The Alignment Problem cover art

The Alignment Problem

Machine Learning and Human Values

Preview
Try Premium Plus free
Pick 1 audiobook a month from our unmatched collection - including bestsellers and new releases.
Listen all you want to thousands of included audiobooks, Originals, celeb exclusives, and podcasts.
Access exclusive sales and deals.
£8.99/month after 30 days. Renews automatically. See here for eligibility.

The Alignment Problem

By: Brian Christian
Narrated by: Brian Christian
Try Premium Plus free

£8.99/month after 30 days. Renews automatically. See here for eligibility.

Buy Now for £22.99

Buy Now for £22.99

Confirm Purchase
Pay using card ending in
By completing your purchase, you agree to Audible's Conditions of Use and authorise Audible to charge your designated card or any other card on file. Please see our Privacy Notice, Cookies Notice and Interest-based Ads Notice.
Cancel

About this listen

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. Recent years have seen an eruption of concern as the field of machine learning advances. When the 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.

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 as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.

The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called “artificial intelligence.” They are steadily replacing both human judgment and explicitly programmed software.

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. In a masterful blend of history and on-the-ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Listeners encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they - and we - succeed or fail in solving the alignment problem will be a defining human story.

The Alignment Problem offers an unflinching reckoning with humanity’s biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our culture - and finds a story by turns harrowing and hopeful.

©2020 Brian Christian (P)2020 Brilliance Publishing, Inc., all rights reserved.
Computer Science History & Culture History & Philosophy Machine Theory & Artificial Intelligence Philosophy Science Technology & Society Thought-Provoking

Listeners also enjoyed...

Bernoulli's Fallacy cover art
Most relevant  
Great overview of the current machine learning landscape and importantly how we got here. Useful sections on uncertainty and safety with strong concluding remarks on models in general. The map is not the territory.

Don't think machine learning's important? Read on.

Something went wrong. Please try again in a few minutes.

I've learned a lot about machine learning from this book. The level of detail is excellent whilst remaining accessible and engaging throughout. Well written and well read. Definitely the most interesting book I've listened to in a long time.

Absolutely Fantastic!

Something went wrong. Please try again in a few minutes.

some earlier chapters were skippable. when I relisten ill see which chapters I marked for relistening

5 stars because I want to relisten

Something went wrong. Please try again in a few minutes.

A nice multidisciplinary history of ML with philosophy and psychology as well as comp sci

history of ML

Something went wrong. Please try again in a few minutes.

A short history of AI, machine learning, and reinforcement learning. Touches on the philosophical, ethical, psychological, and political aspects of AI. A must-read for anyone on the cutting edge of tech, or with a casual interest in that.

Excellent

Something went wrong. Please try again in a few minutes.

I loved “Algorithms to Live By” and expected this to be similar in scope but it’s way broader and way deeper. A rich, nuanced history of AI research so far, grounded in the alignment problem.

Exceeds all expectations

Something went wrong. Please try again in a few minutes.

AI is part of our lives now. Read this to understand it. Well written, explains complex topics well.

A must read

Something went wrong. Please try again in a few minutes.

Easy to understand by non experts
Covers many topics and philosophical debates in AI and Real Life

a must read about ai ethics

Something went wrong. Please try again in a few minutes.

This is more about the history of the alignment problem than theorising it, but this is highly instructive.

More of the history than the theory

Something went wrong. Please try again in a few minutes.

Great book that touches on a lot of concepts and some underlying theory, mixed with examples and philosophy

Better than expected

Something went wrong. Please try again in a few minutes.

See more reviews