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