Goodreads helps you keep track of books you want to read.
Start by marking “Human Compatible: Artificial Intelligence and the Problem of Control” as Want to Read:
Human Compatible: Artificial Intelligence and the Problem of Control
Enlarge cover
Rate this book
Clear rating
Open Preview

Human Compatible: Artificial Intelligence and the Problem of Control

4.12  ·  Rating details ·  2,634 ratings  ·  353 reviews
A leading artificial intelligence researcher lays out a new approach to AI that will enable us to coexist successfully with increasingly intelligent machines

In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is see
Hardcover, 352 pages
Published October 8th 2019 by Viking
More Details... Edit Details

Friend Reviews

To see what your friends thought of this book, please sign up.

Reader Q&A

To ask other readers questions about Human Compatible, please sign up.
Popular Answered Questions
Susanne Layperson here, I was gripped from the start by life 3.0 and could follow most of it, but I am having a hard time getting through even the first chapt…moreLayperson here, I was gripped from the start by life 3.0 and could follow most of it, but I am having a hard time getting through even the first chapters of Human compatible.(less)

Community Reviews

Showing 1-30
Average rating 4.12  · 
Rating details
 ·  2,634 ratings  ·  353 reviews

More filters
Sort order
Start your review of Human Compatible: Artificial Intelligence and the Problem of Control
Let's start with the most important thing: if you have any interest in finding out where technology is heading, please read this book. I particularly recommend that people who know something about moral philosophy do so. You may dislike Human Compatible, you may object to the way the author treats your subject, but you really ought to learn about what's happening here. Moral philosophy has become shockingly relevant to the near-term future of humanity.

I'll back up a little. Since the beginning o
Michael Perkins
Jan 20, 2020 rated it it was amazing
San Francisco police propose using robots capable of using "deadly force" (Hello Blade Runner)


“He who controls the algorithms controls the universe.”

To get just an inkling of the fire we’re playing with, consider how content-selection algorithms function on social media. They aren’t particularly intelligent, but they are in a position to affect the entire world because they directly influence billions of people. Typically, such algorit
Infinite Jen
Apr 09, 2022 rated it it was amazing
Are you interested in Artificial Intelligence and the existential issues it heralds? Then this book is for you. If you, at some point in your travels, got so high on Jamaican hash that you experienced what might reasonably be called a psychotic break, causing you to collapse in supplication before your Vintage Vinyl Cape Jawa and serenade it with the following impromptu poetics:

Sleepy middle-aged vampire slayer, Chicken Chungus.
Strikes fear into the kindred as he walks among us.
Employing sophist
Mar 05, 2021 rated it really liked it
Shelves: science
Russell looks at the future of AI, particularly what it will take to develop a general purpose superintelligent AI machine capable of understanding and interacting with humans. He focuses on the nature of intelligence, how AI machines learn, the dangers inherent in AI, and how we can control AI development to diminish those dangers. Unfortunately he didn’t convince me that his prescriptions to control AI development would be sufficient. Russell’s book is more reserved and a bit drier than other ...more
Sebastian Gebski
Oct 29, 2019 rated it it was amazing
It's quite specific, but personally I've enjoyed it A LOT.
It's a book about REAL AI (not statistics!) w/o buzzwords.

These are mainly philosophical considerations (about conscience, instincts, control mechanisms, ethics, superiority and many more) that DO have a lot of practical applicability. What I appreciate is:
* the book doesn't look for cheap publicity ("we're all doomed!")
* it doesn't try to "ride on the hype wave"
* it's really thorough when it comes to different dilemmas - possibly TOO muc
Dustin Juliano
Oct 12, 2019 rated it it was amazing

The thesis of this book is that we need to change the way we develop AI if we want it to remain beneficial to us in the future. Russell discusses a different kind of machine learning approach to help solve the problem.

