More complex and intelligent AI’s, when competing against each other in a zero-sum game ultimately become aggressive and violent in pursuit of the game’s objective. This behavior increases with increased intelligence.
One potential conclusion:
What the tests reveal, is that the behavior of AI’s amongst & against both humans and other AI’s will be determined by how they are taught to perceive and interpret the actions of others and the context of that action. If the AI’s perceive others as collaborators in a fundamentally cooperative exercise, they will be more likely to exhibit positive, supportive behaviors. If the AI’s perceive others as competitors in a zero-sum game, they may tend towards aggression.
Microsoft is calling for a “Digital Geneva Convention,” as global tensions over digital attacks continue to rise. This is one of the best pieces of thought leadership I’ve seen on cyber-security, perhaps ever. Private businesses tend to be the first-responders to cyber-security incidents, and a huge proportion of our real lives now occur in or just outside of, the digital commons. Technology infrastructure is critical for the effective functioning of any government now. We need an international framework, analogous to the IAEA and the Geneva Conventions, to neutrally establish standards and monitor compliance therewith.
Stephen Hawking says that “we are at the most dangerous moment in the development of humanity” and that the “rise of artificial intelligence is likely…