HUMAN-CHATGPT CO-CREATED SIMULATIONS: DROP-OFF ZONE KINEMATICS CASE STUDY
DOI:
https://doi.org/10.51878/learning.v5i2.5352Keywords:
ChatGPT, AI generatif, Vibe Coding, SimulasiAbstract
The paper reports a collaborative Human-ChatGPT project to build a drop-off simulation in Python. This project aligns with the concept of vibe coding, popularized by OpenAI co-founder Andrej Karpathy, which describes the iterative, conversational development of code between human reasoning and generative AI. The final code was produced through iterative development and refinement via prompting in ChatGPT. We consider a drop-off traffic simulation as the use case, demonstrating how the increasing complexity of human reasoning can be translated into Python through iterative process. We carefully documented each stage of the project with codes, prompts, ChatGPT’s responses, screenshots, and videos in GitHub (https://github.com/eddy-yusuf/dropoff). Each stage captures development milestones which evolve from a single car moving uniformly on a straight lane to 20 interacting cars with complex dynamics including deceleration, stopping, and accelerating at drop-off point. A key finding is that ChatGPT functions not only as a code generator but also as a cognitive partner capable of co-designing the simulation with systematic thinking and reasoning capability. This work can serve as a model for GenAI-enchanced programming education or design. It also poses a critical question for educators about coding pedagogy in the era of Generative AI.
ABSTRAK
Tulisan ini menampilkan proyek kolaboratif antara manusia dan ChatGPT untuk menghasilkan simulasi drop-off menggunakan Python. Proyek ini selaras dengan konsep vibe coding yang dipopulerkan oleh salah satu pendiri OpenAI, Andrej Karpathy, untuk menggambarkan pengembangan kode secara iteratif melalui percakapan manusia dan AI generatif. Kode akhir dihasilkan melalui proses iteratif dan penyempurnaan bertahap melalui prompting di ChatGPT. Simulasi lalu lintas drop-off dipilih sebagai studi kasus untuk menunjukkan bagaimana kompleksitas pemikiran manusia dapat diterjemahkan ke dalam Python melalui proses bertahap. Setiap tahap pengembangan didokumentasikan secara cermat dalam bentuk kode, prompt, respons ChatGPT, tangkapan layar, dan video yang tersedia di GitHub (https://github.com/eddy-yusuf/dropoff). Setiap tahap merekam tonggak perkembangan dari satu mobil yang bergerak secara uniform di jalur lurus menjadi 20 mobil yang saling berinteraksi dengan dinamika kompleks, termasuk perlambatan, berhenti, dan akselerasi di titik drop-off. Temuan penting dari proyek ini adalah bahwa ChatGPT tidak hanya berperan sebagai pembuat kode, tetapi juga sebagai mitra kognitif yang mampu ikut merancang simulasi dengan kemampuan bernalar dan berpikir sistematis. Karya ini dapat menjadi model bagi pendidikan atau desain pemrograman yang diperkuat oleh GenAI, sekaligus sebagai pertanyaan kritis bagi para pendidik terkait pedagogi pemrograman di era AI generatif.
Downloads
References
Biswas, S. (2023). Role of ChatGPT in computer programming. Mesopotamian Journal of Computer Science, 2023, 9–15. https://doi.org/10.58496/MJCSC/2023/002
Brown, T., et al. (2022). Prompt engineering for reliable code generation in large language models. Journal of Artificial Intelligence Research, 74, 1023–1056. https://doi.org/10.1613/jair.1.13567
Bucaioni, A., et al. (2024). Machine learning with applications programming with ChatGPT: How far can we go? Machine Learning with Applications, 15, 100526. https://doi.org/10.1016/j.mlwa.2024.100526
Chang, H. (2008). Autoethnography as method (1st ed.). Routledge. https://doi.org/10.4324/9781315433370
Cheah, C. S. (2020). Factors contributing to the difficulties in teaching and learning of computer programming: A literature review. Contemporary Educational Technology, 12(2). https://doi.org/10.30935/cedtech/8455
Dong, Y., et al. (2024). Self-collaboration code generation via ChatGPT. ACM Transactions on Software Engineering and Methodology, 33(7). https://doi.org/10.1145/3672459
Garcia, R., et al. (2024). Human-in-the-loop debugging: A framework for improving AI code generation. ACM Transactions on Computer-Human Interaction, 31(2), 1–28. https://doi.org/10.1145/3592141
Guo, Q., et al. (2024). Exploring the potential of ChatGPT in automated code refinement: An empirical study. Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. https://doi.org/10.1145/3597503.3623306
Haindl, P., & Weinberger, G. (2024). Students’ experiences of using ChatGPT in an undergraduate programming course. IEEE Access, 12, 43519–43529. https://doi.org/10.1109/ACCESS.2024.3380909
Jacobsen, L. J., & Weber, K. E. (2025). The promises and pitfalls of large language models as feedback providers: A study of prompt engineering and the quality of AI-driven feedback. AI, 6(2). https://doi.org/10.3390/ai6020035
Johnson, L. (2023). Intent modeling: Revolutionizing computer science education through natural language programming. IEEE Transactions on Education, 66(3), 245–253. https://doi.org/10.1109/TE.2023.3266787
Kadar, R., et al. (2021). A study of difficulties in teaching and learning programming: A systematic literature review. International Journal of Academic Research in Progressive Education and Development, 10(3), 591–605. https://doi.org/10.6007/IJARPED/v10-i3/11100
Kok, B., & Gan, S. (2023). ChatGPT, can you generate solutions for my coding exercises? An evaluation on its effectiveness in an undergraduate Java programming course. Proceedings of the ACM Conference on Innovation and Technology in Computer Science Education, 54–60. https://doi.org/10.1145/3587102.3588794
Lee, M., et al. (2023). Co-creating with AI: A paradigm shift in computational design. AI & Society, 38(4), 1437–1453. https://doi.org/10.1007/s00146-022-01607-8
Nguyen, A., et al. (2023). AI-assisted programming education: A meta-analysis of learning outcomes. Computers & Education, 197, 104742. https://doi.org/10.1016/j.compedu.2023.104742
Sands, P. (2019). Addressing cognitive load in the computer science classroom. ACM Inroads, 10(1), 44–51. https://doi.org/10.1145/3210577
Silva, C. A., et al. (2024). ChatGPT: Challenges and benefits in software programming for higher education. Sustainability, 16(3). https://doi.org/10.3390/su16031245
Smith, J., et al. (2021). Instruction ordering effects in neural code generation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 7895–7903. https://ojs.aaai.org/index.php/AAAI/article/view/16932
Stachel, J., et al. (2013). Managing cognitive load in introductory programming courses: A cognitive aware scaffolding tool. Journal of Integrated Design and Process Science, 17(1), 37–54.
Sun, D., et al. (2024). Would ChatGPT-facilitated programming mode impact college students’ programming behaviors, performances, and perceptions? An empirical study. International Journal of Educational Technology in Higher Education, 21(14). https://doi.org/10.1186/s41239-024-00446-5
TIOBE. (2025). TIOBE Index for April 2025. https://www.tiobe.com/tiobe-index/
Williams, K., & Patel, A. (2022). Scaffolded experimentation: A framework for AI-augmented STEM education. Journal of Science Education and Technology, 31(5), 632–645. https://doi.org/10.1007/s10956-022-09985-w
Xie, S., et al. (2024). Utilizing ChatGPT as a scientific reasoning engine to differentiate conflicting evidence and summarize challenges in controversial clinical questions. Journal of the American Medical Informatics Association, 31(7), 1551–1560. https://doi.org/10.1093/jamia/ocae100
Xue, Y., et al. (2024). Does ChatGPT help with introductory programming? An experiment of students using ChatGPT in CS1. Proceedings of the 46th International Conference on Software Engineering: Software Engineering Education and Training, 331–341. https://doi.org/10.1145/3639474.3640076
Yilmaz, R., et al. (2023). Augmented intelligence in programming learning: Examining student views on the use of ChatGPT for programming learning. Computers in Human Behavior: Artificial Humans, 1(2), 100005. https://doi.org/10.1016/j.chbah.2023.100005
Zhang, Y., & Wang, C. (2023). Chain-of-thought reasoning in large language models: A survey. AI Open, 4, 1–12. https://doi.org/10.1016/j.aiopen.2023.06.001
Zhang, Z., et al. (2025). IHEval: Evaluating language models on following the instruction hierarchy. In L. Chiruzzo, et al. (Eds.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol. 1, pp. 8374–8398). Association for Computational Linguistics. https://aclanthology.org/2025.naacl-long.425/
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 LEARNING : Jurnal Inovasi Penelitian Pendidikan dan Pembelajaran
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
