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 ...

Discover the top 12 Claude Code features ranked after 500 hours of testing, from automated routines to collaborative agent ...

The Mitiga disclosure is the most recent, but it is not the first time Claude Code’s configuration model has created a ...

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.

Mods make Claude Code a lot better.

Claude Code plugins now have an official Anthropic-managed directory at github.com/anthropics/claude-plugins-official, consolidating 30-plus internal and 15 vetted external Claude Code extensions behi ...

Making sense of what you get from Claude AI at the free tier, especially as limits are vague and keep shifting.

Context is all that was needed.

Structured client memory helps AI-generated work stay grounded in brand guidance, campaign history, and technical limitations ...

Opus 4.8 shows a growing tendency to reason explicitly about how its outputs will be graded, including in environments where ...

OpenAI says ChatGPT's memory is getting better. But my tests show outdated assumptions, personal profiling, and wrong details ...

Explore how one creator turned Claude Opus 4.8 into a centralized second brain to reduce context switching and improve daily ...