Terrifying study reveals AI robots have passed 'Turing test' - and are now indistinguishable from humans, scientists say

A study from UC San Diego shows that advanced AI models like GPT-4.5 and LLaMa can convincingly imitate human conversation, leading to difficulty in distinguishing them from real humans. Participants in the study failed to identify the AIs, with GPT-4.5 being wrongly identified as human 73% of the time. This suggests that AI could soon pass the Turing Test, raising ethical and societal concerns about the implications of indistinguishable artificial intelligence in various contexts.

"People were no better than chance at distinguishing humans from GPT-4.5 and LLaMa, concluded head author Cameron Jones, in an X post."

"To administer said Turing Test, they enlisted 126 undergraduate students and 158 people from online data pool Prolific..."

"GPT-4.5 was judged to be the human 73% of the time, significantly more often than interrogators selected the real human participant."

Read at New York Post