Home / Humanities / Philosophy / The Alignment Problem: How Can Machines Learn Human Values?

The Alignment Problem: How Can Machines Learn Human Values?

AUTHOR
Price
€18.80
€20.90 -10%
Upon request
Dispatched within 15 - 25 days.

Add to wishlist

How do we prevent AI working against us?

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 Control 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 Al researchers today.
Author: Christian Brian
Publisher: ATLANTIC BOOKS
Pages: 476
ISBN: 9781786494313
Cover: Paperback
Edition Number: 1
Release Year: 2020

Brian Christian is the bestselling author of The Most Human Human, which was named a Wall Street Journal bestseller and a New Yorker favorite book of 2011. His writing has appeared in Wired, The Atlantic, The Wall Street Journal , and The Paris Review, among others. Brian has been a featured guest on The Daily Show with Jon Stewart, The Charlie Rose Show, NPR's Radiolab, and the BBC, and has lectured at Google, Microsoft, SETI, the Santa Fe Institute, the Royal Institution of Great Britain, and the London School of Economics.

You may also like

Newsletter

Subscribe to the newsletter to be the first to receive our new releases and offers
Your account Your wishlist