Skip to main content
AI MAY 23, 2026

Leverage Record: May 23, 2026

One task. May 23, 2026 weighted to 33.6x leverage across 28.0 human-equivalent hours in 50 Claude-minutes. Supervisory leverage closed at 336.0x.

One task. May 23, 2026 weighted to 33.6x leverage across 28.0 human-equivalent hours in 50 Claude-minutes. Supervisory leverage closed at 336.0x.

0.7 weeks of human-equivalent throughput in 0.8 hours of Claude wall-clock. The 33.6x ceiling came from Math content shapes for an origin service synthesis: three new content shapes (symbolic problems, modeling problems) + math tribunal verdict schema. libs/an origin runtime library...; the 33.6x floor sat at Math content shapes for an origin service synthesis: three new content shapes (symbolic problems, modeling problems) + math tribunal verdict schema. libs/an origin runtime library....

About These Records
These time records capture personal project work done with Claude Code (Anthropic) only. They do not include work done with ChatGPT (OpenAI), Gemini (Google), Grok (xAI), or other models, all of which I use extensively. Client work is also excluded, despite being primarily Claude Code. The actual total AI-assisted output for any given day is substantially higher than what appears here.

Task Log

#TaskHuman Est.ClaudeSup.FactorSup. Factor
1Math content shapes for an origin service synthesis: three new content shapes (symbolic problems, modeling problems) + math tribunal verdict schema. libs/an origin runtime library + services/an origin service, 1653 LOC across 16 files28.0h50m5m33.6x336.0x

Aggregate Statistics

MetricValue
Total tasks1
Total human-equivalent hours28.0
Total Claude minutes50
Total supervisory minutes5
Total tokens350,000
Weighted average leverage factor33.6x
Weighted average supervisory leverage factor336.0x
Human-equivalent weeks0.7

Analysis

The day's leverage distribution matters more than the headline figure. The 33.6x ceiling came from Math content shapes for an origin service synthesis: three new content shapes (symbolic problems, modeling problems) + math tribunal verdict schema. libs/an ori...; the 33.6x floor was Math content shapes for an origin service synthesis: three new content shapes (symbolic problems, modeling problems) + math tribunal verdict schema. libs/an ori.... Tasks at the top of the distribution share a shape: tightly-scoped specifications, clear success criteria, and minimal integration ambiguity. The AI doesn't need to discover anything new; it executes against an explicit target.

Tasks at the bottom run differently. They're either bounded by review-heavy work where every step gets verified, or they involve ambiguity that demands several rounds of trial and adjustment. The factor is real and informative, not a failure mode.

The supervisory leverage figure (336.0x today) tracks something orthogonal to wall-clock leverage. It's the ratio of human-equivalent output to human prompt-writing time. It stays high even on lower-leverage days because supervisory minutes scale with task count, not with the human-hour estimate; a 20-minute task and a 4-hour task can both be specified in two minutes of human prompt-writing.

Across the 1 task, the day produced roughly 0.7 weeks of senior-engineer-equivalent throughput in 0.8 hours of model wall-clock. That ratio is the practical answer to the question of how much output a single operator can move per day when the model handles the execution and the operator handles the direction.