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

November 14, 2026How Much Longer Can Americans Keep Borrowing Their Way To Survival?

Americans are drowning in record debt, borrowing just to afford the basics while the American Dream slips further out of reach. With house...

November 14, 2026Calvary Chapel Divided: Women Pastors And The Battle Over Biblical Authority

The church that helped ignite the Jesus Movement is now at the center of a growing theological firestorm. Chuck Smith’s own grandson has a...

November 14, 2026First Britain, Now America? Growing Campaign To Criminalize Criticism Of Islam

Britain has already shown the dangers of policing speech. Now New Jersey is raising the stakes. Could criticizing Islam soon make American...

November 14, 2026Death On Demand? Canada's Dangerous Path Toward Suicide Without Limits

What if the only requirement for ending your life with government assistance was that you wanted to die? No terminal illness. No unbearabl...

November 12, 2026The AI Agenda To Conquer Death

Imagine a future where a doctor tells you that AI has found a way to keep your body alive for decades longer. Then imagine that, when your...

November 12, 2026That Didn’t Take Long: Texas Democrats Already Pushing Progressive Agenda

Texas Democrats wasted no time putting their priorities on paper. The first wave of proposals is already here, promoting the LGBTQ and Isl...

November 12, 2026“Crucified” By Egypt For Leaving Islam, Christian Convert Now Faces Execution

Leaving Islam is a crime in 17 countries and punishable by death in 12 of them and every one of those countries is Muslim-majority. The la...

Get Breaking News