the Tetris playing bot that "paused the game indefinitely to avoid losing". These agents didn't necessarily hack their reward functions but they did take a far easiest path to their goals, e.g. Eventually it "starts transforming first all of Earth and then increasing portions of space into paperclip manufacturing facilities".īut some of this is The Lebowski Theorem of machine superintelligence in action. It devotes all its energy to acquiring paperclips, and to improving itself so that it can get paperclips in new ways, while resisting any attempt to divert it from this goal. Imagine an artificial intelligence, he says, which decides to amass as many paperclips as possible. The "paperclip maximiser" is a thought experiment proposed by Nick Bostrom, a philosopher at Oxford University. That second item is a doozy! Philosopher Nick Bostrom has warned of the dangers of superintelligent agents that exploit human error in programming them, describing a possible future where an innocent paperclip-making machine destroys the universe. In an artificial life simulation where survival required energy but giving birth had no energy cost, one species evolved a sedentary lifestyle that consisted mostly of mating in order to produce new children which could be eaten (or used as mates to produce more edible children).Īgent kills itself at the end of level 1 to avoid losing in level 2.ĪI trained to classify skin lesions as potentially cancerous learns that lesions photographed next to a ruler are more likely to be malignant. Neural nets evolved to classify edible and poisonous mushrooms took advantage of the data being presented in alternating order, and didn't actually learn any features of the input images. This spreadsheet lists a number of ways in which AI agents "cheat" in order to accomplish tasks or get higher scores instead of doing what their human programmers actually want them to.
0 kommentar(er)
