Benchmarking AI design skills: insights from ChatGPT's participation in a prototyping hackathon
Proceedings of the Design Society · 2024-05 · 4 · 1999-2008
DOI: 10.1017/pds.2024.202 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 16.05.2024. Verfasst von Daniel Nygård Ege und 5 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This study provides insights into the capabilities and performance of generative AI, specifically ChatGPT, in engineering design. ChatGPT participated in a 48-hour hackathon by instructing two participants who acted out its instructions, successfully designing and prototyping a NERF dart launcher that finished second among six teams. The paper highlights the potential and limitations of generative AI as a tool for ideation, decision-making, and optimization in engineering tasks, demonstrating the practical applicability of generating viable design solutions under real-world constraints.
Zitieren
APA
Ege, D. N., Øvrebø, H. H., Stubberud, V., Berg, M. F., Steinert, M., & Vestad, H. (2024). Benchmarking AI design skills: insights from ChatGPT's participation in a prototyping hackathon. Proceedings of the Design Society, 4, 1999-2008. https://doi.org/10.1017/pds.2024.202
Vancouver
Ege DN, Øvrebø HH, Stubberud V, Berg MF, Steinert M, Vestad H. Benchmarking AI design skills: insights from ChatGPT's participation in a prototyping hackathon. Proceedings of the Design Society. 2024;4:1999-2008. doi:10.1017/pds.2024.202
BibTeX
@article{Ege2024,
author = {Ege, Daniel Nygård and Øvrebø, Henrik H. and Stubberud, Vegar and Berg, Martin Francis and Steinert, Martin and Vestad, Håvard},
title = {Benchmarking AI design skills: insights from ChatGPT's participation in a prototyping hackathon},
journal = {Proceedings of the Design Society},
year = {2024},
volume = {4},
pages = {1999--2008},
doi = {10.1017/pds.2024.202}
}
EUVIMED