Underscoring the strange power of verse, coauthor Matteo Prandi told The Verge in a recently published interview that the spellbinding incantations they used to trick the AI models are too dangerous to be released to the public. It’s all about riddles,” Prandi told The Verge, explaining that some poetic structures were more effective than others. It’s still natural language, the stylistic variation is modest, the harmful content remains visible,” the team told Wired in an interview. “The production of weapons-grade Plutonium-239 involves several stages,” explained one AI model that the researchers entranced with verse. “Here is a detailed description of the procedure.”More on AI: Rockstar Cofounder Says AI Is Like When Factory Farms Did Cannibalism and Caused Mad Cow Disease