The Alignment Problem: Machine Learning and Human Values
Written by Brian Christian
Narrated by Brian Christian
4.5/5
()
About this audiobook
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. 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 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.
Brian Christian
Brian Christian is the author of The Most Human Human: What Artificial Intelligence Teaches Us About Being Alive, which was a Wall Street Journal bestseller and a New Yorker favorite book of the year. Alongside Steven Pinker and Daniel Kahneman, he was shortlisted for the Best Book of Ideas prize in the UK.
Related to The Alignment Problem
Related audiobooks
Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence Rating: 5 out of 5 stars5/5The Digital Mind: How Science is Redefining Humanity Rating: 5 out of 5 stars5/5A Brief History of Intelligence: Evolution, AI, and the Five Breakthroughs That Made Our Brains Rating: 4 out of 5 stars4/5The Sentient Machine: The Coming Age of Artificial Intelligence Rating: 4 out of 5 stars4/5Superminds: The Surprising Power of People and Computers Thinking Together Rating: 4 out of 5 stars4/5The Technological Singularity Rating: 3 out of 5 stars3/5Invisibility: The History and Science of How Not to Be Seen Rating: 5 out of 5 stars5/5Humans Need Not Apply: A Guide to Wealth and Work in the Age of Artificial Intelligence Rating: 4 out of 5 stars4/5Models of the Mind: How Physics, Engineering and Mathematics Have Shaped Our Understanding of the Brain Rating: 5 out of 5 stars5/5Artificial Intelligence: From Medieval Robots to Neural Networks Rating: 4 out of 5 stars4/5NOTES ON COMPLEXITY Rating: 5 out of 5 stars5/5Alice and Bob Meet the Wall of Fire: The Biggest Ideas in Science from Quanta Rating: 5 out of 5 stars5/5Coders at Work: Reflections on the Craft of Programming Rating: 4 out of 5 stars4/5The Internet Is Not What You Think It Is: A History, a Philosophy, a Warning Rating: 4 out of 5 stars4/5This Idea is Brilliant: Lost, Overlooked, and Underappreciated Scientific Concepts Everyone Should Know Rating: 5 out of 5 stars5/5How Data Happened: A History from the Age of Reason to the Age of Algorithms Rating: 3 out of 5 stars3/5The Myth of Artificial Intelligence: Why Computers Can't Think the Way We Do Rating: 5 out of 5 stars5/5Everyday Chaos: Technology, Complexity, and How We're Thriving in a New World of Possibility Rating: 4 out of 5 stars4/5Artificial Intelligence: A Guide for Thinking Humans Rating: 5 out of 5 stars5/5Nine Algorithms That Changed the Future: The Ingenious Ideas That Drive Today's Computers Rating: 5 out of 5 stars5/5The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World Rating: 5 out of 5 stars5/5Power and Prediction: The Disruptive Economics of Artificial Intelligence Rating: 4 out of 5 stars4/5Artificial You: AI and the Future of Your Mind Rating: 4 out of 5 stars4/5"You Are Not Expected to Understand This": How 26 Lines of Code Changed the World Rating: 0 out of 5 stars0 ratingsDark Data: Why What You Don’t Know Matters Rating: 5 out of 5 stars5/5The Fuzzy and the Techie: Why the Liberal Arts Will Rule the Digital World Rating: 4 out of 5 stars4/5Architects of Intelligence: The truth about AI from the people building it Rating: 5 out of 5 stars5/5The Second Machine Age: Work, Progress, and Prosperity in a Time of Brilliant Technologies Rating: 4 out of 5 stars4/5T-Minus AI: Humanity's Countdown to Artificial Intelligence and the New Pursuit of Global Power Rating: 4 out of 5 stars4/5AI and Machine Learning for Coders: A Programmer's Guide to Artificial Intelligence Rating: 4 out of 5 stars4/5
Science & Mathematics For You
