Experts suggest that having AI systems try to outwit one another could help a person judge their intentions.
The concept comes from researchers at OpenAI, a nonprofit founded by several Silicon Valley luminaries like Peter Thiel, Reid Hoffman or Elon Musk.
Take, for instance, an AI system designed to defend against human or AI hackers. To prevent the system from doing anything harmful or unethical, it may be necessary to challenge it with another AI system to explain the logic for a particular action.
MORE