Mods make Claude Code a lot better.

Claude now authors 80% of Anthropic's production code. The company's new paper maps the path to recursive self-improvement and calls for a global pause mechanism.

今年3月，腾讯发布了《2026年AI人才报告》，其中提到“AI辅助编程工具使通用型开发任务效率提升约50%”。这个数字在测试圈的讨论群里引发了一轮激烈争论。不是因为50%有多吓人，而是因为测试本身就是一道“执行质量”的防线——如果连执行者都在被加速，这道防线还能守多久？ 更具体的信号在最近两个月开始密集出现。 4月份，JetBrains Rider 2026.2 EAP发布了一个新特性：AI ag ...

最近看到一个特别棒的开源项目：Learn Claude Code。 本来以为，它只是一个教人怎么使用 Claude Code 的学习手册。真正看完之后，发现和我想的完全不一样。 这个项目最有意思的地方，在于它把 Claude Code是怎么一步步搭建出来的，拆解得特别清楚。 它从最基础的 Agent Loop 开始，逐步加入任务规划、知识加载、长期上下文管理、多 Agent 协作、后台任务、Wor ...

Boris Cherny was asked at Brainstorm Tech if he was concerned about the rapid progress of AI: "Yes." ...

阿里妹导读文章内容基于作者个人技术实践与独立思考，旨在分享经验，仅代表个人观点。一、背景在 OpenClaw、Claude Code 等产品出现之前，开发同学实现一个 Agent 的基本思路是：基于 LLM 实现一个 Loop 调用，配合 MCP 或代码层面自定义的工具来完成 ReactAgent；或者利用 Spring AI、LangGraph ...

Anthropic has published an unusually concrete account of how its own engineers use Skills in Claude Code, the company’s command-line coding agent, in a June 3 post on the Claude blog written by ...

A Claude Code GitHub Action flaw let one malicious issue hijack repositories via prompt injection. Anthropic has patched it.

A flaw in Anthropic’s Claude Code GitHub Action allowed a malicious GitHub issue from a bot actor to trigger workflows and ...

A flaw in Claude Code's GitHub Action let attackers bypass permission checks via fake bots and steal OIDC tokens through prompt injection.

Y Combinator’s famed CEO Garry Tan told a SXSW audience that he’s got “cyber psychosis” and is barely sleeping because he’s so excited to be working with AI agents. “I sleep, like, four hours a night ...