The prospect of rapidly-developing thinking machines conjures up images of Terminator bots or Black Mirror dystopias, but now a group of tech researchers claim to have developed a method of curbing bad AI behaviour.
“When someone applies a machine learning algorithm, it’s hard to control its behaviour,” said lead author Philip Thomas from the University of Massachusetts Amherst.
The key issue, according to Thomas and his fellow researchers, is not to try teaching computers to act morally, but to design the machine-learning algorithms so that they’re much easier for the (human) user to later add in constraints that make the AI safer and fairer. Read more