Aaron reviewed Artificial Intelligence by Melanie Mitchell
Artificial Intelligence
4 stars
Mitchell, a computer scientist, has written an engaging book about AI, including both its opportunities and problems. She comes down as more skeptical (or at least restrained) than AI enthusiasts, although she clearly sees benefits to the technology. More than any other book I have read, Mitchell skillfully walks non-technological people (like this reader) through technological explanations of what AI is doing. There are plenty of great visual examples in the book, demonstrating how AI can make elementary mistakes (identifying images of random dots as different animals, for instance).
More than anything else, reading this book gave me tremendous respect for what the human mind can accomplish. We use words like "intelligence" to describe what machines are doing, but nothing comes close to what the human mind can do easily.
Near the end of the book, Mitchell quotes the economist Sendhil Mullainathan: "We should be afraid. Not of intelligent machines. …
Mitchell, a computer scientist, has written an engaging book about AI, including both its opportunities and problems. She comes down as more skeptical (or at least restrained) than AI enthusiasts, although she clearly sees benefits to the technology. More than any other book I have read, Mitchell skillfully walks non-technological people (like this reader) through technological explanations of what AI is doing. There are plenty of great visual examples in the book, demonstrating how AI can make elementary mistakes (identifying images of random dots as different animals, for instance).
More than anything else, reading this book gave me tremendous respect for what the human mind can accomplish. We use words like "intelligence" to describe what machines are doing, but nothing comes close to what the human mind can do easily.
Near the end of the book, Mitchell quotes the economist Sendhil Mullainathan: "We should be afraid. Not of intelligent machines. But of machines making decisions that they do not have the intelligence to make. I am far more afraid of machine stupidity than machine intelligence. … Machines can make many many good decisions and then one day fail spectacularly on a tail event that did not appear in their training data." (page 279) The unrestrained hype surrounding AI may have the unfortunate effect of making us too trusting, and thereby blind to Mullainathan's advice.
