The Alignment Problem

ebook How Can Machines Learn Human Values?

By Brian Christian

cover image of The Alignment Problem

Sign up to save your library

With an OverDrive account, you can save your favorite libraries for at-a-glance information about availability. Find out more about OverDrive accounts.

   Not today
Libby_app_icon.svg

Find this title in Libby, the library reading app by OverDrive.

app-store-button-en.svg play-store-badge-en.svg
LibbyDevices.png

Search for a digital library with this title

Title found at these libraries:

Loading...
'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.
The Alignment Problem