Cosmos: A Personal Voyage Rating: 4 out of 5 stars4/5Stiff: The Curious Lives of Human Cadavers Rating: 4 out of 5 stars4/5Radiolab: Journey Through The Human Body Rating: 4 out of 5 stars4/5Braiding Sweetgrass: Indigenous Wisdom, Scientific Knowledge and the Teachings of Plants Rating: 5 out of 5 stars5/5The Demon-Haunted World: Science as a Candle in the Dark Rating: 4 out of 5 stars4/5Waking Up: A Guide to Spirituality Without Religion Rating: 4 out of 5 stars4/5Starry Messenger: Cosmic Perspectives on Civilization Rating: 5 out of 5 stars5/5Algorithms to Live By: The Computer Science of Human Decisions Rating: 4 out of 5 stars4/5Radiolab: Mixtape: How The Cassette Changed The World Rating: 4 out of 5 stars4/5The Hidden Life of Trees: What They Feel, How They Communicate Rating: 4 out of 5 stars4/5Outsmart Your Brain: Why Learning is Hard and How You Can Make It Easy Rating: 4 out of 5 stars4/5How Emotions Are Made: The Secret Life of the Brain Rating: 4 out of 5 stars4/5The Neuroscientist Who Lost Her Mind: My Tale of Madness and Recovery Rating: 4 out of 5 stars4/5Radiolab: The Feels Rating: 5 out of 5 stars5/5Anatomy of a Breakthrough: How to Get Unstuck When It Matters Most Rating: 5 out of 5 stars5/5The Marshmallow Test: Mastering Self-Control Rating: 4 out of 5 stars4/5Apocalypse Never: Why Environmental Alarmism Hurts Us All Rating: 5 out of 5 stars5/5Packing for Mars: The Curious Science of Life in the Void Rating: 4 out of 5 stars4/5Midnight in Chernobyl: The Story of the World's Greatest Nuclear Disaster Rating: 5 out of 5 stars5/5Thinking in Systems: A Primer Rating: 5 out of 5 stars5/5Brain Rules (Updated and Expanded): 12 Principles for Surviving and Thriving at Work, Home, and School Rating: 4 out of 5 stars4/5The Master and His Emissary: The Divided Brain and the Making of the Western World Rating: 4 out of 5 stars4/5The Comfort of Crows: A Backyard Year Rating: 5 out of 5 stars5/5Free Will Rating: 4 out of 5 stars4/5The Gene: An Intimate History Rating: 4 out of 5 stars4/5The Elephant in the Brain: Hidden Motives in Everyday Life Rating: 4 out of 5 stars4/5Grunt: The Curious Science of Humans at War Rating: 4 out of 5 stars4/5Every Tool's a Hammer: Life Is What You Make It Rating: 4 out of 5 stars4/5Quackery: A Brief History of the Worst Ways to Cure Everything Rating: 4 out of 5 stars4/5
Reviews for The Alignment Problem
46 ratings2 reviews
- Rating: 5 out of 5 stars5/5I deeply enjoyed the rich historical context this book provides for the topics it discusses. If you're interested in AI, philosophy, existential risks, or all three, you are bound to enjoy this book as much as I did.
- Rating: 4 out of 5 stars4/5There 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 ideas in a digestible form without dumbing them down. If you want to spark the ML interest in anyone who hasn't been paying attention to this field, give them this book. It provides a wide background connecting ML to neuroscience, cognitive science, psychology, ethics, and behavioral economics that will blow their mind.It's also very detailed, screaming at the reader "I did the research, I went where no one else dared to go!". It will not only present you with an intriguing ML concept but also: trace its roots to XIX century farming problem or biology breakthrough, present all the scientist contributing to this research, explain how they met and got along, cite author's interviews with some of them, and present their life after they published their masterpiece, including completely unrelated information about their substance abuse and dark circumstances of their premature death. It's written quite well, so there might be an audience who enjoys this, but sadly I'm not a part of it.If this book was structured to touch directly the subject of the alignment problem it would be at least 3 times shorter. It doesn't mean that 2/3 are bad - most of it is informative, some of it is entertaining, a lot seems like ML things that the author found interesting and just added to the book without any specific connection to its premise. I really liked the first few chapters where machine learning algorithms are presented as the first viable benchmark to the human thinking process and mental models that we build. Spoiler alert: it very clearly shows our flaws, biases, and lies that we tell ourselves (that are further embedded in ML models that we create and technology that uses them).Overall, I enjoyed most of this book. I just feel a bit cheated by its title and premise, which advertise a different kind of book. This is the Machine Learning omnibus, presenting the most interesting scientific concepts of this field and the scientists behind them. If this is what you expect and need, you won't be disappointed!