通过实际运行才能发现的隐藏Bug，以及作者如何构建ArDD工具来优化AI编码流程。
Last week I wrote about being bad at discipline and building a tool to compensate — ArDD, a set of Claude Code skills that push a project through arti…
开源Claude技能，专注帮你构建正确的应用，从产品经理经验提炼而成，三个入口避免重复工作。
Howdy friends. I've been a zero to one product manager for 12 plus years and along the way I kept borrowing pieces from different discovery frameworks…
生产环境换模型不只是换API，schema、缓存、适配层才是真正卡点，GPT-5.6用更少代码产出更好结果
Ploy builds production marketing websites with an AI agent. They've been benchmarking every frontier release for months. Nothing beat Claude Opus unti…
Anthropic推出Claude Science，为科学家打造的AI工作台，集成60+科学领域技能与连接器，支持通用与专业代理协作。
Article URL: https://www.anthropic.com/news/claude-science-ai-workbench Comments URL: https://news.ycombinator.com/item?id=48901923 Points: 1 # Commen…
本周AI重磅：GPT-5.6三模型亮相，Grok和Claude新版本表现平平，模型战争全面升温。
This week in AI was dense. Multiple frontier model launches, a monster infrastructure funding round, and a research synthesis that reframes how seriou…
免费开源AI RPG引擎，为Claude打造持久派系与经济系统，内含近3万字世界规则
Article URL: https://github.com/RukkaNova/aevum-realm-architect Comments URL: https://news.ycombinator.com/item?id=48907920 Points: 1 # Comments: 0
首个公开评估Claude Fable 5在生物医学挑战问题的表现，直面基准饱和与评估方法可靠性问题。
arXiv:2607.10849v1 Announce Type: new Abstract: Frontier language models are increasingly evaluated on biomedical benchmarks, but two problems undermi…
30分钟用Claude Code搭建首个AI代理，学会用目标驱动代替步骤指令，效率翻倍。
Most "build your first agent" tutorials start with a framework and four new vocabulary words before you've written anything that does something. This …
Veracode报告揭示AI生成代码安全瓶颈，新模型GPT-5/Claude Sonnet 4.5通过率仅50-55%，模型规模增大并未提升安全性。
TL;DR Nearly half of AI-generated code fails basic security tests — and that number hasn't budged as models got bigger. Java is the riskiest language,…
用 kokoro 为 Claude Code 和 Codex 添加语音朗读，macOS 用户可轻松安装，AI 协作体验更沉浸。
Article URL: https://github.com/softcane/aloud Comments URL: https://news.ycombinator.com/item?id=48902347 Points: 2 # Comments: 0
Claude推出Reflect功能，像Spotify Wrapped一样回顾你的AI聊天历史，趣味性十足。
With Claude Reflect, you can find out exactly how much you're relying on AI these days, and for what.
Claude Code处理请求前Token消耗高达OpenCode近5倍，上下文窗口被挤占，开发者面临成本与效率挑战。
IT之家 7 月 14 日消息，科技媒体 systima 于 7 月 12 日发布博文，对比测试指出在相同提示词、相同 AI 模型情况下， 在处理用户请求前，Claude Code 消耗的 Tokens 数量约为 OpenCode 的 4.7 倍。 该媒体对比测试 Claude Code 2.1.2…
探讨如何成为Claude Code高手，以及AI编码工具如何提升工程团队效率与技能分析。
I am building Promptster - an AI fluency platform that helps level up engineering organizations. Engineering managers invite their teammates and Promp…
呼吁开源AI的必要性，介绍良心之作Mindshub——可定制的开源AI协作者
Imagine if operating systems, browsers, or databases had evolved with only closed systems. We wouldn’t have the internet we know today. AI needs world…
用Claude Code技能安全更新PHP和JS包，避免历史重演。
It's not abnormal for projects to go weeks, or dare I say months, between dependency updates. And when people finally do update, they do it in full fo…
一条命令调用AI工程与营销团队，告别模板维护与安全漏洞噩梦
Article URL: https://www.claudethings.com/ Comments URL: https://news.ycombinator.com/item?id=48903346 Points: 3 # Comments: 0
代码榜榜首易主，Claude新模型登顶，Anthropic包揽前五名，AI模型竞争白热化。
IT之家 7 月 13 日消息，Arena（ arena.ai ）平台发布了最新一期 AI 大模型周榜，本期覆盖 2026 年 7 月 6 日 ~2026 年 7 月 12 日。 本周核心变化为代码榜榜首易主， claude-opus-4-7-thinking 从第二升至第一 ，原榜首 claude…
Anthropic至今未修复Claude的两大用户体验Bug：申诉链接无效、验证码与邮件验证方式不匹配。
I've been using Claude for a long time, and overall, I think Anthropic has built one of the best AI products available today. But over the past few mo…
用户呼吁开源替代Claude的标签功能，揭示团队版用户的痛点。
Like the title says, and it's only available in team plans (>=5 members) The proactive follow ups/doing the work is the main part Comments URL: https:…
拦截AI代理工具调用，用确定性策略为Claude Code、Cursor等编码助手加上安全护栏
Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. We bu…