Once upon a time, a bot deep in a game of tic-tac-toe figured out that making improbable moves caused its bot opponent to crash. Smart. Also sassy... even with logical parameters, it turns out that mathematical optimization empowers bots to develop shortcuts humans didn’t think to deem off-limits. Teach a learning algorithm to fish, and it might just drain the lake.
Earlier this year, researchers at the University of Freiburg in Germany challenged a bot to score big in the Atari game Qbert. Instead of playing through the levels like a sweaty-palmed human, it invented a complicated move to trigger a flaw in the game, unlocking a shower of ill-gotten points.
Infanticide: In a survival simulation, one AI species evolved to subsist on a diet of its own children.
Optical Illusion: Humans teaching a gripper to grasp a ball accidentally trained it to exploit the camera angle so that it appeared successful—even when not touching the ball.
No comments:
Post a Comment
Due to a small but consistent influx of spam, comments will now be checked before publishing. Only egregious spam/illegal/racist crap will be disapproved, everything else will be published.