Exploring possibilities and limits of ChatGPT: Usage in building design studies

Year 2025, Volume: 9 Issue: 3, 490 - 500

Ekrem Bahadır Çalışkan

https://doi.org/10.31127/tuje.1591495

Abstract

The architectural design of buildings is a complex and detailed process requiring collaboration with various disciplines. With technological development, digital tools have been stated to enhance content creation and analysis, thereby improving project feasibility and optimization. ChatGPT, one of the important Artificial Intelligence technologies, has the potential to assist tasks ranging from simple analysis to complex processes. Despite its extensive use in different fields, such as education, health, and marketing, application and capabilities in architectural design remain largely unexplored. This study investigates the integration of ChatGPT into architectural project workflows, focusing on its potential to support analysis and content creation. A semi-structured interview was defined to test ChatGPT's possibilities and limits during the design stage of a building project. The interview involved preparing project files of a case study and evaluating ChatGPT's ability to analyze data and generate new insights. The findings highlight ChatGPT's strengths in comparison and content analysis while identifying its limitations, such as difficulties reading certain file formats and providing overly general critiques. The study concludes that while ChatGPT shows promise in enhancing architectural workflows, understanding its capabilities and limitations is essential for future research and practical application.

Keywords

Architectural Design, Artificial Intelligence, ChatGPT, Content Generation, Collaboration

