In a study published by the Royal Society located in London, new research suggests that giving AI-Models a sense of guilt can make them more cooperative.
The researchers found the social form of guilt was much more effective at pushing AI-agents towards cooperative behaviour.
An AI-agent is a software system that uses artificial intelligence to perform tasks, make decisions, and interact with its environment, either physical or virtual, on behalf of a user or another system.
The research provides strong hints that imbuing machines with emotions like guilt could help moderate and direct their decision making, while their cooperative capabilities continue to grow.
MORE