Slashdot Mirror
Hilarious (and Terrifying?) Ways Algorithms Have Outsmarted Their Creators (popularmechanics.com)
"Robot brains will challenge the fundamental assumptions of how we humans do things," argues Popular Mechanics, noting that age-old truism "that computers will always do literally, exactly what you tell them to."
A paper recently published to ArXiv highlights just a handful of incredible and slightly terrifying ways that algorithms think... An AI project which pit programs against each other in games of five-in-a-row Tic-Tac-Toe on an infinitely expansive board surfaced the extremely successful method of requesting moves involving extremely long memory addresses which would crash the opponent's computer and award a win by default...
These amusing stories also reflect the potential for evolutionary algorithms or neural networks to stumble upon solutions to problems that are outside-the-box in dangerous ways. They're a funnier version of the classic AI nightmare where computers tasked with creating peace on Earth decide the most efficient solution is to exterminate the human race. The solution, the paper suggests, is not fear but careful experimentation.
The paper (available as a free download) contains 27 anecdotes, which its authors describe as a "crowd-sourced product of researchers in the fields of artificial life and evolutionary computation. Popular Science adds that "the most amusing examples are clearly ones where algorithms abused bugs in their simulations -- essentially glitches in the Matrix that gave them superpowers."
These amusing stories also reflect the potential for evolutionary algorithms or neural networks to stumble upon solutions to problems that are outside-the-box in dangerous ways. They're a funnier version of the classic AI nightmare where computers tasked with creating peace on Earth decide the most efficient solution is to exterminate the human race. The solution, the paper suggests, is not fear but careful experimentation.
The paper (available as a free download) contains 27 anecdotes, which its authors describe as a "crowd-sourced product of researchers in the fields of artificial life and evolutionary computation. Popular Science adds that "the most amusing examples are clearly ones where algorithms abused bugs in their simulations -- essentially glitches in the Matrix that gave them superpowers."
These aren't really that terrifying. We just don't have the GPU power for re-enforcement learning like this to search for really out there solutions to problems at the moment. But they can produce really funny stories like this.
My favorite story is of a bot given the task of moving itself through a maze or somesuch (important part incoming). Anyway, the programmer decided the more time the bot spent away from the center of the maze the worse points it would get (it's trying to optimize for points here). But instead of going towards the center of the maze as fast as possible to maximize points it just couldn't figure out how to get through. So it sent itself off the virtual edge of the simulation area, ending the run and minimizing it's negative score as best as possible. By accident someone created a suicidal bot, yay!
And that is really the extend of "Deep Re-enforcement Learning" aka AI that teaches itself to do things today. Sometimes, like with Alpha Go, it works. But a lot of the time it does something stupid.
A friend of a friend got a part-time job loading coin-op candy machines. Rather than being paid by the hour, he was paid by the number of machines on his route; working fast or slow didn't matter. It didn't take him long to realize that the popular candy bars were the first to go and took the most time to restock. But one brand, the "Zero Bar" was distinctly unpopular. Before long, he had filled all the machines with Zero Bars and was able to keep the machines full with virtually no effort.