按年被提到
20232023 · 2 次2026
软件工程与 AI 编程›代码生成与程序合成·arXiv:2303.11455 · cs.SE

Large Language Models and Simple, Stupid Bugs

Kevin Jesse, Toufique Ahmed, Premkumar T. Devanbu, Emily Morgan · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-03-31 · 最近 2023-04-24
2不同的人
2活跃月份
2讨论串
83被引(OpenAlex)
arXiv 摘要(候选层不写导读)

With the advent of powerful neural language models, AI-based systems to assist developers in coding tasks are becoming widely available; Copilot is one such system. Copilot uses Codex, a large language model (LLM), to complete code conditioned on a preceding "prompt". Codex, however, is trained on public GitHub repositories, viz., on code that may include bugs and vulnerabilities. Previous studies [1], [2] show Codex reproduces vulnerabilities seen in training. In this study, we examine how prone Codex is to generate an interesting bug category, single statement bugs, commonly referred to as simple, stupid bugs or SStuBs in the MSR community. We find that Codex and similar LLMs do help avoid some SStuBs, but do produce known, verbatim SStuBs as much as 2x as likely than known, verbatim correct code. We explore the consequences of the Codex generated SStuBs and propose avoidance strategies that suggest the possibility of reducing the production of known, verbatim SStubs, and increase the possibility of producing known, verbatim fixes.

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

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次