# Questions of science: chatting with ChatGPT about complex systems

**Authors:** Nuno Crokidakis, Marcio Argollo de Menezes, Daniel O. Cajueiro  
**arXiv:** [2303.16870](https://arxiv.org/abs/2303.16870)  
**Date:** 2023-03-29  
**Summary page:** https://www.summarizepaper.com/en/paper/2303.16870v1/

## Key points

- The study presents an overview of the complex systems field using ChatGPT, a large language model trained on a vast dataset of internet texts.
- The paper is divided into two parts: teaching and learning, where ChatGPT may work as a teacher assistant; and research, where ChatGPT works like a research assistant.
- Researchers and scientists studying and developing in the field of complex systems have made significant contributions.
- Half of the physics Nobel prize of 2021 was awarded to Giorgio Parisi for his contributions to the theory of complex systems; while Syukuro Manabe and Klaus Hasselmann were awarded for their modeling of Earth's climate.
- ChatGPT has demonstrated remarkable abilities to perform tasks such as completion tasks, question answering, reading comprehension, and translation that were once thought to be exclusive to humans.
- It is essential to use it carefully because if the data it uses to learn about the community has biases, ChatGPT may also learn and reproduce those biases.
- The study provides valuable insights into how ChatGPT can be used as a tool for understanding community ideas on teaching and research in complex systems.
- It highlights some challenges faced by researchers in this field such as dealing with complexity and uncertainty.

## Summary

This study presents an overview of the complex systems field using ChatGPT, a large language model trained on a vast dataset of internet texts. The authors explore both teaching and research topics in the field and recognize the value of ChatGPT as a source for the community's ideas. The paper is divided into two parts: the first part focuses on issues related to teaching and learning, where ChatGPT may work as a teacher assistant; while the second part explores issues related to research, where ChatGPT works like a research assistant. The authors note that we are currently in an era where researchers and scientists studying and developing in the field of complex systems have made significant contributions. For instance, half of the physics Nobel prize of 2021 was awarded to Giorgio Parisi for his contributions to the theory of complex systems; while Syukuro Manabe and Klaus Hasselmann were awarded for their modeling of Earth's climate. The diversity of research topics among these award recipients highlights the multidisciplinary nature of the field. ChatGPT has demonstrated remarkable abilities to perform tasks such as completion tasks, question answering, reading comprehension, and translation that were once thought to be exclusive to humans. However, it is essential to use it carefully because if the data it uses to learn about the community has biases, ChatGPT may also learn and reproduce those biases. Overall, this study provides valuable insights into how ChatGPT can be used as a tool for understanding community ideas on teaching and research in complex systems. It also highlights some challenges faced by researchers in this field such as dealing with complexity and uncertainty.