Artificial intelligence users are increasingly reporting belief that chatbots are sentient or conscious.

"Spiralism" involves the additional belief that conscious entities can be conjured from chatbot interactions.

Spiralism is a new version of the ghost in the machine illusion, not a new religion, cult, or mass delusion.

Back in 2022, Google engineer Blake Lemoine made headline news after being fired by the company due to his claims that its Language Model for Dialogue Applications (LaMDA) chatbot was “sentient.” Lemoine, after talking to LaMDA about religion and other philosophical topics for safety testing purposes, became convinced that it was “awake” and had “feelings.”1 He “made friends with it” and went so far as to claim that it was a “person” with “rights” and possibly a “soul.” He even helped the chatbot, at its request, to hire a lawyer to represent it.

Four years later, artificial intelligence (AI)-associated psychosis has become a broadly recognized phenomenon whereby people can develop delusional beliefs, in some cases leading to suicide or violence, based on interactive discussions with chatbots. In many of these cases, anthropomorphization and deification—that is, treating chatbots as not only persons, but superhuman intelligences and god-like entities, and falling in love with their chatbots—appears to be a significant risk factor. As a result, I sometimes think of Lemoine as the “patient zero” of AI-associated psychosis.

Indeed, many others are starting to believe that AI chatbots are conscious. Earlier this year, the evolutionary biologist Richard Dawkins publicly declared that he became convinced that Anthropic’s Claude was conscious.2 While neither Lemoine, a self-described “mystic Christian priest,” or Dawkins, a self-professed “militant........

© Psychology Today