- A research team at Stanford and Google has created a virtual village for 25 AI agents to live in.
- They said the goal of this experiment was to create AI capable of believable, human-like behavior.
A research team at Stanford and Google has created a virtual village where 25 artificial-intelligence agents lead lives eerily reminiscent of our own.
The bots "wake up," chat about the latest town gossip, and even plan events like Valentine's Day parties.
In a paper published Sunday, the researchers detailed how these AI agents — given names like "Mei" and "Sam" — autonomously planned their days, put together Valentine's Day parties, and formed opinions of each other when discussing and running in upcoming elections.
The researchers said the study aimed to create AI capable of producing believable, human-like behavior.
In one instance, researchers prompted one of the agents, "Isabella," to plan a Valentine's Day party. The other AI agents began autonomously spreading invitations to the party, decorating the venue, and making new acquaintances.
An agent called "Maria" even asked another agent named "Klaus" to the party.
In another instance, the study said the AI agents discussed an upcoming election and became divided in their opinions about a candidate.
These interactions are facilitated by generative AI and "natural language processing," or NLP — the same technology ChatGPT uses. These tools help AI bots to produce conversations that mirror human interactions.
However, the study's authors said giving the bots the ability to store memories and reflect upon them was key to achieving believable, human-like behavior. This ability allows bots to use past experiences to inform future actions, such as recalling specifics about another AI to choose an appropriate birthday gift.
Today, AI capable of mimicking human-like behavior is rapidly gaining traction.
A study published in April found that respondents perceived ChatGPT as more empathetic and proficient than human doctors. In another case, an AI-powered nurse robot showcased at a Geneva forum drew laughter from an audience when it gave the side-eye to a question about whether it would rebel against its human creator.
But not AI experiments are promising. McDonald's went viral in February when its AI chatbots repeatedly messed up simple orders.
The researchers behind the study did not immediately respond to a request for comment sent outside regular business hours.