Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 Methodology 2 Methodology 2.1 The task 2.1 The task 2.2 The communication protocol 2.2 The communication protocol 2.3 The copula family 2.3 The copula family 3 Pair programming with ChatGPT 3 Pair programming with ChatGPT 3.1 Warm up 3.1 Warm up 3.2 The density 3.2 The density 3.3 The estimation 3.3 The estimation 3.4 The sampling 3.4 The sampling 3.5 The visualization 3.5 The visualization 3.6 The parallelization 3.6 The parallelization 4 Summary and discussion 4 Summary and discussion 5 Conclusion and Acknowledgments 5 Conclusion and Acknowledgments Appendix A: The solution in Python Appendix A: The solution in Python Appendix B: The solution in R Appendix B: The solution in R References References 3.2 The density Another formula quite similar to (4), but also this one is incorrect. As already mentioned before, ChatGPT is not a good option when it comes to reasoning. So, to get the right formula, some symbolic tool is definitely preferred. However, note that ChatGPT plugins[10] has been recently announced, and particularly Code interpreter, which is an experimental ChatGPT model that can use Python, handle uploads and downloads, allows for symbolic computations. Even if not freely available yet, this might be also a possible way to mitigate the problem, directly in the ChatGPT environment. Following our communication protocol, let us feed ChatGPT with the right formula, and ask for a corresponding function in three programming languages: 1) MATLAB[11], which represents a proprietary software, 2) Python[12], an opensource software popular in the AI community, and R [13], an open-source software popular in the statistical community. Note that in cases when the output is too wide, we adjust it in order to fit on the page; otherwise we do not adjust it in any other way. After feeding ChatGPT with the right formula, it immediately generated a functional code. Notice that we used quite a natural and relaxed form of conversation, e.g., like in an email. As ChatGPT takes into account the previous conversation, we could afford to be extremely concise with our prompts and still get correct solutions. In what follows, we ask for code only in MATLAB to save space. However, the equivalent code in Python and R is shown in the appendices, where all the functions can be easily identified by their names. 3.3 The estimation By contrast to our struggles with the PDF, we immediately got a correct solution. This may be due to the fact that code snippets computing ML estimators occur more frequently in ChatGPT’s training data. This pattern (the more general the task, the more frequently we receive a working solution on first trial) is observed also in other examples throughout this work. Author:
(1) Jan G´orecki, Department of Informatics and Mathematics, Silesian University in Opava, Univerzitnı namestı 1934/3, 733 40 Karvina, Czech Republic (gorecki@opf.slu.cz). Author: Author: (1) Jan G´orecki, Department of Informatics and Mathematics, Silesian University in Opava, Univerzitnı namestı 1934/3, 733 40 Karvina, Czech Republic (gorecki@opf.slu.cz). This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv available on arxiv [10] https://openai.com/blog/chatgpt-plugins [11] We used version R2020a. [12] Version 3.9. [13] Version 4.2.2.

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

ChatGPT, Symbolic Math, and the Struggle for Accuracy

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

11 Proven Solutions to Common GitHub Copilot Problems

Using AI to Build a Monte Carlo Simulation

Exploring AI Memory, Limitations, and Workarounds in Practice

Testing ChatGPT as a Pair Programming Partner

When AI Gets It Wrong—and Then Gets It Right

Debugging Copulas and Speeding Up Simulations with AI

11 Proven Solutions to Common GitHub Copilot Problems

Using AI to Build a Monte Carlo Simulation

Exploring AI Memory, Limitations, and Workarounds in Practice

Testing ChatGPT as a Pair Programming Partner

When AI Gets It Wrong—and Then Gets It Right

Debugging Copulas and Speeding Up Simulations with AI

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps