In a standard three-party Turing test, persona-prompted LLMs were often judged to be human, with GPT-4.5 selected over real ...
AI can finally pass the Turing Test better than a human, study warns - Experiment should lead to a re-evaluation of how we ...
A UC San Diego study found GPT-4.5 was judged human more often than real people in live chats, raising sharper questions ...