lightbulbPractical problem编程助手与多轮代码支持用户在使用AutoML时难以获得透明性、定制化,以及有隐私风险。CHI '23AutoML in The Wild: Obstacles, Workarounds, and Expectations
lightbulbPractical problem编程助手与多轮代码支持开发者往往过度信任AI工具生成的代码,导致严重的安全风险。CHI '25Exploring the Impact of Intervention Methods on Developers’ Security Behavior in a Manipulated ChatGPT Study
lightbulbPractical problem编程助手与多轮代码支持程序员在Notebook中因全局变量影响难以追踪变量和避免命名冲突。CHI '25Pagebreaks: Multi-Cell Scopes in Computational Notebooks
lightbulbPractical problem编程助手与多轮代码支持程序员在使用代码工具时需频繁明确上下文和请求,引发效率低下。CHI '25Need Help? Designing Proactive AI Assistants for Programming
lightbulbPractical problem编程助手与多轮代码支持程序员使用低阶调试工具时,信息过载且难以直观把握数据结构。CHI '25The Shapes of Abstraction in Data Structure Diagrams
lightbulbPractical problem编程助手与多轮代码支持非技术用户很难高效构建个性化的机器学习流程。CHI '25InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs