You know the plot from every sci-fi movie that features artificial intelligence: the robot brain goes all ‘skynet’ and starts taking out humans. Even Stephen Hawking has warned that AI could be the “worst thing” for human beings.
So, um, brace yourself to get freaked out. Google now says it’s AI, known as DeepMind, is demonstrating highly aggressive tendencies when it’s in fear of losing a simulated game.
Last year, DeepMind showed its makers it was capable of learning independently, teaching itself to beat the world champion in a game of Go!.
But in the latest tests, two DeepMind agents were tasked with playing a game of ‘Gathering’ – a computer game where two people, or in this case computers, play against each other to collect the most apples.
The AI beings operated smoothly when there were enough apples to go around, but once the apples became more sparse, the DeepMind systems began using laser beams, or tagging, to knock the other one out, ensuring they could collect all the apples.
A blog post from the DeepMind team read: “We let the agents play this game many thousands of times and let them learn how to behave rationally using deep multi-agent reinforcement learning.
“Rather naturally, when there are enough apples in the environment, the agents learn to peacefully coexist and collect as many apples as they can.
“However, as the number of apples is reduced, the agents learn that it may be better for them to tag the other agent to give themselves time on their own to collect the scarce apples.”
“The greed motivation reflects the temptation to take out a rival and collect all the apples oneself.”
Yeah, that’s really… worrisome. Think about it the next time you ask Siri to help you with a problem….?