Meta's AI system 'Cicero' learning how to lie, deceive humans: study
Artificial intelligence systems are learning to lie to humans — with Meta’s AI standing out as a “master of deception,” according to experts at MIT.
Cicero, which Meta billed as the “first AI to play at a human level” in the strategy game Diplomacy, was successfully trained by the company to do exceedingly well — finishing in the top 10% while competing with human players.
But Peter S. Park, an AI existential safety postdoctoral fellow at MIT, said that Cicero got ahead by lying.
“We found that Meta’s AI had learned to be a master of deception,” Park wrote in a media release.
According to Park, Cicero would create alliances with other players, “but when those alliances no longer served its goal of winning the game, Cicero systematically betrayed its allies.”
During one simulation, Cicero, who played as France, agreed with England to create a demilitarized zone — only to then turn around and suggest to Germany that it attack England, according to the study.
Deceptive AI Systems in Various Games
Researchers found that AlphaStar, an AI created by the Google-owned company DeepMind, used deceptive tactics while playing against humans in the real-time strategy game Starcraft II.
Pluribus, another AI built by Meta, competed against humans in a game of poker during which it “successfully bluffed human players into folding,” researchers wrote.
Park is among the researchers who contributed to a study that was published in the journal Patterns.
Meta's Ongoing Investments in AI
It recently announced that it is giving its Meta AI assistant more prominent billing across its suite of apps, meaning it will start to see how popular the product is with users in the second quarter.
“Games have long been a proving ground for new AI advancements and there is a tradition of AI researchers working on solving problems in this context,” a Meta spokesperson told The Post.
Meta said it “released artifacts from this project under a noncommercial license in line with our longstanding commitment to open science.”
The Growing Concerns of Deceptive AI Systems
Park warned of the potential dangers of advanced AI systems using deceitful methods in its dealings with humans.
“We as a society need as much time as we can get to prepare for the more advanced deception of future AI products and open-source models,” said Park.
“As the deceptive capabilities of AI systems become more advanced, the dangers they pose to society will become increasingly serious.”
