The Alignment Problem
by Brian Christian · first published 2020
64% recommend36% neutral
Why HN recommends it
Readable, well-written overview of machine learning and human values, covering the history and pitfalls of different ML approaches; suits readers new to AI safety and product or policy people wanting a grounded picture.
Summarised by Claude from recommending comments
"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 aut
Affiliate links. As an Amazon Associate I earn from qualifying purchases.
Mentions per year
What Hacker News says
Related books
2008–2026The Ancestor's Tale
Richard Dawkins
Recommended by 21 · mentioned by 2421 recommend · 24 mention21 recommend · 2421 recommend
2008–2026The God Delusion
Richard Dawkins
Recommended by 41 · mentioned by 10341 recommend · 103 mention41 recommend · 10341 recommend
2009–2026How to Measure Anything
Douglas W. Hubbard
Recommended by 46 · mentioned by 5846 recommend · 58 mention46 recommend · 5846 recommend
2016–2026Algorithms to Live By
Brian Christian, Tom Griffiths
Recommended by 69 · mentioned by 10769 recommend · 107 mention69 recommend · 10769 recommend
2007–2026Hackers
Steven Levy
Recommended by 130 · mentioned by 188130 recommend · 188 mention130 recommend · 188130 recommend
2008–2026How to Read a Book
Mortimer J. Adler, Charles Lincoln Van Doren
Recommended by 157 · mentioned by 234157 recommend · 234 mention157 recommend · 234157 recommend
2007–2026The Cuckoo’s Egg
Clifford Stoll
Recommended by 205 · mentioned by 275205 recommend · 275 mention205 recommend · 275205 recommend
2007–2026The Soul of a New Machine
Tracy Kidder
Recommended by 260 · mentioned by 376260 recommend · 376 mention260 recommend · 376260 recommend
From the lens of a Product Manager working in ML / Large Language Models... The Alignment Problem By Brian Christian How do we tell the computer to do all the things we want it to do, all the things we don't want it to do, and all the things we didn't realize we want it to do or not do? How do…
on “Ask HN: Which books do you consider real gems in your field of work/study?” ↗Very cool project. I'm currently reading The Alignment Problem by Brian Christian on AI (very well written and easy to read), and also (very slowly) My Great Predecessors, Vol 1 by Garry Kasparov. This is a great combination of the two topics! I'm particularly interested…
on “Show HN: ChessCoach – A neural chess engine that comments on each player's moves” ↗The Alignment Problem: Machine Learning and Human Values[1] by Brian Christian is a nice overview of some of this history and exploration of some of the pitfalls in different ML approaches. It's really interesting reading…
on “A stubborn computer scientist accidentally launched the deep learning boom” ↗The Alignment Problem by Brian Christian. It sets up the complexity of ML field and human values. It paints a picture to the readers on the future we navigate.
on “Ask HN: What book should my CS1 students read?” ↗The Alignment Problem
on “Ask HN: What nonfiction books do you keep rereading?” ↗…days to not recognize the lack of substance in such a book, and in its author. Far better books on the possible futures of modern AI are Stuart Russell's "Human Compatible" or Brian Christian's "The Alignment Problem", both of which predate the boom in LLMs but still anticipate their Achilles heel -- the inability to control what they learn or how they will use it.
on “My Favorite Book on AI” ↗…that matters the most. Among those articles, I don’t see great minds doing their best work. (The constraints of their medium and funding model are a big problem I think.) Read Brian Christian’s “The Alignment Problem”’s take on predictive policing if you want a specific example of what I mean. There are actually mathematical impossibilities at play when it comes to common sense, ethical reasoning. Common sense ethical…
on “Statement from Dario Amodei on Our Discussions with the Department of War” ↗…presence in it. It was Tom to give the "appetizer" presentation at TED: https://www.ted.com/talks/tom_griffiths_3_ways_to_make_bette... -- By the way, I see that Brian Christian has published a The Alignment Problem - Machine Learning and Human Values, https://brianchristian.org/the-alignment-problem/ Has anyone read it?
on “Ask HN: What nonfiction books do you keep rereading?” ↗Brian Christian here. Honored to be the guest on the Ezra Klein show this week and by Ezra’s kind words: "Brian Christian’s recent book The Alignment Problem is the best book on the key technical and moral questions of A.I. that I’ve read." Happy to take any questions, etc., if folks are interested! AMA.
on “If 'All Models Are Wrong,' Why Do We Give Them So Much Power?” ↗Brian Christian, the author of "Algorithms to Live By", has also written "The Alignment Problem" on the technical and moral questions of A.I.
on “Book Review: Algorithms to Live By – The Computer Science of Human Decisions” ↗…misalignment, and now seem to define AI misalignment so that, by definition, it excludes all current systems. So tautologically the answer to your question will be "no". Brian Christian's book "The Alignment Problem" contains many examples of harms from systems which people plausibly see as being based on precursor technology.
on “Misalignment Museum” ↗…Sometimes you just can't win. "Quality" is one of those things. As soon as I define quality one way, you can attack me by defining it another way. A particular version of this principle is explained in The Alignment Problem by Brian Christian, by the way, regarding predictive policing iirc.) I'm seeing a lot of moral outrage but not enough intellectual curiosity. It embarrassingly easy to say "they should have done better"…
on “An update on recent Claude Code quality reports” ↗