The Alignment Problem: How Can Machines Learn Human Values?

The Alignment Problem: How Can Machines Learn Human Values? image
ISBN-10:

1786494302

ISBN-13:

9781786494306

Author(s): Christian, Brian
Edition: Main
Released: Jan 21, 2021
Publisher: ATLANTIC BOOKS *
Format: Hardcover, 0 pages
to view more data

Description:

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

Low Price Summary






Top Bookstores


























We're an Amazon Associate. We earn from qualifying purchases at Amazon and all stores listed here.

DISCLOSURE: We're an eBay Partner Network affiliate and we earn commissions from purchases you make on eBay via one of the links above.

Want a Better Price Offer?

Set a price alert and get notified when the book starts selling at your price.

Want to Report a Pricing Issue?

Let us know about the pricing issue you've noticed so that we can fix it.