The Alignment Problem
eBook - ePub

The Alignment Problem

'If you're going to read one book on artificial intelligence, this is the one' New York Times

  1. English
  2. ePUB (mobile friendly)
  3. Available on iOS & Android
eBook - ePub

The Alignment Problem

'If you're going to read one book on artificial intelligence, this is the one' New York Times

About this book

'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.

Frequently asked questions

Yes, you can cancel anytime from the Subscription tab in your account settings on the Perlego website. Your subscription will stay active until the end of your current billing period. Learn how to cancel your subscription.
No, books cannot be downloaded as external files, such as PDFs, for use outside of Perlego. However, you can download books within the Perlego app for offline reading on mobile or tablet. Learn more here.
Perlego offers two plans: Essential and Complete
  • Essential is ideal for learners and professionals who enjoy exploring a wide range of subjects. Access the Essential Library with 800,000+ trusted titles and best-sellers across business, personal growth, and the humanities. Includes unlimited reading time and Standard Read Aloud voice.
  • Complete: Perfect for advanced learners and researchers needing full, unrestricted access. Unlock 1.4M+ books across hundreds of subjects, including academic and specialized titles. The Complete Plan also includes advanced features like Premium Read Aloud and Research Assistant.
Both plans are available with monthly, semester, or annual billing cycles.
We are an online textbook subscription service, where you can get access to an entire online library for less than the price of a single book per month. With over 1 million books across 1000+ topics, we’ve got you covered! Learn more here.
Look out for the read-aloud symbol on your next book to see if you can listen to it. The read-aloud tool reads text aloud for you, highlighting the text as it is being read. You can pause it, speed it up and slow it down. Learn more here.
Yes! You can use the Perlego app on both iOS or Android devices to read anytime, anywhere — even offline. Perfect for commutes or when you’re on the go.
Please note we cannot support devices running on iOS 13 and Android 7 or earlier. Learn more about using the app.
Yes, you can access The Alignment Problem by Brian Christian in PDF and/or ePUB format, as well as other popular books in Computer Science & Artificial Intelligence (AI) & Semantics. We have over one million books available in our catalogue for you to explore.

INDEX

0–1 loss function, 354n47
3CosAdd algorithm, 316, 397n13
Abbeel, Pieter, 257, 258–59, 267–68, 297
Ackley, Dave, 171–72
actor-critic architecture, 138
actualism vs. possibilism, 234–40
effective altruism and, 237–38
imitation and, 235, 239–40, 379n71
Professor Procrastinate problem, 236–37, 379n61
actuarial models, 92–93
addiction, 135, 153, 205–08, 374n65
See also drug use
AdSense, 343n72
adversarial examples, 279–80, 387n8
affine transformations, 383n16
African Americans. See racial bias
Against Prediction (Harcourt), 78–79
age bias, 32, 396n7
AGI. See artificial general intelligence
Agüera y Arcas, Blaise, 247
AI Now Institute, 396n9
AI safety
artificial general intelligence delay risks and, 310
corrigibility, 295–302, 392–93n51
field growth, 12, 249–50, 263
gridworlds for, 292–93, 294, 295, 390n29
human-machine cooperation and, 268–69
irreversibility and, 291, 293
progress in, 313–14
reward optimization and, 368n56
uncertainty and, 291–92
See also value alignment
AIXI, 206–07, 263
Alciné, Jacky, 25, 29, 50
ALE. See Arcade Learning Environment
Alexander, Robert McNeill, 382n13
Alexnder VIII (Pope), 303
AlexNet
brittleness of, 279
complexity of, 100
development of, 21, 23–25
dropout and, 24, 285, 389n21
ensembles and, 285
feature visualization and, 108, 109–10
ground truth gaps and, 75
algorithms, ...

Table of contents

  1. Cover
  2. Title
  3. Copyright
  4. Contents
  5. Prologue
  6. Introduction
  7. I. Prophecy
  8. II. Agency
  9. III. Normativity
  10. Conclusion
  11. Acknowledgments
  12. Notes
  13. Bibliography
  14. Index