AI Coding工具,可能就要过时了
很多软件创业者都给我抱怨:自从有了 AI Coding,软件行业越来越卷了。现在客户甚至要求必须用 AI Coding,然后预算直接砍一半! 然而,用 AI Coding 远没有看上去的那么简单,毕竟AI只能辅助写代码,需求拆解、架构设计等工作,仍然需要人来参与。
双11直播间爆改AI秀场,罗永浩上手TRAE,秒变AI Coding的大众嘴替
AI写代码飞快,项目却越写越乱?23.6万星开源神器,给AI装上
AI写代码飞快,项目却越写越乱?23.6万星开源神器,给AI装上资深工程师工作流程不知道你有没有踩过这个大坑!用Cursor、Claude Code写代码,生成代码速度快到飞起,分分钟输出一大段代码。
一天烧掉5倍Token预算、3周没看一眼代码!微软产品经理让Claude Code、Codex重构代码库,结果Skills是假的、测试连上了生产环境
近日,AI Engineer 栏目在 YouTube 分享了 Keiji Kanazawa 的这段经历——《I Let Agents Refactor My Codebase for 3 Weeks. Then I Read the Code》。
AI越能写,研究者越头疼?他们破解了AI编码“失真”难题
In social science research, grounded theory is widely adopted to analyze and code textual data. While large language models open new possibilities for coding at scale, they complicate the GT workflow by generating excessive codes and introducing hallucinations, posing challenges for experts to audit and revise the coding results. To address these challenges, we conducted a two-year design study and derived a series of domain needs and design tasks via interviews with scientists in entrepreneurial management. Subsequently, we presented PROVA-GT, a visual analytics system facilitating the GT workflow by supporting both the forward process of code generation and the backward process of validation and refinement, which are interconnected and iterative. Specifically, our system features a provenance workflow that leverages the agentic LLM and novel visual designs to assist experts in the backward process. To evaluate the usefulness of PROVA-GT and its generalizability in different domains, we reported two in-depth expert studies on entrepreneurial inspirations and trust erosion, respectively. We also conducted a user study to assess the effectiveness of the agentic workflow.
AICoding工具,可能就要过时了
最近,AI Coding的讨论又往前走了一步。以前大家问它能不能帮程序员写代码,现在更尖锐的问题变成了,客户既然要求用AI,项目预算是不是就该砍一半。很多软件公司老板的第一反应并不轻松。需求没少,验收责任也没少,报价却可能先缩水。
为什么桌面云是 AI Coding 的最优运行载体:安全、环境的系统支撑
AI Coding 兴起后,很多人把注意力放在“换更强的工具”上,却忽略了真正决定效率与安全的,是工具运行其上的底座。当 Claude Code、WorkBuddy 等 AI 编程工具与重载 IDE、编译任务并行,传统本地 PC 在算力、安全、环境三个维度同时失守。
10天狂揽近2万星,00后大学生拿下大结果,DeepSeek Harness移动端爆火
这款应用叫dsh-Go,是一款可以在安卓手机上运行DeepSeek Harness的移动端应用。在这个大爆款出现之前,小C还在DSH内测期间开发过一个交互式终端界面dsh-TUI,GitHub上Star数超过7.3k,得到了Deepseek Harness团队负责人崔添翼的推荐,两个项目累计超过2.5万Star。