The Alignment Problem: Machine Learning and Human Values by Brian Christian

The Alignment Problem: Machine Learning and Human Values

Brian Christian

496 pages first pub 2020 (editions)

nonfiction science informative medium-paced

Description

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 decisi...

Read more

Community Reviews Summary of 71 reviews

Moods

informative 100%
challenging 42%
hopeful 42%
reflective 35%
inspiring 21%
emotional 7%
funny 7%
relaxing 7%

Pace

medium 71%
slow 28%

Average rating

4.49

See all reviews...

Content Warnings

This book doesn't have any content warnings yet!

If you're the author of this book and want to add author-approved content warnings, please email us at [email protected] to request the content warning form.