Skip to main content
AI06 July 2026

Mostly coding

6 tasks. July 6, 2026 closed at 8.3x weighted leverage across 72.0 human-equivalent hours in 520 minutes of wall-clock time. Supervisory leverage came in at 86.4x.

That is 1.8 weeks of human-equivalent throughput in 8.7 hours. The ceiling was 10.1x; the floor was 3.4x. 6 of the 6 entries came from a single project.

Task Log

#TaskHuman Est.ClaudeSup.Factor
1Coding16.0h95m10m10.1x
2Coding20.0h130m12m9.2x
3Testing28.0h185m18m9.1x
4Content production3.5h35m3m6.0x
5AVIAN [engine subsystem] per-category response budget: right-sized reasoning max_tokens 16384->2048 + made [engine subsystem]_max_tokens per-category in the model registry (resolve_[engine subsystem]_config…2.5h40m3m3.8x
6Coding2.0h35m4m3.4x

Aggregate Statistics

MetricValue
Total tasks6
Total human-equivalent hours72.0
Total Claude minutes520
Total supervisory minutes50
Total tokens2,690,000
Weighted average leverage factor8.3x
Weighted average supervisory leverage factor86.4x
Human-equivalent weeks1.8

Analysis

The highest factor of the day came in at 10.1x and the lowest at 3.4x, a spread of 2.9 times between the two. That is a narrow range, which tends to happen when a day stays inside one kind of work.

The largest single entry accounted for 16.0 of the 72.0 human-equivalent hours, or 22 percent of the day. No single task dominated the total, so the weighted average is representative.

Supervisory time was 50 minutes against 520 minutes of execution, a ratio of about 1 to 10. Supervisory leverage of 86.4x is the figure I find most honest, because it measures the hours I actually spent rather than the hours a machine spent on my behalf.

Every figure here is recorded at the time the work is done rather than reconstructed afterwards. The human estimate is my own judgement and carries the uncertainty that implies; the minutes and tokens are measured. The full dataset, including this day, is available for download.