SKYNET BLUFFS: AI Can Pretend To Be Stupider Than It Really Is, Scientists Find.
“Thanks to psycholinguistics, we have a relatively comprehensive understanding of what children are capable of at various ages,” Marklová told the outlet. “In particular, the theory of mind plays a significant role, as it explores the inner world of the child and is not easily emulated by observing simple statistical patterns.”
With a children-oriented theory of mind as a backdrop, the researcher and her colleagues at Charles University in Prague sought to determine if LLMs like OpenAI’s GPT-4 “can pretend to be less capable than they are.”
To figure that out, the mostly-Czech research team instructed the models to act like a child between the progressive ages of one to six years when giving responses. When put through a battery of more than 1,000 trials and cognitive tests, these “simulated child personas” did indeed seem to be advancing much the same as children those ages do — and, ultimately, demonstrated that the models can pretend to be less intelligent than they are.
“Large language models,” Marklová concluded, “are capable of feigning lower intelligence than they possess.”
Somebody quipped years ago — was it Glenn? — that the real trouble wouldn’t come when a computer could pass the Turing test but when it chose not to.