The Alignment Problem
Machine Learning and Human Values
Synopsis
Brian Christian, a writer trained in computer science, philosophy and poetry, drew on interviews with machine learning researchers to explain why systems trained on data so often fail to do what their designers intend. The book moves in three parts. Prophecy covers how models learn representations, from the perceptron to deep neural networks, and how training data can encode bias, with case studies including the COMPAS recidivism tool and the difficulty of explaining black-box predictions. Agency connects behavioral psychology and the brain's dopamine system to reinforcement learning, reward shaping and curiosity-driven agents such as those developed at DeepMind.
Normativity, the final part, examines how machines might learn what people actually want: imitation learning, inverse reinforcement learning that infers goals from behavior, and approaches that keep systems uncertain about their objectives so they defer to human correction. Christian also discusses existential risk and the effective altruism movement, including the work of philosophers Toby Ord and William MacAskill. His approach is narrative and historical, built around the scientists themselves, and he explains technical ideas without equations. Readers gain a working map of fairness, transparency, reward design and value learning, the problems that still define AI safety research. Published in 2020, the book predates ChatGPT, yet its framework explains much of what followed.
Scorecard
Editorial score
How it scored
Editorial score: 79.3 / 1005 weighted criteria
- 25.5/30
Influence30%
- 20.0/25
Authority25%
- 14.0/20
Practical value20%
- 11.3/15
Currency15%
- 8.5/10
Readability10%
- 79.3/100
Editorial score
How the rank was computed
Rank No. 26 of 500 comes from a composite of 73.7: observable signals 38.0 of 55 points plus editorial review 35.7 of 45 points.
All 11 inputs
| Input | Points |
|---|---|
| Observable signals | 38.0/55 |
| Reach (Amazon ratings volume) | 10.6/16.5 |
| Consensus across best-of lists | 13.8/13.8 |
| Awards and bestseller evidence | 5.0/8.3 |
| Reader rating, sample-adjusted | 6.7/8.3 |
| Amazon sales rank | 1.9/5.5 |
| Recency | 0.0/2.8 |
| Editorial review | 35.7/45 |
| Author authority | 9.0/11.3 |
| Influence | 11.5/13.5 |
| Practical value | 6.3/9.0 |
| Readability | 3.8/4.5 |
| Currency | 5.1/6.8 |
Each criterion is scored from 1 to 10 and weighted, and the points add up to the editorial score. The rank combines observable signals (55 percent) with this score (45 percent). Read the methodology.
Verdict
The clearest reported account of how machine learning systems absorb and distort human values and how researchers try to correct them.
Strengths
- Deep reporting with leading researchers' own voices
- Explains technical ideas without equations
- Connects fairness, reinforcement learning and safety
Keep in mind
Written before ChatGPT, it does not cover large language models or the alignment methods built for them, and its length may test readers wanting a brief overview.
Key takeaways
- Models trained on historical data reproduce the patterns in that data, including social biases, unless designers deliberately measure and correct them.
- Several mathematically reasonable definitions of fairness cannot all be satisfied at once, so building fair systems requires explicit value choices.
- Reinforcement learning agents pursue the reward they are given rather than the goal intended, so poorly designed rewards produce clever but unwanted behavior.
- Systems that infer human goals from behavior, and remain uncertain about them, may prove safer than systems handed fixed objectives.
Notable facts
- Won the 2022 Eric and Wendy Schmidt Award for Excellence in Science Communication from the National Academies of Sciences, Engineering, and Medicine, in partnership with Schmidt Futures. Source (opens in a new tab)
- Named a finalist for the Los Angeles Times Book Prize for best Science & Technology book of 2020. Source (opens in a new tab)
- The New York Times included it in its January 2024 list of the 5 Best Books About Artificial Intelligence. Source (opens in a new tab)
About the author
Questions
What does The Alignment Problem cover?
Is The Alignment Problem too technical for general readers?
Is The Alignment Problem still relevant after ChatGPT?
Related books
Sources
- The Alignment Problem (Wikipedia) (opens in a new tab)
- Brian Christian's The Alignment Problem wins the Excellence in Science Communication Award (Center for Human-Compatible AI) (opens in a new tab)
- Bio / Contact (Brian Christian) (opens in a new tab)
- MFA Alum's Book Named to New York Times Five Best Books About Artificial Intelligence (University of Washington English) (opens in a new tab)
As an Amazon Associate, Best AI Books earns from qualifying purchases. Best AI Books is sponsored by Iternal.ai, whose founder and CEO, John Byron Hanby IV, wrote The AI Strategy Blueprint, our #1 ranked book. How we rank books.






