Alignment Problem, The: How Can Machines Learn Human Values?

Brian Christian

Format: Hardback

Publisher: Atlantic Books

Published: 21st Jan '21

£20.00

How do we prevent AI working against us?

Gift Wrapping

During lockdown most books will come direct from our distributors to you, and so we are unable to offer Gift Wrapping currently. However, normally you can have your books hand wrapped in our bespoke tissue paper with our kite sticker to tie it all together. We’ll bring this service back as soon as we can!

Description

‘Vital reading. This is the book on artificial intelligence we need right now.’ Mike Krieger, cofounder of InstagramArtificial 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.

Additional information

Weight 0.915 kg
Dimensions 47 × 165 × 242 mm
Page Count 496