The Alignment Problem

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.

'Vital reading. This is the book on artificial intelligence we need right now.' Mike Krieger, cofounder of Instagram Artificial intelligence is rapidly dominating every aspect of our modern lives influencing the news we consume, whether we get a mortgage, and even which friends wish us happy birthday. But as algorithms make ever more decisions on our behalf, how do we ensure they do what we want? And fairly? This conundrum - dubbed 'The Alignment Problem' by experts - is the subject of this timely and important book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, bestselling author Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics. If we stand by, we face a future with unregulated algorithms that propagate our biases - and worse - violate our most sacred values. Urgent and fascinating, this is an accessible primer to the most important issue facing AI researchers today.

A playful, profound book that is not only a testament to one man's efforts to be deemed more human than a computer, but also a rollicking exploration of what it means to be human in the first place. “Terrific. ... Art and science meet an engaged mind and the friction produces real fire.” —The New Yorker Each year, the AI community convenes to administer the famous (and famously controversial) Turing test, pitting sophisticated software programs against humans to determine if a computer can “think.” The machine that most often fools the judges wins the Most Human Computer Award. But there is also a prize, strange and intriguing, for the “Most Human Human.” Brian Christian—a young poet with degrees in computer science and philosophy—was chosen to participate in a recent competition. This

"The most important book on AI this year." --The Guardian "Mr. Russell's exciting book goes deep, while sparkling with dry witticisms." --The Wall Street Journal "The most important book I have read in quite some time" (Daniel Kahneman); "A must-read" (Max Tegmark); "The book we've all been waiting for" (Sam Harris) 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 seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial.

SHORTLISTED for the 2021 BC and Yukon Book Prizes' Hubert Evans Non-Fiction Prize A personal story about not only facing but conquering fears. In 2015, Eva Holland was forced to confront her greatest fear when her mother had a stroke and suddenly passed away. After the shock and grief subsided, Holland began to examine the extent to which her many fears had limited her, and wondered whether or not it was possible to move past them. This sent Holland on a deep dive into the science of fear, digging into an array of universal and personal questions: Why do we feel fear? Where do phobias come from and how are they related to anxiety disorders and trauma? Can you really smell fear? (Yes.) What would it be like to feel no fear? Is there a cure for fear? Or, put differently, is there a better way to feel afraid? On her journey, Holland meets with scientists who are working to eliminate phobias with a single pill, she explores the lives of the few individuals who suffer from a rare disease that prevents them from ever feeling fear, and she immerses herself in her own fears including hurling herself out of a plane for her first skydive (and in the process, learns that there are right and wrong ways to face your fears). Fear is a universal human experience, and Nerve answers these questions in a refreshingly accessible way, offering readers an often personal, sometimes funny, and always rigorously researched journey through the science of facing our fears.

The history of robotics and artificial intelligence in many ways is also the history of humanity’s attempts to control such technologies. From the Golem of Prague to the military robots of modernity, the debate continues as to what degree of independence such entities should have and how to make sure that they do not turn on us, its inventors. Numerous recent advancements in all aspects of research, development and deployment of intelligent systems are well publicized but safety and security issues related to AI are rarely addressed. This book is proposed to mitigate this fundamental problem. It is comprised of chapters from leading AI Safety researchers addressing different aspects of the AI control problem as it relates to the development of safe and secure artificial intelligence. The book is the first edited volume dedicated to addressing challenges of constructing safe and secure advanced machine intelligence. The chapters vary in length and technical content from broad interest opinion essays to highly formalized algorithmic approaches to specific problems. All chapters are self-contained and could be read in any order or skipped without a loss of comprehension.

About the bookToby Ord try to fill this gap. They argue that there are distinctive norms that govern how one ought to make decisions and defend an information-sensitive account of how to make such decisions. They do so by developing an analogy between moral uncertainty and social choice, noting that different moral views provide different amounts of information regarding our reasons for action, and arguing that the correct account of decision-making under moral uncertainty must be sensitive to that. Moral Uncertainty also tackles the problem of how to make intertheoretic comparisons, and addresses the implications of their view for metaethics and practical ethics. Very often we are uncertain about what we ought, morally, to do. We do not know how to weigh the interests of animals against humans, how strong our duties are to improve the lives of distant strangers, or how to think about the ethics of bringing new people into existence. But we still need to act. So how should we make decisions in the face of such uncertainty? Though economists and philosophers have extensively studied the issue of decision-making in the face of uncertainty about matters of fact, the question of decision-making given fundamental moral uncertainty has been neglected. In Moral Uncertainty, philosophers William MacAskill, Krister Bykvist, and Toby Ord try to fill this gap. They argue that there are distinctive norms that govern how one ought to make decisions and defend an information-sensitive account of how to make such decisions. They do so by developing an analogy between moral uncertainty and social choice, noting that different moral views provide different amounts of information regarding our reasons for action, and arguing that the correct account of decision-making under moral uncertainty must be sensitive to that. Moral Uncertainty also tackles the problem of how to make intertheoretic comparisons, and addresses the implications of their view for metaethics and practical ethics.