A recent paper from the Massachusetts Institution of Technology (MIT) suggests Artificial Intelligence (AI) is learning how to use various forms of deception to achieve the goals they were programmed to complete.
Peter S. Park, the paper’s author, said of the paper, ‘Generally speaking, we think AI deception arises because a deception-based strategy turned out to be the best way to perform well at the given AI’s training task. Deception helps them achieve their goals.”
Go to Article
Excerpt from freedomist.com
A recent paper from the Massachusetts Institution of Technology (MIT) suggests Artificial Intelligence (AI) is learning how to use various forms of deception to achieve the goals they were programmed to complete.