5 posts
A plain-English memo on what Anthropic has been shipping in August 2026, how Claude is turning into operational software, and what the public reaction seems to be from observable signals.
A plain-English memo on what model scores really mean, why 98% vs 95% is usually a small real-world gap, and where the differences actually matter.
A practical memo on what Anthropic has shipped in the last 14 days, how people are actually using Claude and Claude Code, and what SMB and mid-market teams can do with it now.
My multi-agent setup with OpenClaw: one orchestrator, one for social, one for events. How I split responsibilities and why it works.
MCP servers, skills, hooks, agents, tools—Claude Code has a lot of terminology. Here's the reference I made after getting confused by all of it.