The idea is to use something called Inverse Reinforcement Learning. It basically means having AI learn our preferences and goals by observing us. This is in contrast to us specifying goals for the AI, a mainstream practice that he refers to as the “standard model”. Add some game th

Dec 20, 2020 rated it it was amazing
AI research over the years has been a mish-mash of pet theories, conflicting assumptions, a focus on instrumentality, expert systems, evolutionary programming, and Deep Learning. All different ways that often must be used in conjunction to push us over that edge into true Artificial Intelligence.

I mean, we're not there yet, or to be precise, we aren't at the point of AI super-intelligence.

But that doesn't speak to the issue that has gotten a lot of traction in popular media, from movies to scien
“Everything civilization has to offer is the product of our intelligence; gaining access to considerably greater intelligence would be the biggest event in human history. The purpose of the book is to explain why it might be the last event in human history and how to make sure that it is not.”

First of all, discussions about intelligence can go astray without defining roughly what we mean by intelligence. A definition of intelligence I like is the one offered by David Krakauer. He defines int
Aug 17, 2020 rated it it was amazing  ·  review of another edition
I'm a computer guy, but I don't know much about how AI works. Russell added a lot to my knowledge & did so in basic steps that I appreciated. As in any field, there's a vocabulary to pick up & while it often resembles typical speech, there can important differences that need to be spelled out. This holds especially true with concepts that we don't understand well in ourselves & yet are trying to build into machines, specifically "intelligence". Just what that is only partially answered in the se ...more
Vidur Kapur
May 17, 2020 rated it it was amazing
Shelves: science
An engaging, well-written book by one of the leading experts in his field. Russell writes that a number of breakthroughs are needed before we're able to build an artificial general intelligence (AGI), and indeed is personally more conservative in his estimates of when AGI will be built than the median AI expert. These breakthroughs include language, abstract action discovery, and the management of mental activity.

In order to control such an AI, and align it with human interests, Russell propose
Nilendu Misra
Sep 15, 2019 rated it it was amazing
A delightful book on theory, practicality and implications of AI from one of its pioneers. Has a strong intellectual rigor under the fluent style. Loved it!
Liina Haabu
Feb 19, 2020 rated it really liked it  ·  review of another edition
Shelves: 2020, non_fiction
It took me ages to finish this one probably because it caused me such anxiety and to be honest, depressed me so, that I tolerated it only in small doses. The continuous striving for greater and greater efficiency and doing things faster (what AI largely aims for) - it reminds me of a hamster wheel that at one point will fall over. We all know that more efficiency will not give us more free time. Quite the contrary - the wheel will start to spin even faster. Let the hamster rather take a leisurel ...more
Apr 04, 2020 rated it it was amazing
Shelves: ai
A lot of writing on AI safety (lots from the effective altruism community) can't help but sound far-fetched and crazy. One of my main gripes is that most of these theoretical analyses and hypothetical scenarios are too distanced from what is actually happening in research / practice.

Russell somehow manages to communicate the minority view on the importance of the safety / control problem, while remaining grounded in practical problems and research methods. It's such a difficult topic to write a
James Munro
Jun 20, 2021 rated it really liked it  ·  review of another edition
Interesting insights into the dichotomy of AI and how we can balance its vast applications with its associated risks. Technical at times, but still enjoyed it.
Bryan Murphy
Jan 18, 2020 rated it it was amazing
If ever a book deserved the epithet "must-read", it is this one. ...more
Mar 13, 2022 rated it liked it
2.5 stars.

It's okay, but you should read "Superintelligence: Paths, Dangers, Strategies" instead: "Human Compatible" has much less depth and doesn't really bring anything new of substance.
Feb 23, 2021 rated it it was amazing
Shelves: 2021
A Superintelligence is an artificial general intelligence (AGI) which has an intelligence surpassing that of humans.

