Tag
A Lobsters discussion asking whether teams allow LLMs to write both production code and tests, with the author considering a policy restricting AI generation to only one of the two to avoid tautological, over-engineered results.
Simon Willison 引用了 Addy Osmani、Morgan Westlee Lunt 和 Qing Wang 关于 Anthropic Claude Code 团队代码审查实践的观点，指出 AI 审查让代码审查从发布前的关卡变为写作过程中的持续检查，从而让人类审查专注于更高层次的问题。
一位开发者发推询问大家如何管理历史 Claude Code 会话，抱怨需要手动记录 `claude resume` 命令，并指出 Codex/ChatGPT 已很好地解决了这个问题。
Matt Pocock argues that while agent skills aren't strictly necessary if you already follow a great process, they make it easier to follow that process consistently.
A viral tech take arguing that highly automated codebases exist to help humans ship product decisions faster, quoting Kent C. Dodds on shipping 60+ PRs a day solo with AI agents.
Indie game developer Kyle Kukshtel writes up his 'Your Game Is A Harness' talk from Indie Rodeo Calgary, exploring how to practically use LLMs like Claude Code in day-to-day game development rather than one-shot demos, and why LLMs struggle with game-specific code.
作者分享让持久化 AI 代理真正可用的三点经验：为每个代理分配独立容器、主动测试安全边界而非默认信任，以及定义可机器验证的"完成"标准。
Matt Pocock lists common mistakes developers make when working with AI coding agents, including misaligned effort, overly long prompts, weak automated checks, poor codebase navigation, and insufficient agent autonomy.
Kent C. Dodds argues that preventing AI 'slop' is a straightforward three-step engineering process — high-quality agent PRs, solid PR review, and feature flags with disaster recovery — noting these practices long predate AI agents.
Matt Pocock asks how developers are finding the GLOSSARY.md approach from /grill-with-docs, noting that investing more in the glossary makes him more productive and helps the AI agent 'speak his language'.
Addy Osmani emphasizes that verification is crucial for getting good results from AI coding agents: clearly define "done" before review, give the agent executable checks (bash commands, tests, browser tests) to pass, and only ship when nothing blocks merge.
A tweet sharing best practices for Claude Code's multi-agent workflow: use Sonnet to build, Haiku subagents for parallel grunt work, and Opus only at key review checkpoints to save tokens and context.
Bradley Gibbs 的文章提出"循环工程"方法，介绍如何通过优化终端评估、内层循环与学习循环来降低 AI 辅助代码生成带来的验证瓶颈，保留人类的时间、注意力与判断力。
Kent C. Dodds announces a personal record of merging 104 GitHub PRs in a single day, teasing an upcoming YouTube video explaining his workflow.
作者分享如何用 Tailscale 组网，将 Muse/Grokbot 接入本地运行的 Qwen 3.8 Flash Next，实现近乎零成本、无额度限制的 24/7 持续推理，替代容易耗尽免费额度的 OpenRouter。
A developer reflects on the overhead of supervising coding agents and shares a small open-source experiment that separates completion checks from the agent doing the work, so tasks get sent back automatically instead of requiring manual 'continue' prompts.
Ars Technica reports on a study showing AI coding agents boost code output but slow overall delivery, with pull request review times rising 49%, changes-requested rates nearly doubling, and no significant employment changes attributable to AI so far.
Matt Pocock shares guidance on when to use /grill-with-docs, /wayfinder, or one-shot prompting for AI coding agents, advising one-shot for tiny diffs and starting with /grill-with-docs before escalating to /wayfinder for larger tasks.
Matt Pocock shares a 'prompt of the day': a /wait-what command designed to collect questions an AI agent has accumulated in its context window after running autonomously for hours.
Berth is an open-source macOS app that runs coding agents like Claude Code and Codex on your own remote dev boxes, letting them keep working when your laptop is closed, with worktree management, live diffs, and split views.