aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

研究称更强编程模型未提高代码合并率

AI 导读

一项哈佛研究利用 Claude Fable 5 因美国出口管制指令中断服务 19 天的情况,比较了 297 名原用户与 8,908 名继续使用 Opus 4.8 的开发者。获得 Fable 5 访问权限后,拉取请求的 7 天合并率仅高出 1.4 个百分点,差异处于统计噪声范围;研究还称,另外五次模型升级也未提高合并率。

原帖引用 · 原文

@rohanpaul_ai

– https://t.co/8xHdi1rm5A

Title: "Higher-Scoring Coding Models Did Not Get More Work Done"

回复Rohan Paul@rohanpaul_ai
New Harvard paper finds that when Claude Fable 5 was suspended for 19 days, its users' pull requests got merged about as often on the weaker Opus 4.8. A U.S. export control directive cut off Claude Fable 5 for 19 days in June 2026, and most users switched to Opus 4.8. The study tracked GitHub pull requests from 297 Fable 5 users against 8,908 developers who stayed on Opus 4.8. Access to Fable 5 raised the 7-day merge rate by only 1.4 points, a change within noise. Across 5 other model upgrades, merge rates did not rise either, though 94.5% of pull requests were already merged beforehand.
在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错