Abstract: The emergence of large language models (LLMs), represented by ChatGPT, has had a profound impact on various fields, including software engineering, and has also aroused widespread concerns. To see a right way through the fog, we have recently been discussing and contemplating a theme of “software development in the age of LLMs,” or rather “the capability of LLMs in software development,” based on various technical literature, shared experiences, and our own preliminary explorations. Additionally, I have participated in several online interviews and discussions on the theme, which have triggered further insights and reflections. Based on the aforementioned thinking and discussions, this article has been composed to disseminate information and foster an open discussion within the academic community. LLMs still largely remain a black box, and the technology is still rapidly iterating and evolving. Moreover, the existing cases reported by practitioners and our own practical experiences with LLM-based software development are relatively limited. Therefore, many of the insights and reflections in this article may not be accurate, and they may be constantly refreshed as technology and practice continue to develop.

智能化时代的软件开发：拥抱大模型的正确姿势

[1]Brooks FP Jr, 1987. No silver bullet essence and accidents of software engineering. Computer, 20(4):10-19.

[2]Dou SH, Shan JJ, Jia HX, et al., 2023. Towards understanding the capability of large language models on code clone detection: a survey. https://arxiv.org/abs/2308.01191

[3]Du XY, Liu MW, Wang KX, et al., 2023. ClassEval: a manually-crafted benchmark for evaluating LLMs on class-level code generation. https://arxiv.org/abs/2308.01861

[4]Hou XY, Zhao YJ, Liu Y, et al., 2023. Large language models for software engineering: a systematic literature review. https://arxiv.org/abs/2308.10620

[5]Liu JW, Xia CS, Wang YY, et al., 2023. Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation. http://arxiv.org/abs/2305.01210

[6]Meyer B, 2023. AI does not help programmers. Commun ACM, early access.

[7]Open AI, 2023. GPT-4 technical report. https://arxiv.org/abs/2303.08774

[8]Wang JJ, Huang YC, Chen CY, et al., 2023. Software testing with large language model: survey, landscape, and vision. https://arxiv.org/abs/2307.07221

[9]Welsh M, 2023. The end of programming. Commun ACM, 66(1):34-35.

[10]Wu QY, Bansal G, Zhang JY, et al., 2023. AutoGen: enabling next-Gen LLM applications via multi-agent conversation. https://arxiv.org/abs/2308.08155

[11]Yuan ZQ, Liu JW, Zi QC, et al., 2023a. Evaluating instruction-tuned large language models on code comprehension and generation. https://arxiv.org/abs/2308.01240

[12]Yuan ZQ, Lou YL, Liu MW, et al., 2023b. No more manual tests? Evaluating and improving ChatGPT for unit test generation. https://arxiv.org/abs/2305.04207

[13]Zhao WX, Zhou K, Li JY, et al., 2023. A survey of large language models. https://arxiv.org/abs/2303.18223

[14]Zheng ZB, Ning KW, Chen JC, et al., 2023. Towards an understanding of large language models in software engineering tasks. https://arxiv.org/abs/2308.11396