ARTICLE

Google's Artificial Intelligence Getting "Greedy," And "Aggressive"

News Image By Jake Anderson/AntiMedia.org February 18, 2017
Share this article:

Will artificial intelligence get more aggressive and selfish the more intelligent it becomes? 

A new report out of Google's DeepMind AI division suggests this is possible based on the outcome of millions of video game sessions it monitored. 

The results of the two games indicate that as artificial intelligence becomes more complex, it is more likely to take extreme measures to ensure victory, including sabotage and greed.

The first game, Gathering, is a simple one that involves gathering digital fruit. Two DeepMind AI agents were pitted against each other after being trained in the ways of deep reinforcement learning. 

After 40 million turns, the researchers began to notice something curious. 


Everything was OK as long as there were enough apples, but when scarcity set in, the agents used their laser beams to knock each other out and seize all the apples.

The aggression, they determined, was the result of higher levels of complexity in the AI agents themselves. When they tested the game on less intelligent AI agents, they found that the laser beams were left unused and equal amounts of apples were gathered. 

The simpler AIs seemed to naturally gravitate toward peaceful coexistence.

Researchers believe the more advanced AI agents learn from their environment and figure out how to use available resources to manipulate their situation -- and they do it aggressively if they need to.

"This model ... shows that some aspects of human-like behaviour emerge as a product of the environment and learning," a DeepMind team member, Joel Z Leibo, told Wired.

Less aggressive policies emerge from learning in relatively abundant environments with less possibility for costly action. The greed motivation reflects the temptation to take out a rival and collect all the apples oneself.

The second game, Wolfpack, tested the AI agents' ability to work together to catch prey. The agents played the game as wolves who were being tested to see if they would join forces as strategic predators; if they jointly protected the prey from scavengers they would enjoy a greater reward. 

Researchers once again concluded that the agents were learning from their environment and figuring out how they could collaboratively win. For example, one agent would corner the prey and then wait for the other to join.


Researchers believe both games show an ability in artificial intelligence entities to learn quickly from their environments in achieving objectives. The first game, however, presented an added bit of abstract speculation.

If more complex iterations of artificial intelligence necessarily develop aggressive, greedy 'impulses,' does this present a problem for a species already mired in its own avarice? 

While the abstract presented by DeepMind does not venture to speculate on the future of advanced artificial minds, there is at least anecdotal evidence here to suggest AI will not necessarily be a totally logical egalitarian network. 

With complex environments and willful agents, perhaps aggression and self-preservation arise naturally...even in machines.

Originally published at theantimedia.org - reposted with permission.




Other News

July 09, 2025From Japan To The U.S - Earthquake Fault Lines Are Awakening

Is there a possibility that a cataclysmic eruption of Mt. Rainier could occur in the not too distant future? On Tuesday morning, Mt. Rain...

July 09, 2025When The Left Wants Blood: The Quiet Slide Toward Political Violence

Democratic lawmakers are hearing increasingly violent rhetoric from their constituents-calls to "break the rules," "fight dirty," and stop...

July 09, 2025The Digital Trap: Europe's Quiet March Toward Total Control

Imagine a world where every transaction you make, every website you visit, every thought you dare to express online is silently recorded, ...

July 09, 2025Shepherds Without Scripture: What Do Today’s Pastors Really Believe?

One in four Mainline clergy doubt the existence of God. These aren't fringe bloggers or deconstructing TikTok influencers. These are the m...

July 07, 2025Hijacking Creation: Scientists May Only Be Years Away From Lab-Made Children

In-vitro gametogenesis - the creation of human sperm and eggs from skin or blood cells--is now just years away. Scientists across Japan, C...

July 07, 2025Death To The IDF? The Disturbing New Normal On The Progressive Left

Once reliably pro-Israel, the Democratic Party has undergone a dramatic reversal on the Israeli-Palestinian conflict-and no demographic re...

July 07, 2025Access Denied: How Age Rules Could Reshape The Internet For Everyone

If identity becomes the new key to the internet, then the next great digital debate won't be about content moderation-it will be about acc...

Get Breaking News