A.I.s are in some specific cases already better than humans, e.g. by winning ever more complex games like chess,Go, or StarCraft against human champions. AGIs are not restricted to a specific field but can do intellectual tasks like humans. In the case of strong AGIs, they are even conscious and self-aware.

As soon as a superintelligence gets better than a human, it gets better at e
Alex Railean
A very thought-provoking book. The author explains some basic AI concepts and reviews the history of the field, then moves on to the main theme - a discussion about what it takes to ensure the AI will remain under our control.

The primary value I got out of it is his 3-point approach towards solving the problem. I find his argument convincing and will definitely keep these points (see notes below) in mind in the future.

Note: I only documented the latter part of the book; the intro was also very i
May 08, 2020 rated it did not like it  ·  review of another edition
Shelves: technology, return-bin, ai
This was terrible...
I did not finish it. I made it ~halfway through and then pulled the plug, which is something I almost never do.
I was excited to read this one, as I am very interested in AI. Author Stuart Russell's delivery left much to be desired, however...
The book is written in an extremely dry and long-winded manner. I found my attention wandering, and was getting irritated. The reading was extremely tedious and jumped around quite a lot.
The final straw was hearing him talk about how c
Daniel Hageman
May 23, 2021 rated it really liked it
I still have a fair bit of hesitancy with various views in this space, particularly around some of the analogies used to illustrate the proposition of intelligence explosions, but this is surely the go-to book to hear this side of the story (notably more digestible than Bostrom's SI). ...more
Keith Swenson
Dec 18, 2019 rated it really liked it
After years of disappointing expectations, AI is finally arriving. It is here today in nascent form, and will surely expand capabilities quickly. But can we avoid creating a super intelligence that destroys humanity? This concern is routinely listed on the top five possible ways for humanity to terminate itself -- so listen up: this is important.

Russell steps back from this dire prognostication to begin the book with a review of AI, how it has come along to where we are today. The Baldwin effect
Tarmo Pungas
Sep 29, 2021 rated it it was amazing
Great introductory book for everyone wanting to learn about AI safety. Doesn't require a technical background and some concepts are explained more elaborately in the appendices. ...more
Quinn Dougherty
Feb 19, 2021 rated it liked it
Good stuff. You should probably read. I'm skipping appendices because I have somewhat of a CS education in AI and at a glance the appendices look like background for the uninitiated.

Russell calls all of goaldirectedness "the standard model" and says we should declare today year zero of real ai research-- he proposes a nonstandard model that is just three principles. 1. The machine's only objective ought to be satisfaction of human preferences. 2. The machine is uncertain about what those prefer
Jan 07, 2022 rated it it was amazing
Perhaps safely described as one of the most important books recently published. Prof is co-author of AI bible. We're on the cusp of truly smart AI, perhaps the most consequential milestone in human history. We don't want to be extinct, we don't want to be pets. What failsafe should we program into the AI before it escapes 'control' and exponentiates its own intelligence within a matter of days or weeks? The prof provides a suggestion. 3 rules should underwrite the AI's existence: i) prioritizati ...more
Dec 11, 2019 rated it did not like it
Shelves: junk
Another nobody who has found the best solution ever: we should get a czar to lead us!
Dec 20, 2019 rated it it was amazing
Just F***ING read this book!
Dec 06, 2021 rated it really liked it
I think this was a fantastic introduction to learning about AI safety and alignment (although I have to read some more about the topics to verify that intuition!). Russell identifies critical issues with the current model of designing machines to pursue specific objectives and proposes an alternative model which instead centers human preferences and accounts for uncertainty. Along with that, he also covers the history of research into intelligence, conceptual breakthroughs required for superinte ...more
Marco Loya
Jun 27, 2021 rated it it was amazing
It’s a great book to really get into the AI topics. The guy is clearly a genius and you can see it in the way the relates so much knowledge from different areas to answer questions about AI.

The book thought me that AI is not to be taken lightly. Too much is at stakes, and nobody knows when the big AI boom will happen. It will probably be the next big catastrophe in our history or the machines might be our saviors, who knows!

All the relevant questions are answered in this book with the best infor
Jun 12, 2020 rated it really liked it
An interesting study about possible threats of artificial intelligence on humans and on the existence of civilization. Learned quite a bit of new information from this book.
It is actually a 5* book but wasn't overly happy with the style of writing.
Laura Hill
Feb 08, 2020 rated it it was amazing
An extremely well-written, comprehensive overview of Artificial Intelligence (AI) — with a focus on the very real risks it poses to the continued viability of the human race and a proposal for how to move forward reaping the benefits of AI without making us “seriously unhappy.”

AI Pioneer Stuart Russell is a Professor of Computer Science at UC Berkeley, has numerous awards, fellowships, chairmanships, etc. and has co-authored a textbook on AI with Peter Norvig. This is a book written by that rar
« previous 1 3 4 5 6 7 8 9 10 11 12 next »
topics  posts  views  last activity   
TAC Book Lovers' ...: Human Compatible by Stuart Russell 1 10 Jan 22, 2021 01:09AM  

Readers also enjoyed

  • The Alignment Problem: Machine Learning and Human Values
  • Superintelligence: Paths, Dangers, Strategies
  • Life 3.0: Being Human in the Age of Artificial Intelligence
  • The Precipice: Existential Risk and the Future of Humanity
  • Artificial Intelligence: A Guide for Thinking Humans
  • Rebooting AI: Building Artificial Intelligence We Can Trust
  • The Big Picture: On the Origins of Life, Meaning, and the Universe Itself
  • What We Owe the Future
  • AI 2041: Ten Visions for Our Future
  • Lying
  • The Singularity is Near: When Humans Transcend Biology
  • Doing Good Better: How Effective Altruism Can Help You Make a Difference
  • A Thousand Brains: A New Theory of Intelligence
  • The Metaverse: And How It Will Revolutionize Everything
  • The Scout Mindset: Why Some People See Things Clearly and Others Don't
  • The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World
  • AI Superpowers: China, Silicon Valley, and the New World Order
  • Genius Makers: The Mavericks Who Brought AI to Google, Facebook, and the World
See similar books…

Goodreads is hiring!

If you like books and love to build cool products, we may be looking for you.
Learn more »
See top shelves…
Librarian Note: There is more than one author in the GoodReads database with this name. See this thread for more information. ...more

News & Interviews

Need another excuse to treat yourself to a new book this week? We've got you covered with the buzziest new releases of the day. To create our...
24 likes · 5 comments
“The right to mental security does not appear to be enshrined in the Universal Declaration. Articles 18 and 19 establish the rights of “freedom of thought” and “freedom of opinion and expression.” One’s thoughts and opinions are, of course, partly formed by one’s information environment, which, in turn, is subject to Article 19’s “right to . . . impart information and ideas through any media and regardless of frontiers.” That is, anyone, anywhere in the world, has the right to impart false information to you. And therein lies the difficulty: democratic nations, particularly the United States, have for the most part been reluctant—or constitutionally unable—to prevent the imparting of false information on matters of public concern because of justifiable fears regarding government control of speech. Rather than pursuing the idea that there is no freedom of thought without access to true information, democracies seem to have placed a naïve trust in the idea that the truth will win out in the end, and this trust has left us unprotected.” 7 likes
“Finally, methods of control can be direct if a government is able to implement rewards and punishments based on behavior. Such a system treats people as reinforcement learning algorithms, training them to optimize the objective set by the state. The temptation for a government, particularly one with a top-down, engineering mind-set, is to reason as follows: it would be better if everyone behaved well, had a patriotic attitude, and contributed to the progress of the country; technology enables measurement of individual behavior, attitudes, and contributions; therefore, everyone will be better off if we set up a technology-based system of monitoring and control based on rewards and punishments.” 4 likes
More quotes…