Anthropic Says Its Defenses Are Reducing Claude Distillation Attack Effectiveness

Every "7 local models that replace Claude Code" list opens the same way: a table of SWE-bench scores,...

At AI Engineer New York, Anthropic drew on lessons from Unix and Linux to explain how agents can...

Claude Code helped Linus Torvalds explore Linux read performance. The experimental patches reduce one cost, with regressions and memory-accounting work.

What I learned building Vibrary with Claude Code — privacy-first activity tracking, realtime presence bugs, signed auto-updates, and a canvas engine that started as one HTML file.

Requests still return 200. You just pay full price again. Five causes from this quarter's bug reports, and a limit I measured: 21 blocks hit, 22 miss.

Prompt injection hides in tickets, emails, chat, docs and web pages. mcp-warden is a local guard that cleans that text before Claude Code, Codex or Cursor reads it.

Two agents, one checkout, one overwritten file. Give each agent its own worktree, branch and port, spot overlap early, review by turn. Real git output.

Claude and ChatGPT plans already include their coding agents. When is a $20 AI editor still worth it, and when will a free console do?

I use Claude Code on Java projects a lot. After almost every change, the agent wants to run ./gradlew...

I shipped v0.1 of mod-audit — an offline, stdlib-only supply-chain auditor for Claude Code Mods — and...