Recent advances in Large Language Models (LLMs) have introduced a new paradigm for software development, where source code is generated from natural language prompts. While this paradigm significantly boosts development productivity, building complex, real-world software systems remains challenging because natural language offers limited control over the code generation process. Inspired by the historical evolution of programming languages toward higher levels of abstraction, we advocate for a high-level abstraction language that gives developers greater control over LLM-assisted code writing. To this end, we propose Code Semantic Zooming (CodeZoom), a novel approach based on pseudocode that allows developers to iteratively explore, understand, and refine code across multiple layers of semantic abstraction. In a within-subjects user study (n=26), our method matches a state-of-the-art coding agent, Claude Code, on usability while producing a large effect on code comprehension: over 90% of participants reported feeling more in control of design decisions when using CodeZoom compared to using Claude Code.

翻译：大语言模型（LLM）的最新进展为软件开发引入了新范式，即通过自然语言提示生成源代码。尽管这一范式显著提升了开发效率，但由于自然语言对代码生成过程的控制能力有限，构建复杂的真实世界软件系统仍面临挑战。受编程语言向更高抽象层级演进的历史启发，我们主张采用一种高层抽象语言，使开发者能够更精准地掌控大语言模型辅助代码编写过程。为此，本文提出基于伪代码的创新方法——代码语义缩放（CodeZoom），使开发者能够在多层语义抽象中迭代探索、理解并优化代码。在受试者内用户研究（n=26）中，该方法在可用性上与最新代码智能体Claude Code相当，并在代码理解方面产生巨大效果：相较于使用Claude Code，超过90%的参与者反馈使用CodeZoom时对设计决策拥有更强的掌控感。