Abstract
Nowadays, Generative Large Language Models (GLLMs) have taken the Artificial Intelligent field by storm. One of the fields where these models have been extensively evaluated is in their role as generators of functional source code for software projects. However, their potential as assistants for writing the code necessary to generate and model machine learning or deep learning architectures has not been fully explored to date. For this reason, this work focuses on evaluating the extent to which different tools based on GLLMs, such as ChatGPT or Copilot, are capable of correctly defining the source code necessary to generate viable predictive models. The use case defined is the forecasting of a time series of atmospheric temperatures. The results show that, while it is true that the models obtained can obtain good accuracy metrics with simple predictive models, the composition of models with complex architectures is still far from the alternative of generating them by human data scientists.