Does GPT-4 pass the Turing test?

arXiv:2310.20216v2 Announce Type: replace-cross
Abstract: We evaluated GPT-4 in a public online Turing test. The best-performing GPT-4 prompt passed in 49.7% of games, outperforming ELIZA (22%) and GPT-3.5 (20%), but falling short of the baseline set by human participants (66%). Participants' decisions were based mainly on linguistic style (35%) and socioemotional traits (27%), supporting the idea that intelligence, narrowly conceived, is not sufficient to pass the Turing test. Participant knowledge about LLMs and number of games played positively correlated with …

abstract arxiv cs.ai cs.cl decisions eliza games gpt gpt-3 gpt-3.5 gpt-4 human prompt public set style test turing turing test type