We Don’t Really Know How A.I. Works. That’s a Problem. - The New York Times

For us to trust it on certain subjects, researchers in the growing field of interpretability might need to learn how to open the black box of its brain. Credit... Illustration by Max Guther Supported by By Oliver Whang When Deep Blue, IBM’s chess-playing supercomputer, beat Garry Kasparov in 1997, computers were still just computers. Deep Blue weighed more than a ton, had 32 central processing units and could evaluate 200 million board positions in a second, but everyone knew what it was doing: The computer determined the best next move by simulating, and assigning values to, board positions up to 12 moves ahead (amounting to billions of positions). This ability was programmed into Deep Blue directly by its makers, just as the first modern computer, the Electronic Numerical Integrator and Computer, or ENIAC, was programmed in 1945 to add numbers. These were “white box” systems. There was no mystery around what was going on inside them, even though they were, in a way, intelligent: What

saved by

• Adi Mehta