Jun 12, 2026
and what is Loop Engineering?
Apr 19, 2026
Here's what image tokenization is, what changed in 4.7, and when it's actually worth paying for
Apr 16, 2026
The docs said 1.0–1.35x more tokens. On real content, I measured 1.47x.
Apr 8, 2026
What Claude Code's /sandbox blocks at the OS, what still slips through, and a settings.json that matches the experiments
Apr 1, 2026
Pro, Max, Team, and API rates, plus real session math with prompt caching
Anthropic sends your utilization data on every API response. Claude Code doesn't show it to you. So I built a proxy to catch it.
Mar 25, 2026
What Effort Levels Cost and What You Can't See
Mar 18, 2026
Measured API payload: system text vs tools vs CLAUDE.md, and how to read /context
Mar 17, 2026
Also, the 5 hooks worth installing today
Confessions of an AI coding addict