References

• Chappell, D., & Dunn, M. (2016). The Architect in Practice (Eleventh., Vol. 11). Wiley-Blackwell. https://doi.org/10.1080/00038628.1968.9697112
• Coskun, H., & Sancar, S. (2021). Client satisfaction as perceived by Architects and Civil Engineers. Turkish Journal of Engineering, 5(3), 100–104. https://doi.org/10.31127/tuje.688291
• Sacks, R., Eastman, C., Lee, G., & Teicholz, P. (2018). BIM Handbook. BIM Handbook. https://doi.org/10.1002/9781119287568
• Mondal, S., Das, S., & Vrana, V. G. (2023). How to Bell the Cat? A Theoretical Review of Generative Artificial Intelligence towards Digital Disruption in All Walks of Life. Technologies, 11(2). https://doi.org/10.3390/technologies11020044
• Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., … Wright, R. (2023). “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. International Journal of Information Management, 71(March). https://doi.org/10.1016/j.ijinfomgt.2023.102642
• Crompton, H., & Burke, D. (2023). Artificial intelligence in higher education: the state of the field. International Journal of Educational Technology in Higher Education, 20(22). https://doi.org/10.1186/s41239-023-00392-8
• Jaruga-Rozdolska, A. (2022). Artificial intelligence as part of future practices in the architect’s work: MidJourney generative tool as part of a process of creating an architectural form. Architectus, 3(71), 95–104. https://doi.org/10.37190/arc220310
• Guo, E., Gupta, M., Deng, J., Park, Y. J., Paget, M., & Naugler, C. (2024). Automated Paper Screening for Clinical Reviews Using Large Language Models: Data Analysis Study. Journal of Medical Internet Research, 26(1). https://doi.org/10.2196/48996
• Lahat, A., Sharif, K., Zoabi, N., Shneor Patt, Y., Sharif, Y., Fisher, L., … Klang, E. (2024). Assessing Generative Pretrained Transformers (GPT) in Clinical Decision-Making: Comparative Analysis of GPT-3.5 and GPT-4. Journal of medical Internet research, 26, e54571. https://doi.org/10.2196/54571
• Kayıran, H. F. (2022). The function of artificial intelligence and its sub-branches in the field of health. Engineering Applications, 1(2), 99–107.
• Uzer, A. U. (2024). Efficient prediction of compressive strength in geotechnical engineering using artificial neural networks. Turkish Journal of Engineering, 8(3), 457–468. https://doi.org/10.31127/tuje.1415931
• Özkurt, C. (2024). Interpretable AI analysis of chaos systems distribution in time series data from industrial robotics. Turkish Journal of Engineering, 8(4), 656–665. https://doi.org/10.31127/tuje.1471445
• Mcgee, R. W. (2023). ANNIE CHAN: Three Short Stories Written with Chat GPT. https://doi.org/10.13140/RG.2.2.21169.66401
• Biswas, S. S. (2023). Potential Use of Chat GPT in Global Warming. Annals of biomedical engineering. https://doi.org/10.1007/s10439-023-03171-8
• Landgrebe, J., & Smith, B. (2021). Making AI meaningful again. Synthese, 198(3), 2061–2081. https://doi.org/10.1007/s11229-019-02192-y
• OpenAI. (2023). Retrieved 13 March 2023, from https://openai.com/
• Caucheteux, C., Gramfort, A., & King, J. R. (2022). Deep language algorithms predict semantic comprehension from brain activity. Scientific Reports, 12(1), 1–10. https://doi.org/10.1038/s41598-022-20460-9
• Chat GPT. (2024). Retrieved 22 July 2024, from https://chatgpt.com/
• Aydın, Ö., & Karaarslan, E. (2023). Is ChatGPT Leading Generative AI? What is Beyond Expectations? Academic Platform Journal of Engineering and Smart Systems, 11(3), 118–134. https://doi.org/10.21541/apjess.1293702
• Floridi, L., & Chiriatti, M. (2020). GPT-3: Its Nature, Scope, Limits, and Consequences. Minds and Machines, 30(4), 681–694. https://doi.org/10.1007/s11023-020-09548-1
• Mcgee, R. W. (2023). Who Were the 10 Best and 10 Worst U . S . Presidents? The Opinion of Chat GPT ( Artificial Intelligence ). https://doi.org/10.13140/RG.2.2.15304.19201
• Sobieszek, A., & Price, T. (2022). Playing Games with Ais: The Limits of GPT-3 and Similar Large Language Models. Minds and Machines, 32(2), 341–364. https://doi.org/10.1007/s11023-022-09602-0
• Çalışkan, E. B. (2023). Briefing with artificial intelligence for requirement elicitation: Three cases with ChatGPT for exploration of possibilities. Architectus, 3(3(75)), 0–2. https://doi.org/10.37190/arc230309
• Yang, X., Li, Y., Zhang, X., Chen, H., & Cheng, W. (2023). Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization. arxiv, February. https://doi.org/https://doi.org/10.48550/arXiv.2302.08081
• Singh, S., & Kaur, R. (2023). ChatGPT : Vision and challenges. Internet of Things and Cyber-Physical Systems, 3(May), 262–271.
• Bozkurt, A., Xiao, J., Lambert, S., Pazurek, A., Crompton, H., Koseoglu, S., … Jandrić, P. (2023). Speculative Futures on ChatGPT and Generative Artificial Intelligence (AI): A Collective Reflection from the Educational Landscape Asian Journal of Distance Education Introduction: Origins. Asian Journal of Distance Education, 18(1), 53.
• Mema, B., Basholli, F., & Hyka, D. (2024). Learning transformation and virtual interaction through ChatGPT in Albanian higher education. Advanced Engineering Science, 4, 130–140.
• Park, H., & Ahn, D. (2024). The Promise and Peril of ChatGPT in Higher Education: Opportunities, Challenges, and Design Implications. In Conference on Human Factors in Computing Systems - Proceedings. https://doi.org/10.1145/3613904.3642785
• Wang, X., Anwer, N., Dai, Y., & Liu, A. (2023). ChatGPT for design, manufacturing, and education. In 33rd CIRP Design Conference (Vol. 119, pp. 7–14). Elsevier B.V. https://doi.org/10.1016/j.procir.2023.04.001
• Jiang, Y., & Yang, C. (2024). Is ChatGPT a Good Geospatial Data Analyst? Exploring the Integration of Natural Language into Structured Query Language within a Spatial Database. ISPRS International Journal of Geo-Information, 13(1). https://doi.org/10.3390/ijgi13010026
• Abate, N., Visone, F., Sileo, M., Danese, M., Minervino Amodio, A., Lasaponara, R., & Masini, N. (2023). Potential Impact of Using ChatGPT-3.5 in the Theoretical and Practical Multi-Level Approach to Open-Source Remote Sensing Archaeology, Preliminary Considerations. Heritage, 6(12), 7640–7659. https://doi.org/10.3390/heritage6120402
• Hu, X., Tian, Y., Nagato, K., Nakao, M., & Liu, A. (2023). Opportunities and challenges of ChatGPT for design knowledge management. Procedia CIRP, 119, 21–28. https://doi.org/10.1016/j.procir.2023.05.001
• Caliskan, E. B. (2023). Interview with Chat GPT to Define Architectural Design Studio Work: Possibilities, Conflicts and Limits. Journal of Design Studio, 5(1), 57–71. https://doi.org/10.46474/jds.1267485
• Zhang, C., & Wang, S. (2023). Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data. arxiv.
• Abioye, S. O., Oyedele, L. O., Akanbi, L., Ajayi, A., Davila Delgado, J. M., Bilal, M., … Ahmed, A. (2021). Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges. Journal of Building Engineering, 44(April 2020), 103299. https://doi.org/10.1016/j.jobe.2021.103299
• Rane, N., Choudhary, S., & Rane, J. (2023). Integrating Building Information Modelling (BIM) with ChatGPT, Bard, and similar generative artificial intelligence in the architecture, engineering, and construction industry: applications, a novel framework, challenges, and future scope. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4645601
• Rane, N. (2023). ChatGPT and Similar Generative Artificial Intelligence (AI) for Building and Construction Industry: Contribution, Opportunities and Challenges of Large Language Models for Industry 4.0, Industry 5.0, and Society 5.0. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4603221
• den Otter, A., & Emmitt, S. (2008). Design team communication and design task complexity: The preference for dialogues. Architectural Engineering and Design Management, 4(2), 121–129. https://doi.org/10.3763/aedm.2008.0072
• Fellow, R., & Liu, A. (2008). Research Methods for Constructions (3rd ed.). Wiley-Blackwell.
• Bechhofer, F., & Paterson, L. (2000). Principles of Research in the Social Sciences. Social Reseach Today. Routledge.