Small-Step Live Programming by Example
Kasra Ferdowsifard, Allen Ordookhanians, Hila Peleg, Sorin Lerner, Nadia Polikarpova
摘要
Live programming is a paradigm in which the programming environment continually displays runtime values. Program synthesis is a technique that can generate programs or program snippets from examples. paper presents a new programming paradigm called Synthesis-Aided Live Programming that combines these two prior ideas in a synergistic way. When using Synthesis-Aided Live Programming, programmers can change the runtime values displayed by the live works that combine the two have taken a holistic approach to the way examples describe the behavior of functions and programs. This paper presents a new programming paradigm called Small-Step Live Programming by Example that lets the user apply Programming by Example locally. When using Small-Step Live Programming by Example, programmers can change the runtime values displayed by the live visualization to generate local program snippets. % Live programming and program % synthesis work perfectly together because the live programming environment % reifies values, which makes it easy for programmers to provide the examples % needed by the synthesizer. We implemented this new paradigm in a tool called , and performed a user study on programmers. Our study finds that Small-Step Live Programming by Example with helps users solve harder problems faster, and that for certain types of queries, users prefer it to searching the web. Additionally, we identify the , in which users' mental models of the tool do not match its ability, and needs to be taken into account in the design of future synthesis tools.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
引用它的顶会 Paper17
- Grounded Copilot: How Programmers Interact with Code-Generating ModelsShraddha Barke, Michael B. James, Nadia PolikarpovaOOPSLA 2023 · 被引用 408 次
- The Metacognitive Demands and Opportunities of Generative AILev Tankelevitch, Viktor Kewenig, Auste Simkute, Ava Elizabeth Scott 等CHI 2024 · 被引用 279 次
- A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and ChallengesJenny T. Liang, Chenyang Yang, Brad A. MyersICSE 2024 · 被引用 126 次
- On the Design of AI-powered Code Assistants for NotebooksAndrew M. McNutt, Chenglong Wang, Robert A. DeLine, Steven Mark DruckerCHI 2023 · 被引用 78 次
- Discovering the Syntax and Strategies of Natural Language Programming with Generative Language ModelsEllen Jiang, Edwin Toh, Alejandra Molina, Kristen Olson 等CHI 2022 · 被引用 76 次
相关 Paper
- LooPy: interactive program synthesis with control structuresKasra Ferdowsifard, Shraddha Barke, Hila Peleg, Sorin Lerner 等OOPSLA 2021 · 被引用 18 次
- Focused Live Programming with Loop SeedsSorin LernerUIST 2020 · 被引用 6 次
- Projection Boxes: On-the-fly Reconfigurable Visualization for Live ProgrammingSorin LernerCHI 2020 · 被引用 52 次
- Programming with a read-eval-synth loopHila Peleg, Roi Gabay, Shachar Itzhaky, Eran YahavOOPSLA 2020 · 被引用 15 次
- Validating AI-Generated Code with Live ProgrammingKasra Ferdowsi, Ruanqianqian (Lisa) Huang, Michael B. James, Nadia Polikarpova 等CHI 2024 · 被引用 27 次
