Politics & SocietyScience & Nature
The Alignment Problem
- Pages
- 356
- 8 editions
- First published
- 2020
- 1 language
Join or log in to shelve and rate Free, no password.
Overview
"A jaw-dropping exploration of everything that goes wrong when we build AI systems-and the movement to fix them. Today's "machine-learning" systems, trained by data, are so effective that we've invited them to see and hear for us-and to make decisions on our behalf. But alarm bells are ringing. Systems cull résumés until, years later, we discover that they have inherent gender biases. Algorithms decide bail and parole-and appear to assess black and white defendants differently. We can no longer assume that our mortgage application, or even our medical tests, will be seen by human eyes. And autonomous vehicles on our streets can injure or kill. When systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem. In best-selling author Brian Christian's riveting account, we meet the alignment problem's "first-responders," and learn their ambitious plan to solve it before our hands are completely off the wheel"--Provided by publisher.
Ratings & reviews
Log in to rate or review this book.
No written reviews yet.
Discussions
Talk about this book with other readers.
Log in to start a discussion.
No discussions yet.
Editions
-
Format not known Norton & Company, Incorporated, W. W. 2020 356 pages English ISBN 9780393635836 Open Library
Details & links
- First published
- 2020
- Pages
- 356
- Languages
- Available in 1 language
- Audiobook
- Audiobook edition known
Where to buy this book: see “Buy this book”
More about this book
Read a sample, borrow it or see other editions → openlibrary.org