Google’s Artificial Intelligence Learns “Highly Aggressive” Behavior, Concept of Betrayal – HealthyTipsAdvice

Google made news again recently, after it’s artificial intelligence program learned “highly aggressive” behavior.



In particular, the AI program was working through a couple of learning scenarios, including a wolfpack hunting game and a fruit gathering game. 



While the wolfpack game required cooperation, the fruit game was dependent on individual effort from each AI.


In turn, researchers found that as the fruit squares were more limited, the AI become more aggressive – even attacking other players in the scenarios. 

When less fruit was available, the attacks were more frequent.

As Extreme Tech notes:

Guess what the neural networks learned to do. Yep, they shoot each other a lot. As researchers modified the respawn rate of the fruit, they noted that the desire to eliminate the other player emerges “quite early.” When there are enough of the green squares, the AIs can coexist peacefully. When scarcity is introduced, they get aggressive. They’re so like us it’s scary. 


While Google’s AI program is still in the relatively early stages, it isn’t hard to imagine a dystopian future controlled by robots, is it?

If you enjoyed this article or learned something new, please don’t forget to share it with others so they have a chance to enjoy this free information. This article is open source and free to reblog or use if you give a direct link back to the original article URL. Thanks for taking the time to support an open source initiative. We believe all information should be free and available to everyone. Have a good day and we hope to see you soon!
Please follow and like us: