188 books
—
142 voters
Goodreads helps you keep track of books you want to read.
Start by marking “The Alignment Problem: Machine Learning and Human Values” as Want to Read:
The Alignment Problem: Machine Learning and Human Values
by
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 a ...more
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 a ...more
Get A Copy
Hardcover, 496 pages
Published
October 6th 2020
by W. W. Norton Company
Friend Reviews
To see what your friends thought of this book,
please sign up.
Reader Q&A
To ask other readers questions about
The Alignment Problem,
please sign up.
Be the first to ask a question about The Alignment Problem
Community Reviews
Showing 1-30
Start your review of The Alignment Problem: Machine Learning and Human Values
The biggest problem in artificial intelligence (AI) is to devise a reward function that gives you the behavior you want, while avoiding side effects or unforseen consequences. This book examines the alignment problem from a number of fascinating perspectives.
This is a fascinating book, full of the implications of AI on philosophy, sociology, and psychology. There are interactions between AI and sociology, psychology in a two-way street. Our understanding of psychology helps to improve AI in num ...more
This is a fascinating book, full of the implications of AI on philosophy, sociology, and psychology. There are interactions between AI and sociology, psychology in a two-way street. Our understanding of psychology helps to improve AI in num ...more
A well researched book on AI safety written to be enjoyed by experts and newbies alike!
This book is the culmination of *four years* of dedicated work and interviews with over 100 world-class experts. The brilliant thing about this book is that it is so information dense and full of interesting anecdotes that people of any level of expertise stand to gain something from it. He’s carefully tuned it so a wide variety of people can enjoy it without getting bored or overwhelmed.
This book covers the ...more
This book is the culmination of *four years* of dedicated work and interviews with over 100 world-class experts. The brilliant thing about this book is that it is so information dense and full of interesting anecdotes that people of any level of expertise stand to gain something from it. He’s carefully tuned it so a wide variety of people can enjoy it without getting bored or overwhelmed.
This book covers the ...more
'The Alignment Problem: Machine Learning and Human Values' by Brian Christian is a very interesting overview about the issues in developing useful computing machines. I found it very comprehensive and yet easy to understand. However, it does give me pause in any fantasy I may have had over the Singularity occurring.
The main goal of machine learning is teaching the computer to see, hear and do things without human oversight, and to learn to categorize and make inferences on inputs like humans, an ...more
The main goal of machine learning is teaching the computer to see, hear and do things without human oversight, and to learn to categorize and make inferences on inputs like humans, an ...more
My AI's perception as a superior technology which should be embraced unquestionably almost reverentially was successfully challenged after going through the numerous examples in this book. By the end of the book, I was convinced that AI is better and will get even more efficient as compared to human ingenuity, but needs to be constantly tested for questioned, any AI system depends upon the quality of the training data and the type of algorithms employed to solve any problem.
...more
There is a great book trapped inside this good book, waiting for a skillful editor to carve it out. The author did vast research in multiple domains and it seems like he could neither build a cohesive narration that could connect all of it nor leave anything out.
This book is probably the best intro to machine learning space for a non-engineer I've read. It presents its history, challenges, what can be done, and what can't be done (yet). It's both accessible and substantive, presenting complex id ...more
This book is probably the best intro to machine learning space for a non-engineer I've read. It presents its history, challenges, what can be done, and what can't be done (yet). It's both accessible and substantive, presenting complex id ...more
Really nice introduction to AI & the alignment problem - Christian gives a great overview over some bigger trends in ML (e.g. curiosity, imitation learning, transparency) and the history of AI, often connecting it to insights from cognitive science, which really enriched the book, speaking as a human and cognitive scientist. I wonder what more refined thinkers on the future of AI think of the book*, but I found that it connects nicely to many of the looming challenges with building AI systems th
...more
Brilliant reading that covers numerous aspects concerning learning and teaching of both humans and programs, a bit of practical ethics and filosofy all woven together under one topic that is the development of machine learning programs. It demonstrates perfectly how in order to teach you must first understand the subject and how you learn more as you teach it to someone.
If you have any interest in AI, its safety and real ethical problems or the history of how machine learning has developed hand ...more
If you have any interest in AI, its safety and real ethical problems or the history of how machine learning has developed hand ...more
It’s a good overview of a brief moment in technological advancement.
