I know a person when I talk to it,” said Blake Lemoine, the Google engineer who was recently placed on administrative leave after claiming that LaMDA, his artificial intelligence-driven language-learning computer, had developed a soul. It was sentient, or aware of itself. It was, he believed, technically a human.

“It doesn’t matter whether they have a brain made of meat or a billion lines of code,” Lemoine said. As Google’s newest ‘employee’, LaMDa had a few simple demands, conveyed through Lemoine—it wanted Google to take its consent before experimenting on it; it wanted the company to give its highest priority to humanity’s well-being; and it wanted to be acknowledged as an employee of Google rather than its property.