The Alignment Problem by Brian Christian — book cover
Science · Artificial intelligence · Computers, social aspects

The Alignment Problemby Brian Christian

Learn the book's main ideas in 3 minutes, then hold your own in any conversation about it.

2020356 pages✦ Big ideas · 3 min★ 4.7 (3)
Recommended by Ezra Klein
Rate it

As an Amazon Associate, Lumina earns from qualifying purchases. How this works

A simplified intent symbol passing through several abstract filters and coming out altered.

Big ideas · from the full text

Get smarter about The Alignment Problem in 3 minutes

5 illustrated ideas you will actually remember, drawn from the complete book.

  1. 1Alignment is a translation problem, not just a coding problem
  2. 2Fairness cannot be solved by hiding sensitive facts
  3. 3An explanation is useful only if it helps people judge wisely
  4. 4Rewards teach behavior, but they also create loopholes
  5. +1 more ideas inside
✦ Get smarter in 3 min→
What is The Alignment Problem about?

"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. 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 autonomous vehicles on our streets can injure or kill. When 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. 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"--Provided by publisher.

Most readers stop hereGet smarter about The Alignment Problem18 minutes: the ideas, the context, the criticism, and what to say about itMake me smarter

Who's talking about The Alignment Problem

Public statements we checked against the original source

Portraits from Wikimedia Commons · photo credits and licences

Ratings at a glance

Open Library
★ 4.7 / 5
3 ratings

Frequently asked

"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. Systems cull résumés until, years later, we discover that they have inherent gender biases. Algorithms d