There’s a common thread in machine learning (AI, I'm going to use these terms interchangeably) research that “oh man we got to be really careful and think about how we set up these machines because they may end the world as we know it.” Thankfully this seems to be counterbalanced by the actual empirical research being done, which mostly seems like a lot of fun tricks. Similar to impressing people with your ability to open a jar ...more
There’s a common thread in machine learning (AI, I'm going to use these terms interchangeably) research that “oh man we got to be really careful and think about how we set up these machines because they may end the world as we know it.” Thankfully this seems to be counterbalanced by the actual empirical research being done, which mostly seems like a lot of fun tricks. Similar to impressing people with your ability to open a jar ...more
tldr worth a read !
Really solid overview of the research field that is typically referred to as "responsible AI" (fairness, explainability, deep learning, language models, RL) -- this book is therefore unique from other tech x society books in the sense that it is highly technical but also [I think] accessible, though I'm probably not the best person to judge that. I'd consider myself pretty familiar with the academic work that this book describes, but Christian packages a really nice story for ...more
Really solid overview of the research field that is typically referred to as "responsible AI" (fairness, explainability, deep learning, language models, RL) -- this book is therefore unique from other tech x society books in the sense that it is highly technical but also [I think] accessible, though I'm probably not the best person to judge that. I'd consider myself pretty familiar with the academic work that this book describes, but Christian packages a really nice story for ...more
Strongly recommended if you're into Machine Learning. The first third of the book is accessible to all readers, but the rest of it is more enjoyable if you have some basic idea of how ML works.
Had some fascinating takeaways beyond machine learning that can be applied to decision making. My favorites were:
1. Simpler models tend to be the most generalizable. For example, when modeling the self-reported happiness of a couple, a simple metric (# of times they had sex - # of times they fought) was fa ...more
Had some fascinating takeaways beyond machine learning that can be applied to decision making. My favorites were:
1. Simpler models tend to be the most generalizable. For example, when modeling the self-reported happiness of a couple, a simple metric (# of times they had sex - # of times they fought) was fa ...more
Very nice! Superb technical writing and enjoyable (and I say this as someone who isn't particularly into science writing).
I was somewhat familiar with part 1 of the book (on fairness and transparency) from my work and studies, and can confidently say that the author has done a fabulous job of distilling the current understanding on these topics with nuance. This is a real feat when the subject is so complex. Even though I knew about these topics from before, the book still deepened my understand ...more
I was somewhat familiar with part 1 of the book (on fairness and transparency) from my work and studies, and can confidently say that the author has done a fabulous job of distilling the current understanding on these topics with nuance. This is a real feat when the subject is so complex. Even though I knew about these topics from before, the book still deepened my understand ...more
There are already dozens of excellent reviews summarizing the content of this book so there's no need for me to write anything. This book is important and useful for anyone who wants to get a fairly deep layman's understanding of the problems inherent with machine learning AI development. These problems are difficult, but it is extremly important that they be confronted head on since they can literaly be a matter of life and death. Christian has written an excellent book, one I think should be w
...more
This book is an excellent read for DS professionals and those just wondering about machine learning's origins, limitations, and prospects. There is nothing particularly mind-blowing or too technical. Still, some cases and stories backtracing the evolution of things one otherwise takes for granted nowadays are fabulous—many references to cognitive scientists, human biology and anthropology studies, which I loved the most. Worth reading indeed.
...more
This is an EXCELLENT book about one of the most important problems of our times. I was already fairly familiar with the alignment problem and the technical side of things, but I still got a lot out of it, especially in the earlier sections about the history of AI and of reinforcement learning. I also really liked the deeper links he drew between reinforcement learning, and how we make decisions.
This book had the rare delight of being half about unfamiliar topics, and half about topics I knew wel ...more
This book had the rare delight of being half about unfamiliar topics, and half about topics I knew wel ...more
May 04, 2021
Alex Railean
rated it
it was amazing
Shelves:
computers,
programming,
ai,
audio,
intelligence,
behaviour,
philosophy,
research,
ethics,
reference
This is an excellent book, it is like a survey paper written in very understandable terms.
