1960s chatbot ELIZA beats OpenAI's GPT-3.5 in Turing test

ELIZA, a chatbot built in the 1960s, beat OpenAI's GPT-3.5 in Turing test conducted by researchers from UC San Diego in the US. The Turing test has been the benchmark for determining a machine’s ability to imitate human conversation. ELIZA was able to pass itself off as human 27% of the time, while GPT-3.5 had success rate of just 14%.