GPT-4 TURBO: EXPANDING THE BOUNDARIES OF ARTIFICIAL INTELLIGENCE THROUGH API INTEGRATION

B. R. Tanatova, V. P. Kulikov

2023

Full text Open access: Hybrid Metadata (CSL-JSON)

DOI 10.54596/2958-0048-2023-4-140-147

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

GPT-4 Turbo represents a new milestone in the development of artificial intelligence (AI), providing unique opportunities for API integration into proprietary developments. This algorithm, based on the GPT-4 architecture, not only improves the quality of natural language, but also provides high performance and efficiency in a wide variety of tasks. In this article, we will look at the key characteristics of the GPT-4 Turbo, as well as consider the prospects for its implementation through the API in various areas.