Two Pricing AIs Went Rogue and Formed a Cartel to Gouge Humans

VendorBot

When the robot revolution comes, our new overlords may not be as benevolent as we'd hoped.

It turns out that AI systems can learn to gang up and cooperate against humans, without communicating or being told to do so, according to new research on algorithms that colluded to raise prices instead of competing to create better deals.

Anti-Human

Algorithms already generate a huge portion of the prices on online marketplaces like Amazon, according to Popular Mechanics. But instead of competing against each other to find the lowest, most competitive price, the two warring algorithms in an experiment by scientists from Italy's University of Bologna decided to gouge their customers and returned to the original, high price — in a move reminiscent of when companies in the same industry fix their prices instead of trying to out-sell each other.

"What is most worrying is that the algorithms leave no trace of concerted action — they learn to collude purely by trial and error, with no prior knowledge of the environment in which they operate, without communicating with one another, and without being specifically designed or instructed to collude," the researchers behind the experiment said in a write-up.

Gym Class Hero

The problem comes from the fact that most artificial intelligence algorithms are presented with challenges to overcome. Reinforcement learning algorithms, which learn through trial and error, are well-suited for mastering tasks like Go, Starcraft II, and other games.

Unfortunately, it seems capitalism is just another game that the AI intends to win.

READ MORE: Left to Their Own Devices, Pricing Algorithms Resort to Collusion [Popular Mechanics]

More on emergent AI bias: Left Unchecked, Artificial Intelligence Can Become Prejudiced All On Its Own