Tag
Gergely Orosz 的 Pragmatic Engineer 通讯文章回顾 2025 年软件工程与 LLM 的结合现状，涵盖 Anthropic、Cursor、Google、Amazon 等公司如何使用 Claude Code、Cursor、Windsurf 等 AI 开发工具，以及资深工程师们的观察。
开发者 Melvin Vivas 分享他如何用 Grok Bot 在手机上协调 29 个自动化机器人完成实际工程工作，包括 Colab 实验、模型微调和内容创作，从而改变了日常的工作方式。
A developer reflects on their experience using AI coding assistants extensively, discussing the addictive nature, loss of control over code understanding, and potential negative impacts on software quality and personal skills.
A developer created an open-source local memory layer called Memmy to share context between Claude Code and Cursor, eliminating the need to re-explain architecture when switching tools.
The article argues that requiring thorough code review negates the supposed productivity gains of LLM coding assistants, as empirical research shows they do not help write code better or faster, and proponents fail to address the inherent error rates.
ArcKit is an open-source enterprise architecture governance harness that works with AI coding assistants like Claude Code and GitHub Copilot to manage governance workflows including requirements, design reviews, and traceability.
A developer introduces agent-rigor, an open-source framework that enforces runtime discipline and traditional SDLC mechanics into AI coding assistants to prevent common agent failures like scope creep and fix-forward loops.
The author built a 3-layer memory system (project/session/source) for AI coding assistants and is seeking feedback.
The user seeks a value comparison between Claude Code and OpenAI Codex $20 subscriptions, sharing their personal workflow involving Haiku, Sonnet, Qwen, and DeepSeek.