TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Developers spend most of their time figuring the system out

20 点作者 r4um4 天前

3 条评论

exiguus大约 10 小时前
The interesting part of the article is the cite: <a href="https:&#x2F;&#x2F;www.researchgate.net&#x2F;publication&#x2F;318811113_Measuring_Program_Comprehension_A_Large-Scale_Field_Study_with_Professionals" rel="nofollow">https:&#x2F;&#x2F;www.researchgate.net&#x2F;publication&#x2F;318811113_Measuring...</a><p>A revelation struck me as I read this: if software development consists of 5-10% programming or editing (as evidenced by the study and confirmed by my own experience) and over 50% comprehension, then the current state of AI coding agents is quite poor. This is because they only understand a very small portion of your software, and this portion is a very limited context that they can compare with what they already know. However, there is hope; MCP will expand this context, the financial cost and what you think about data privacy when you give AI access to anything related to a project (like mail, confluence, meeting notes and git history).
JohnFen4 天前
This appears to just be an advertisement.
评论 #44068033 未加载
sakesun大约 9 小时前
We need better tool to understand the system. But, before that, please spend sometime to understand the different between gtoolkit and lepiter.