One gift, endless possibilities
    Buy new:
    €122.18
    FREE delivery 17 - 22 November. Details
    Usually dispatched within 7 to 8 days
    Dispatches from
    ErgodeBooks Ships From USA
    Returns
    Returnable if requested within 14 days of receipt.
    Payment
    Secure transaction
    €122.18
    Prices for items sold by Amazon include VAT. Depending on your delivery address, VAT may vary at Checkout. For other items, please see details.
    FREE delivery 17 - 22 November. Details
    Usually dispatched within 7 to 8 days
    €122.18 () Includes selected options. Includes initial monthly payment and selected options. Details
    Price
    Subtotal
    €122.18
    Subtotal
    Initial payment breakdown
    Delivery cost, delivery date and order total (including tax) shown at checkout.
    Dispatches from
    ErgodeBooks Ships From USA
    ErgodeBooks Ships From USA
    Dispatches from
    ErgodeBooks Ships From USA
    Returns
    Returnable if requested within 14 days of receipt.
    Returnable if requested within 14 days of receipt.
    Item can be returned for a refund if requested within 14 days of receipt unless seller’s return policy specifies more favourable return conditions. For seller’s return policy click on seller’s name located in the “Sold by” section”.
    Payment
    Secure transaction
    Your transaction is secure
    We work hard to protect your security and privacy. Our payment security system encrypts your information during transmission. We don’t share your credit card details with third-party sellers, and we don’t sell your information to others. Learn more
    €23.40
    Von Europas Nr.1 für gebrauchte Bücher und Medien. Gebrauchter Artikel mit minimalen Gebrauchsspuren, unbeschädigten Seiten ohne Markierungen, intaktem Umschlag/Zubehör, falls enthalten. Leichte Gebrauchsspuren auf dem Umschlag und dem Begleitheft sind möglich, aber es sind keine Markierungen oder Anmerkungen vorhanden. Von Europas Nr.1 für gebrauchte Bücher und Medien. Gebrauchter Artikel mit minimalen Gebrauchsspuren, unbeschädigten Seiten ohne Markierungen, intaktem Umschlag/Zubehör, falls enthalten. Leichte Gebrauchsspuren auf dem Umschlag und dem Begleitheft sind möglich, aber es sind keine Markierungen oder Anmerkungen vorhanden. See less
    €3 delivery 29 October - 3 November. Details
    Only 2 left in stock.
    €122.18 () Includes selected options. Includes initial monthly payment and selected options. Details
    Price
    Subtotal
    €122.18
    Subtotal
    Initial payment breakdown
    Delivery cost, delivery date and order total (including tax) shown at checkout.
    Dispatched from and sold by MEDIMOPS. For further information, company details, terms and conditions, and cancellation rights, please click on the seller's name.
    Kindle app logo image

    Download the free Kindle app and start reading Kindle books instantly on your smartphone, tablet or computer – no Kindle device required.

    Read instantly on your browser with Kindle for Web.

    Using your mobile phone camera - scan the code below and download the Kindle app.

    QR code to download the Kindle App

    Follow the author

    Something went wrong. Please try your request again later.

    The Alignment Problem: Machine Learning and Human Values Hardcover – 6 Oct. 2020

    4.6 out of 5 stars 627 ratings

    {"desktop_buybox_group_1":[{"displayPrice":"€122.18","priceAmount":122.18,"currencySymbol":"€","integerValue":"122","decimalSeparator":".","fractionalValue":"18","symbolPosition":"left","hasSpace":false,"showFractionalPartIfEmpty":true,"offerListingId":"hcGrvq7Rur7cAzeXIfEMa9tJzRzCHdwlfUTnDtYK5CL5oobzZTw26FD8rDCOyoaGJhLqoeXPtMdxIR%2FwkEPQWoWQB96ddFSuGoJ%2Bld63ov7jgQxVvWPOMWXhVOFJPwxn%2Fro2ZGx5EyxMwcQHJ%2F76rWV8eGtJA3vUHV3%2FXuvkR4F8W%2F5II7ewqQ%3D%3D","locale":"en-GB","buyingOptionType":"NEW","aapiBuyingOptionIndex":0}, {"displayPrice":"€23.40","priceAmount":23.40,"currencySymbol":"€","integerValue":"23","decimalSeparator":".","fractionalValue":"40","symbolPosition":"left","hasSpace":false,"showFractionalPartIfEmpty":true,"offerListingId":"hcGrvq7Rur7cAzeXIfEMa9tJzRzCHdwlBUoZA12MscK3iGtvZZH4SM7wZ2yPwKLnMLKDSKn4DLzgwagVgFdQbEYmxVw45OqCjSbN%2BTBX3WxyK1nL3ZQeJDfA1X%2BKLx%2Fv%2BiSvcg1E5qvE6XyneOliaQmIGQh6Dutjg9lQK1LYoPrbIm4nRsBevw%3D%3D","locale":"en-GB","buyingOptionType":"USED","aapiBuyingOptionIndex":1}]}

