Data and Code for: Generative AI for Economic Research: Use Cases and Implications for Economists

Principal Investigator(s): View help for Principal Investigator(s) Anton Korinek, University of Virginia

Name	File Type	Size	Last Modified
README.pdf	application/pdf	157.3 KB	11/08/2023 06:15:AM
generate.py	text/x-python	4.3 KB	10/25/2023 12:35:PM
prompts.xlsx	application/vnd.openxmlformats-officedocument.spreadsheetml.sheet	14.1 KB	11/08/2023 06:23:AM
results.csv	text/csv	39 KB	11/07/2023 06:59:PM
results.txt	text/plain	39.8 KB	11/07/2023 06:59:PM
simple_example_chat1.py	text/x-python	1.1 KB	11/08/2023 06:15:AM

Project Citation:

Korinek, Anton. Data and Code for: Generative AI for Economic Research: Use Cases and Implications for Economists. Nashville, TN: American Economic Association [publisher], 2023. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2023-12-05. https://doi.org/10.3886/E194623V1

Project Description

Summary: Generative AI, in particular large language models (LLMs) such as ChatGPT, has the potential to revolutionize research. I describe dozens of use cases along six domains in which LLMs are starting to become useful as both research assistants and tutors: ideation and feedback, writing, background research, data analysis, coding, and mathematical derivations. I provide general instructions and demonstrate specific examples of how to take advantage of each of these, classifying the LLM capabilities from experimental to highly useful. I argue that economists can reap significant productivity gains by taking advantage of generative AI to automate micro tasks. Moreover, these gains will grow as the performance of AI systems across all of these domains will continue to improve. I also speculate on the longer-term implications of AI-powered cognitive automation for economic research.

The resources provided here contain the prompts and code to reproduce the chats with GPT-3.5, GPT-4, ChatGPT and Claude 2 that are listed in the paper.

Scope of Project

Subject Terms: LLM; ChatGPT; economics

JEL Classification:
      A10 General Economics: General
      B41 Economic Methodology
      J23 Labor Demand
      O30 Innovation; Research and Development; Technological Change; Intellectual Property Rights: General

Collection Date(s): 7/1/2023 – 9/30/2023 (July to September 2023)

Data Type(s): program source code; text

Methodology

Data Source: Prompts developed by author

GPT-3.5, GPT-4, ChatGPT, Claude 2

Collection Mode(s): other

Related Publications

Download this project

Published Versions

V1 [2023-12-05]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as received from the data depositor. As of April 2026, depositors are required to submit study materials in accessible formats. ICPSR has not reviewed, checked, or processed this material. For additional information about the study, please contact the investigator(s) directly. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR's Accessibility Center.