按年被提到
20232023 · 1 次2026
软件工程与 AI 编程›代码生成与程序合成·arXiv:2305.12050 · cs.SE

AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation

Vijayaraghavan Murali, Chandra Maddila, Imad Ahmad, Michael Bolin, Daniel Cheng, Negar Ghorbani, Renuka Fernandez, Nachiappan Nagappan, Peter C. Rigby · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-06-03 · 最近 2024-05-13
2不同的人
2活跃月份
2讨论串
57被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool developed and deployed at Meta internally. CodeCompose is based on the InCoder LLM that merges generative capabilities with bi-directionality. We have scaled up CodeCompose to serve tens of thousands of developers at Meta, across 9 programming languages and several coding surfaces. We present our experience in making design decisions about the model and system architecture for CodeCompose that addresses these challenges. To release a LLM model at this scale, we needed to first ensure that it is sufficiently accurate. In a random sample of 20K source code files, depending on the language, we are able to reproduce hidden lines between 40% and 58% of the time, an improvement of 1.4x and 4.1x over a model trained only on public data. We gradually rolled CodeCompose out to developers. At the time of this writing, 16K developers have used it with 8% of their code coming directly from CodeCompose. To triangulate our numerical findings, we conduct a thematic analysis on the feedback from 70 developers. We find that 91.5% of the feedback is positive, with the most common themes being discovering APIs, dealing with boilerplate code, and accelerating coding. Meta continues to integrate this feedback into CodeCompose.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论muglug · 2024-05

“GitHub touts a 55% improvement in coding speed based on a study conducted in-house that tested the participants’ ability to paste a pre-written prompt and then check the output: https://github.blog/2022-09-07-research-quantifying-github-copilots-impact-on-developer-productivity-and-happiness/ The effectiveness of a Copilot-like tool trialed at FB showed …”

Did GitHub Copilot increase my productivity?原评论 ↗
被提交为 story · 1 次