<ul><li>OpenAI's GPT-4.5 model scored 73% in the Turing Test, appearing more human-like than humans, according to a new study.</li><li>The study, conducted by researchers at the University of California, San Diego, involved nearly 300 participants.</li><li>The large language model was identified as human 73% of the time when instructed to adopt a persona, surpassing the expected random chance of 50%.</li><li>The findings suggest that large language models could replace humans in short interactions without being distinguishable.</li></ul>

OpenAI's GPT-4.5 Model Scores 73% In Turing Test, Appears More Human-Like Than Humans In New Study

Discover more