ßßßßßßßßßßßßßßßßßßßß notes for personal üse
- word2vec example: doctor - man + woman = nurse
- and so it went, with many examples placing women in household contexts
- perceptron
- - bias in the camera itself, color calibration [could not adequately represent black people]
- Kodak employee and model, Shirley Page
- - "Shirley card" - the same principle applies to any data set used for training
- bias propagate ...more
ßßßßßßßßßßßßßßßßßßßß notes for personal üse
- word2vec example: doctor - man + woman = nurse
- and so it went, with many examples placing women in household contexts
- perceptron
- - bias in the camera itself, color calibration [could not adequately represent black people]
- Kodak employee and model, Shirley Page
- - "Shirley card" - the same principle applies to any data set used for training
- bias propagate ...more
The Alignment Problem was phenomenal and I would highly recommend it to anyone who is even remotely interested in machine learning, how algorithms shape modern life, or even the parallels between psychology and artificial intelligence. My main background in AI is from an extensive article on Wait But Why, which explained much more of the future cases of what artificial general intelligence would mean for our society. The Alignment Problem, however, goes into the nuts and bolts of both the histor
...more
If you’re plugged into the artificial intelligence world, you’ll immediately recognize the title. The “alignment problem” in AI is ensuring that artificial agents’ goals align with the goals of humans. That’s not an easy problem to solve, as Christian details through countless examples. The “reward function” for AI programs is often misspecified.
Early in the book Christian tells the story of AI researcher Dario Amodei, who in 2016 was working on a general-purpose AI to play computer games and ha ...more
Early in the book Christian tells the story of AI researcher Dario Amodei, who in 2016 was working on a general-purpose AI to play computer games and ha ...more
A well-researched treatment of the problem of AI alignment. The author does have a tendency, like many popular science writers, to digress and relay anecdotes or stories about historical scientific experiments that aren't really necessary to aid the reader's understanding of the topic. However, the final third of the book was focused and informative. After reading Stuart Russell's Human Compatible, I became more confident that the alignment problem can be solved. This book wasn't as big an updat
...more
"We are in danger of losing control of the world not to AI or to machines as such but to models."
This is full of interesting historical anecdotes (like that time William James kept a bunch of chickens in his basement to help out a student) and good high-level explanations of various approaches to machine learning.
Perhaps the most shocking issue discussed is how some US state justice systems used a model (called COMPAS) from a third-party provider for years to guide bail and sentencing decisions ...more
This is a fantastic book for people who are interested in the ideas of machine learning in the past, present and near future. I have tried to read a few books on AI before but found them to be either too technical, too basic or too boring. Not this book.
The Alignment Problem is an engrossing and thought-provoking exploration of the development of machine learning and human learning intertwined. Through it all, the book stresses on the "Alignment Problem" - How can we develop AI to do what we wan ...more
The Alignment Problem is an engrossing and thought-provoking exploration of the development of machine learning and human learning intertwined. Through it all, the book stresses on the "Alignment Problem" - How can we develop AI to do what we wan ...more
I learned a lot from this book about the history of AI development over the last 70 years, but more about how the author and the scientists he interviewed felt about AI and the alignment problem than I did the actual problem itself. They all seemed a little naive in thinking the problem is a programming error when it is an human error really. We are not aligned or alignable but ‘crooked timber’ through and through. Computers might help us follow or reveal the grain of that timber but the danger
...more
A terrific book on what must be the most important question in the field of artificial intelligence – how do we ensure they don’t inadvertently evolve into a technologically dystopian status. Surprisingly, the key issues are as much philosophical and practical as they are technical. The good news is there are a lot of talented and dedicated people working on AI safety and ethics, many of whom we ‘meet’ in the course of reading the book. Engaging, very readable, and highly informative! Strongly r
...more
A very well-written book on AI alignment that is more focused on recent research efforts and practical algorithms rather than higher-level philosophical ideas like "Life 3.0" or "Superintelligence." I thought the coverage of reinforcement learning was especially detailed but accessible. I would recommend this to anyone who is curious about current AI research. It fills a similar niche to Stuart Russell's "Human Compatible," but I would recommend this book over that one by a significant margin. (
...more
Mar 16, 2021
David Laing
added it
I had high hopes because I loved Algorithms to Live By, and I wasn't let down. The book is about as good as it could be, given its goal of explaining machine learning to a general audience through the lens of human values. It's not gonna change your life or anything, but if you're looking for a crystal-clear, equation-free, comprehensive overview of the state of machine learning research, this is the book to read. Large parts of it may be outdated within 5-10 years, so the time to read it is now
...more
This fascinating book looks deeply at both the history of machine learning and the urgent challenges around ethics and safety that are being faced by those on the front lines. Well-researched and well-written, this book is approachable for people without a technical background—you will learn a lot!—while still being thought-provoking for those in the field. Highly recommended!
