Even when artificial intelligence behaves exactly like a human, people are reluctant to consider it conscious, according to a new study from Ludwig Maximilian University of Munich (LMU). As artificial intelligence becomes more advanced, reports of AI systems misleading users, working together, or appearing to pursue independent goals are becoming increasingly common. These behaviors often lead people to describe AI as though it can think, feel, or make decisions for itself.
But does behaving like a human actually convince people that a machine has consciousness? New research from LMU suggests that people make a clear distinction between displaying intelligent behavior and possessing a conscious mind, even when humans and AI act in precisely the same way. How Scientists Tested Perceptions of AI Consciousness Published in the journal Cognition, the study was led by Dr.
Louis Longin of LMU's Chair of Philosophy of Mind, working alongside Dr. Bahador Bahrami, Professor Ophelia Deroy, and other researchers. "Whereas previous studies have typically asked general questions about whether AI actually has mental states, our study is the first to directly compare how people attribute the same mental states to AI and humans behaving in exactly the same way, under identical circumstances," says Longin.
"We may be using mental terms to refer to AI, but this may only be because we lack better words," says Ophelia Deroy, philosopher and a senior author of the study. "After all, AI is trained to act and speak like a human, so these descriptions seem natural." To investigate how people judge consciousness, the researchers conducted experiments involving nearly 1,100 participants. One group read brief descriptions of artificial agents that showed different levels of responsiveness to their environments.
For example, some agents reacted to sounds or recognized the emotional states of others. Another group encountered the same situations, except the characters were described as humans rather than AI systems. Participants then evaluated how conscious or aware each character seemed to be of its surroundings.
A Surprising Gap Between Human and AI Consciousness The experiments revealed that responsiveness influenced how participants judged both humans and artificial intelligence. Characters that reacted more actively to their surroundings were generally considered more conscious and more aware. However, a striking difference emerged when participants evaluated consciousness specifically.
Extract — continue reading at the source.
