• The Alignment Problem

  • Machine Learning and Human Values
  • By: Brian Christian
  • Narrated by: Brian Christian
  • Length: 13 hrs and 33 mins
  • 4.7 out of 5 stars (516 ratings)

1 title per month from Audible’s entire catalog of best sellers, and new releases.
Access a growing selection of included Audible Originals, audiobooks and podcasts.
You will get an email reminder before your trial ends.
Your Premium Plus plan is $14.95 a month after 30 day trial. Cancel anytime.
Buy for $30.09

Buy for $30.09

Pay using card ending in
By confirming your purchase, you agree to Audible's Conditions of Use and Amazon's Privacy Notice. Taxes where applicable.

Publisher's Summary

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.

What listeners say about The Alignment Problem

Average Customer Ratings
Overall
  • 4.5 out of 5 stars
  • 5 Stars
    421
  • 4 Stars
    73
  • 3 Stars
    12
  • 2 Stars
    5
  • 1 Stars
    5
Performance
  • 4.5 out of 5 stars
  • 5 Stars
    322
  • 4 Stars
    88
  • 3 Stars
    8
  • 2 Stars
    3
  • 1 Stars
    2
Story
  • 5 out of 5 stars
  • 5 Stars
    345
  • 4 Stars
    58
  • 3 Stars
    6
  • 2 Stars
    6
  • 1 Stars
    4

Reviews - Please select the tabs below to change the source of reviews.

Sort by:
Filter by:
  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

One of the best outlook books on AI

It was a pleasure listening to the book. It's cosncie enough to suit experts in the field and also offer a broad general overview if you don't know much about the current state of AI. Particularly enjoyes the chapters on RL

4 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    4 out of 5 stars
  • Story
    5 out of 5 stars

Required reading for any AI course

Brian Christian’s holistic approach is approachable to wide audience both technical and otherwise. I read this book while also taking an AI course in college. This book alone easily surpassed what I learned in that course. That’s not even mentioning the methodological and philosophical knowledge picked up from this read. Brian Christian is easily the Malcom Gladwell of computational philosophy.

3 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Clear and thought provoking

I enjoy listening to books read by the author - they are the authority on how to convey the importance of the material. And this is very, very important material and concepts. This is an excellent book,not just for understanding the potential risks and challenges of teaching (and coexisting and thriving with) our intelligent machines, but also as a clear and concise history and background of the development of artificial intelligence algorithms. Please read/listen to it- it is the responsibility of an informed citizenry to become familiar with these issues.

l had read books about the dangers of bias in AI applications, and indeed that is explained here as well (with a clearer technical background than most of those other books). But this book goes beyond these cautionary cases to explain, clearly, the root challenges that can lead to biases (and much greater disasters) and the likely pathways to solutions. These pathways are developed via well-explained explorations of machine epistemological theories and learning mechanisms, building from social, psychological and in some cases neurological concepts, to computational ideas.

This book is already helping me to add new and forward-looking concepts to the university course I teach on risk assessment in engineered systems, as well as a course I co-teach with faculty from humanities disciplines on the nature of knowledge. Thank you!

2 people found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

An amazing look into decision making of human and computers

I was expecting a book on machine learning and computer ethics with a tale of interesting examples. What I got was far more insight into the learning biological machine that we as humans are. It did touch on the mistakes of ML training and how techniques have developed so for those worried it wouldn’t cover that it does - in not overly technical language. I highly recommend it though as it weaves in neuro-physiology and psychological in such an interesting way. A great read for all.

1 person found this helpful

  • Overall
    2 out of 5 stars
  • Performance
    2 out of 5 stars
  • Story
    2 out of 5 stars

Too much to process

Brought this book after listening to some good reads from Brian Christian. But this was way below my expectation. I could not complete it.

1 person found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

Must read/listen

The book dives deep into AI and machine learning. Excellent story, excellently written. In some ways it is humanity's most pressing topic.

1 person found this helpful

  • Overall
    4 out of 5 stars
  • Performance
    4 out of 5 stars
  • Story
    4 out of 5 stars

Interesting overall

I liked the subject of the book. I also liked the ideas and stories shared in it.

However, the book ultimately came across as a summarization of research over the last 100 years related to machine learning and artificial intelligence -- instead of a what I expected to be an in depth description of the potential severity of the "alignment problem" in a modern or future context.

1 person found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

I am a huge fan of Brian Christian.

I am a huge fan of Brian Christian. So all my reviews will be biased. :)

1 person found this helpful

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

One of the best books on alignment problem

Insightful, clear, and beautifully one of best written books in this field! Thank you for making this complex subject such an amusing and fascinating subject

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars

My favorite book of 2022!

This is the most intellectually engaging book on artificial intelligence I've read so far... My favorite book of 2022 thus far! I highly recommend

Sort by:
Filter by:
  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Rene
  • Rene
  • 04-13-22

Better than expected

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

  • Overall
    1 out of 5 stars
  • Performance
    1 out of 5 stars
  • Story
    2 out of 5 stars
Profile Image for Nigel Warburton
  • Nigel Warburton
  • 10-15-21

Learnt 12% of what AI A Guide For Humans offered

Take quotes from interviewees + same old AlphaZero amazements + assumptions that everything is fungible with code/maths + hype narratives about just needing to scale these into generality + Gladwellesque padding like 'It was a chill Chicago day and [insert AI luminary name] was about to discuss logic and neural networks' is the recipe for this book. I found it a waste of time and much recommend Melanie Mitchell's book AI A Guide For Thinking Humans instead. For addressing societal issues Virginia Eubank's Automating Inequality is also great albeit a winding narrative. Or even The Atlas of AI for a more braodswept 'material culture' account.

  • Overall
    4 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    4 out of 5 stars
Profile Image for Scott Sampson
  • Scott Sampson
  • 09-30-21

history of ML

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

  • Overall
    5 out of 5 stars
Profile Image for David Mears
  • David Mears
  • 06-08-21

5 stars because I want to relisten

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

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for Anonymous User
  • Anonymous User
  • 04-13-21

Absolutely Fantastic!

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.

  • Overall
    5 out of 5 stars
  • Performance
    5 out of 5 stars
  • Story
    5 out of 5 stars
Profile Image for C Vernon
  • C Vernon
  • 10-17-20

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

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.