    Purchase options and add-ons

    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. Readers 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

    Product details

    • Publisher ‏ : ‎ W W Norton & Co Inc
    • Publication date ‏ : ‎ 6 Oct. 2020
    • Language ‏ : ‎ English
    • Print length ‏ : ‎ 356 pages
    • ISBN-10 ‏ : ‎ 0393635821
    • ISBN-13 ‏ : ‎ 978-0393635829
    • Dimensions ‏ : ‎ 16.51 x 4.32 x 24.38 cm
    • Best Sellers Rank: 2,403,743 in Books (See Top 100 in Books)
    • Customer reviews:
      4.6 out of 5 stars 627 ratings

    About the author

    Follow authors to get new release updates, plus improved recommendations.
    Brian Christian
    Brief content visible, double tap to read full content.
    Full content visible, double tap to read brief content.

    Brian Christian is the author of the acclaimed bestsellers "The Most Human Human," a New York Times editors’ choice and a New Yorker favorite book of the year, and "Algorithms to Live By" (with Tom Griffiths), a #1 Audible bestseller, Amazon best science book of the year and MIT Technology Review best book of the year.

    Christian’s writing has appeared in The New Yorker, The Atlantic, Wired, and The Wall Street Journal, as well as peer-reviewed journals such as Cognitive Science. He has been featured on The Daily Show and Radiolab, and has lectured at Google, Facebook, Microsoft, the Santa Fe Institute, and the London School of Economics. His work has won several awards, including publication in Best American Science & Nature Writing, and has been translated into nineteen languages.

    Christian holds degrees in computer science, philosophy, and poetry from Brown University and the University of Washington. A Visiting Scholar at the University of California, Berkeley, he lives in San Francisco.

    Customer reviews

    4.6 out of 5 stars
    627 global ratings

    Top reviews from Germany

    • Reviewed in Germany on 26 March 2023
      Format: HardcoverVerified Purchase
      I got progressively more interested, the further I advanced in the book.

      Also the hardcover is light blue, which has an appeal to me.
      One person found this helpful
      Report
    • Reviewed in Germany on 5 July 2023
      Format: Audiobook
      I liked this too 10 classic about AI a lot. It’s very detailed about the beginnings of AI and the issues mankind will have to deal with. A must read.
    • Reviewed in Germany on 30 June 2021
      Format: HardcoverVerified Purchase
      Zugegebenermaßen bin ich alles andere als ein Fachmann auf den Gebieten von Künstlicher Intelligenz (KI) und Machine Learning (ML). Doch gerade deshalb war ich dankbar für dieses Buch, das sich dezidiert (auch) an Nicht-Experten wendet und deshalb auch weitestgehend auf Fachterminologien und (mathematisch) formalisierte Darstellungen verzichtet.

      Leute, die weit besser als ich in diesen Thematiken und Forschungsfeldern bewandert sind, haben mir bestätigt, dass der Autor dieses Buches, Brian Christian, über einen großen Sachverstand verfüge und dass die Zugänglichkeit seiner Darstellungen nicht auf Kosten der sachlichen Korrektheit ginge. Alles in allem also wohl eines jener profunden Sachbücher, für die man den englischsprachigen Kulturraum immer noch beneiden kann.

