Can Artificial Intelligence Robots Write Effective Instructions?

Johndan Johnson-Eilola Clarkson University ; Stuart A. Selber Pennsylvania State University ; Eric J. York Clarkson University

Abstract

The authors analyze the ability of ChatGPT to generate effective instructions for a consequential task: taking a COVID-19 test. They compare the output from a commercial prompt for generating these instructions to those provided by the test manufacturer. They also analyze the input, the prompt itself, to address prompt-engineering issues. The results show that although the output from ChatGPT exhibits certain conventions for documentation, the human-authored instructions from the manufacturer are superior in most ways. The authors conclude that when it comes to creating high-quality, consequential instructions, ChatGPT might be better seen as a collaborator than a competitor with human technical communicators.

Journal
Journal of Business and Technical Communication
Published
2024-07-01
DOI
10.1177/10506519241239641
Open Access
Closed
Topics

Citation Context

Cited by in this index (9)

  1. Journal of Technical Writing and Communication
  2. Journal of Technical Writing and Communication
  3. Written Communication
  4. Journal of Business and Technical Communication
  5. Technical Communication Quarterly
Show all 9 →
  1. College Composition and Communication
  2. Technical Communication Quarterly
  3. Technical Communication Quarterly
  4. Journal of Technical Writing and Communication

Cites in this index (2)

  1. Poroi
  2. Technical Communication Quarterly
Also cites 3 works outside this index ↓
  1. 10.37514/TPC-B.2023.1923.2.10
  2. Felten E., Raj M., Seamans R. (2023). How will language modelers like ChatGPT affect occupations and industri…
  3. Wang L., Xu W., Lan Y., Hu Z., Lan Y., Lee R. K. W., Lim E. P. (2023). Plan-and-solve prompting: Improving ze…
CrossRef global citation count: 13 View in citation network →