On the question of the specifics of the formulation and use of the Turing test for the ChatGPT

Abstract

The subject of the research in this article are the features and regularities of the functioning of systems based on ChatGPT technologies, the knowledge of which makes it possible to formulate appropriate modifications of the Turing test, as well as the features and regularities of the formulation and use of the Turing test for systems based on ChatGPT technologies. The purpose of the study is to identify the features and patterns of functioning of systems based on the technologies of ChatGPT, as well as the features and patterns of formulation and use of the Turing test for systems based on the technologies of Chat GPT. As research methods, the method of social experiment was used, when during the study of a system based on Chat GPT technologies, certain questions were asked, answers were received, the analysis of which allowed us to conclude about the features of the "thinking" of systems based on ChatGPT technologies. In the course of the study, the following was found. Unlike human thinking, which is based on certain facts, the "thinking" of systems based on ChatGPT technologies, in some cases is not based on facts that take place in reality, often the user is given deliberately false information about facts and circumstances that take place in reality. In contrast to human thinking, which is usually systemic in nature, the "thinking" of systems based on ChatGPT technologies is disorderly and fragmentary. Systems based on ChatGPT technologies cannot admit their mistakes, and attempts to force systems based on ChatGPT technologies to critically comprehend their answers lead to a malfunction of these systems. The article also provides a Turing test developed by the author for ChatGPT, which made it possible to identify the features of the "thinking" of systems based on ChatGPT technologies.