (pbk. :)
Dewey class:
174.90063
Language:
English
BRN:
2536140
View my active saved list
0 items in my active saved list