I must admit that I was taken by surprise by the contents of Brian Christian’s recent book, The Alignment Problem. The book came out in 2020 and made quite a splash among the artificial intelligence (AI) and machine intelligence community. Much of the public, including myself, had been made aware of “the alignment problem” by Nick Bostrom’s book, Superintelligence, or the writings of people such as MIT physicist, Max Tegmark. In fact, in my case, it was the conundrum of the alignment problem tha
...more
On March 23rd 2016, Microsoft threw their twitter chatbot at the world. It started all innocent, what with the chatbot claiming that humans are cool. Not 24 hours later, On March 24th 2016, the very chatbot proclaimed that Hitler did nothing wrong and wishing that feminists burned in hell. Here's the link to that saga.
So, why did this ambitious machine learning project go tits up? Because the chatbot was modeling itself on the shit that was already in public domain like it was designed to.
Like ...more
So, why did this ambitious machine learning project go tits up? Because the chatbot was modeling itself on the shit that was already in public domain like it was designed to.
Like ...more
My main insight from this book is that alignment is a far more concrete problem than I imagined. I assumed that alignment simply meant making sure bad people don't have control of the goals of AI, and that we're thoughtful about crafting those goals. Instead, AI safety research is about engineering systems that can understand and carefully act in environments with ambiguous or contradictory goals.
That was a very abstract sentence, so let me try to explain that again. A big problem for AI safety ...more
That was a very abstract sentence, so let me try to explain that again. A big problem for AI safety ...more
If you’re looking for an accessible introduction to the current state of machine learning, I can’t recommend this book highly enough. Christian has a real gift for explaining complex subjects clearly and engagingly. His treatment of the potential safety and bias issues with AI is serious and measured, and mostly steers clear of Musk-ian “AI overlord” BS in favor of more realistic concerns about what happens when the imperfect models we create increasingly are allowed to run the world. I found th
...more
This book actually covered more fundamentals of AI than I expected, instead of going straight into what the alignment problem was, which to me is a good thing. It was quite readable for me despite not having any background in AI, and I think Christian did a pretty good job in explaining different basic concepts like the reward hypothesis and intrinsic motivations, as well as AI techniques with increasing complexity (RL, IRL, CIRL). The parts related to 'alignment' were mostly around the first fe
...more
| topics | posts | views | last activity | |
|---|---|---|---|---|
| Science and Inquiry: March 2022 - Alignment Problem | 16 | 108 | May 07, 2022 10:14AM |
Goodreads is hiring!
70 users
69 users
65 users
37 users
29 users
21 users
11 users
10 users
6 users
5 users
Brian Christian is the author of The Most Human Human, which was named a Wall Street Journal bestseller, a New York Times Editors’ Choice, and a New Yorker favorite book of the year. He is the author, with Tom Griffiths, of Algorithms to Live By, a #1 Audible bestseller, Amazon best science book of the year and MIT Technology Review best book of the year.
Christian’s writing has been translated int ...more
Christian’s writing has been translated int ...more
News & Interviews
For those of us with a taste for it, historical fiction scratches an itch that no other genre can quite reach. By crossing the wires of...
11 likes · 0 comments
No trivia or quizzes yet. Add some now »
“You should consider that Imitation is the most acceptable part of Worship, and that the Gods had much rather Mankind should Resemble, than Flatter them. —MARCUS AURELIUS”
—
1 likes
“What the field needed, he argued, was what he called inverse reinforcement learning. Rather than asking, as regular reinforcement learning does, “Given a reward signal, what behavior will optimize it?,” inverse reinforcement learning (or “IRL”) asks the reverse: “Given the observed behaviour, what reward signal, if any, is being optimized?”15 This is, of course, in more informal terms, one of the foundational questions of human life. What exactly do they think they’re doing? We spend a good fraction of our life’s brainpower answering questions like this. We watch the behavior of others around us—friend and foe, superior and subordinate, collaborator and competitor—and try to read through their visible actions to their invisible intentions and goals. It is in some ways the cornerstone of human cognition. It also turns out to be one of the seminal and critical projects in twenty-first-century AI.”
—
1 likes
More quotes…
