      Das im Titel angesprochene Ausrichtungs- oder Orientierungsproblem eräutert bereits der Untertitel weitgehend: Es geht darum, inwieweit auf ML-basierte KI-Systeme im Einklang mit menschlichen Werten stehen bzw. in Widerspruch zu ihnen geraten können oder es bereits getan haben. Konkrete Probleme reichen von Bilderkennungs- bzw. –klassifikationssystemen mit ›gender bias‹ oder ›racial bias‹ bis hin zum Einsatz von KI-basierten Systemen zur Bestimmung der Rückfallwahrscheinlichkeit von Straftätern, über deren Bewährung entschieden werden soll. Das Buch enthält zahlreiche weitere Beispiele des Einsatzes von ML in unterschiedlichen gesellschaftlichen Bereichen.

      Christian nimmt eine mittlere Position ein zwischen einer pessimistischen Technikdystopie und einer optimistischen KI-Euphorie. Akribisch werden die konkreten Probleme benannt und auf ihre Ursachen hin untersucht. Vieles gebe, so Christian, Anlass zur Skepsis und zur Sorge, doch gleichzeitig betont er die grundsätzliche technische Beherrschbarkeit der Probleme. Um Letzteres zu demonstrieren, taucht er tief in die aktuelle Forschungslandschaft ein und zeichnet erstaunliche Entwicklungslinien nach, die bisweilen wissenschaftshistorisch recht weit ausgreifen. Erstaunlich ist unter anderem, wie sich unterschiedliche Disziplinen (wechselseitig) beeinflussen und um welche Disziplinen es sich dabei handelt. Dass sich Informatiker und Ingenieure, die mit der ML-Entwicklung befasst sind, intensiv für die Ergebnisse von Primatenforschung, Entwicklungspsychologie oder Erziehungswissenschaft interessieren könnten, hätte man vor wenigen Jahrzehnten wohl nicht prognostiziert.

      Ich habe das Buch mit sehr großem Gewinn gelesen. Was man monieren kann, ist zum einen Christians Hang, manchmal in die journalistische Trickkiste zu greifen, um Erzählungen ›spannend‹ zu gestalten. Doch das scheint mir verzeihlich, weil es nicht auf Kosten des Wahrheitsgehalts geht. Problematischer erscheint mir, dass der Autor allzu sehr ausblendet, dass ein erheblicher Teil der KI- bzw. ML-Forschung in den Institutionen der großen Tech-Konzerne stattfindet und man sich durchaus fragen sollte, inwieweit dieses Faktum – KI/ML-Forschung am Tropf von Konzernen mit Profitmaximierungsinteressen – ein ganz eigenes ›alignment problem‹ mit sich bringt.
      Report
    • Reviewed in Germany on 7 January 2021
      Format: Audiobook
      Solid overview on the history of many of today's central ideas in ML and RL. Christian connects this well to today's and tomorrows challenges. I recommend this to any person wanting to get an overview on what research is important right now, either to fund it or of course to contribute to it directly.

    Top reviews from other countries

    • William Maddox
      5.0 out of 5 stars Understanding AI
      Reviewed in the United States on 20 September 2025
      Format: Kindle EditionVerified Purchase
      A comprehensive and fairly deep review of AI to date. Needs to be read slowly to appreciate. I am somewhat more optimistic about the future of AI after reading this book.
    • Emidio Stani
      5.0 out of 5 stars Immersive flow in the continuous research of the alignment
      Reviewed in France on 1 July 2022
      Format: Kindle EditionVerified Purchase
      This book deals with the alignment problem analyzed in different perspectives over time while scaling out its abstraction and complexity.

      Being an IT person, I am fascinated by what machine learning has reached so far and what yet needs to be done for AI to be integrated in our society.

      The book does not require technical knowledge and I recommend it to anyone interested in machine learning, data engineering but also in policy making around AI.

      I like the style of the book, in part historical with a lot of references, and having for me the right speed of reading without stopping by too much on a topic.
    • Georgina
      5.0 out of 5 stars Good introductory text to the issues
      Reviewed in Australia on 23 April 2021
      Trying to understand alignment of human values and machine learning
      It’s a great eye opener and easy to understand - covers a lot of ground
    • MPH
      5.0 out of 5 stars Great and fast
      Reviewed in Canada on 3 September 2025
      Format: PaperbackVerified Purchase
      Great
    • bnjasim
      1.0 out of 5 stars Philosophy is useless anyway!
      Reviewed in India on 11 November 2024
      Format: PaperbackVerified Purchase
      Don't read a book, rather DO something. Philosophy is useless!