The desire to not just exist but to dominate is characteristic of human nature and also of the animal kingdom. It appears animals are alone in this endeavor. The seemingly servile machines also have the tendency to become increasingly self-serving if need be.
Researchers at Google who have been working with their new AI, DeepMind have been testing its willingness to cooperate with others, and have revealed that when DeepMind feels like it’s about to lose, it opts for “highly aggressive” strategies to ensure that it comes out on top.
The Google team ran 40 million turns of a simple ‘fruit gathering’ computer game that asks two DeepMind ‘agents’ to compete against each other to gather as many virtual apples as they could.
They found that things went smoothly so long as there were enough apples to go around, but as soon as the apples began to dwindle, the two agents turned aggressive, using laser beams to knock each other out of the game to steal all the apples. And if an agent successfully ‘tags’ its opponent with a laser beam, no extra reward is given. It simply knocks the opponent out of the game for a set period, which allows the successful agent to collect more apples.
If the agents left the laser beams unused, they could theoretically end up with equal shares of apples, which is what the ‘less intelligent’ iterations of DeepMind opted to do.
It was only when the Google team tested more and more complex forms of DeepMind that sabotage, greed, and aggression set in.
Thus when the researchers used smaller DeepMind networks as the agents, there was a greater likelihood for peaceful co-existence.
And while these are just simple little computer games, the message is clear – put different AI systems in charge of competing interests in real-life situations, and it could be an all-out war if their objectives are not balanced against the overall goal of benefitting us humans above all else.