Blog
In-depth articles on AI models, tools, and engineering practices.
Claude Code Security: Scanning Codebases for Vulnerabilities
Anthropic launches a research preview of Claude Code's security scanning feature, bringing AI-powered vulnerability detection directly into developer workflows.
Claude Code Review: How Anthropic Solved Its Own AI Code Review Bottleneck
Claude Code's new multi-agent code review feature runs deep PR analysis automatically, built to solve Anthropic's own 200% code output growth bottleneck.
Claude Code Remote Control: Kick Off Tasks in Terminal, Control from Phone
Claude Code Remote lets you start coding tasks in your terminal and monitor or steer them from your phone. Here's how it works and why it matters.
Claude Code Memory System: How CLAUDE.md and Auto Memory Work
How Claude Code's memory system works across sessions using CLAUDE.md files and auto memory, with practical setup guidance for engineering teams.
Claude Code's Extension Stack: How Skills, Hooks, Agents, and MCP Turn a CLI Into a Programmable AI Platform
Claude Code ships 4 extension primitives — Skills, Hooks, Agents, MCP — turning a terminal AI coding assistant into a programmable development platform.
How Claude Code Is Reshaping Engineering at Ramp, Shopify, Spotify, and More
How engineering teams at Ramp, Rakuten, Brex, Wiz, Shopify, and Spotify are using Claude Code to ship faster, reduce toil, and rethink developer workflows.
Claude Code Ctrl+S Prompt Stashing: Queue Prompts While Claude Works
How Claude Code's Ctrl+S prompt stashing lets you queue up your next instruction while Claude is still working, eliminating idle waiting time.
Claude Code and Claude.ai Hit With Login Errors and Performance Issues
Claude Code and claude.ai users report elevated login errors and slower performance amid surging demand. Here's what's happening and what to do.
Claude Code /btw: Side Chain Conversations While Your Agent Works
Claude Code's new /btw command lets you have side chain conversations while your agent keeps working — no more waiting to ask questions.
Claude Code Agent Teams: Multi-Agent AI Coding with Parallel Sub-Agents
Claude Code Agent Teams let developers spawn parallel AI sub-agents in isolated git worktrees. Here's how multi-agent orchestration actually works.
Anthropic Exposes Industrial-Scale Model Distillation Attacks by DeepSeek, Moonshot AI, and MiniMax
Anthropic reveals that DeepSeek, Moonshot AI, and MiniMax ran 24,000+ fake accounts to distill Claude's capabilities across 16 million exchanges.
Anthropic and the Department of War: What Dario Amodei's Statement Means for AI in Defense
Dario Amodei issued a statement on Anthropic's discussions with the Department of War, as AI companies navigate classified deployments and safety guardrails.