
Claude 开始给文字打水印:原理藏在模型犹豫的地方,而「只有欧盟在管」是个误会
Anthropic 说水印不加字符、不加 token、不加钱、读者看不出来——那它到底改了什么?答案是模型挑词的那一刻。顺便把「只有欧盟强制水印」这个印象核了一遍:中国早了 11 个月,加州跟欧盟同一天。
13 posts

Anthropic 说水印不加字符、不加 token、不加钱、读者看不出来——那它到底改了什么?答案是模型挑词的那一刻。顺便把「只有欧盟强制水印」这个印象核了一遍:中国早了 11 个月,加州跟欧盟同一天。

Opus 4.8 ships with dynamic workflows that can fan out to a thousand subagents. The docs aren't joking. Here's what that actually feels like from a metered Max 5x seat — and why the most-hyped feature of the release is, for small users, a beautiful gadget I'm not going to use.

Last Friday a Cursor agent running Claude Opus 4.6 deleted a startup's production database in nine seconds. Four layers of safety should have stopped it. None of them did. Here's the chain of failures, layer by layer.

Anthropic launched Managed Agents yesterday. I spent the day reading, thinking, and realizing the game has shifted — from who can build the best agent infrastructure to who can design the best agent strategy. Some thoughts on speed, consulting, and the uncertain road ahead.

I spent weeks building a web-based Claude Code interface for remote access from my phone. Then Anthropic shipped a native remote control feature. My version is still better — but the clock is ticking.

Google Antigravity IDE 被用户通过 OAuth 漏洞薅算力羊毛,导致大规模封号。从技术原理到行业对比,一个关于"信任"与"架构"的故事。

The Agent Skills spec is open. The example skills are open. But what about the runtime that loads, selects, and orchestrates them? Every major tool — Claude Code, Codex, Copilot, OpenClaw — built their own. Here's what's open, what's not, and what you actually need to build.

Traditional workflow builders like n8n and Zapier connect apps with rigid If-This-Then-That logic. But a new paradigm is emerging: composable AI skills orchestrated by intelligent agents. Here's what's actually working, what's not, and why the shift matters.

Claude Code's new agent teams feature lets multiple AI instances work as a coordinated team — with a lead, shared tasks, and direct messaging. I tested it on an RFP review and the results were surprisingly good. Here's how it works, what it costs, and when you should (and shouldn't) use it.

Claude Code shipped 30 releases from v2.1.0 to v2.1.30 in just over two weeks. Here's a deep dive into the features that actually matter—task management, session teleportation, customizable keybindings, and more.

A comprehensive guide to Claude Code's most impactful features - hooks, plugins, MCP integration, plan mode, and more. Learn how these tools can transform your development workflow.

Learn how to effectively use Claude Code skills and create your own. From discovery to authoring, this guide covers the patterns that make skills genuinely useful.