Skip to main content
AI JUL 06, 2026

Leverage Record: July 6, 2026

Six tasks. July 6, 2026 weighted to 8.3x leverage across 72.0 human-equivalent hours in 520 Claude-minutes. Supervisory leverage closed at 86.4x. Model benchmarking and content-generation routing ran the day: a 30-subje…

Six tasks. July 6, 2026 weighted to 8.3x leverage across 72.0 human-equivalent hours in 520 Claude-minutes. Supervisory leverage closed at 86.4x. Model benchmarking and content-generation routing ran the day: a 30-subject three-model synthesis-quality benchmark, an entailment-floor re-validation that rescued 27 of 33 partial packages, a beta-tier expansion from 44 to 106 packages, and per-domain model routing for the retrieval-answering service.

1.8 weeks of human-equivalent throughput in 8.7 hours of Claude wall-clock. The 10.1x ceiling came from Ran a per-subject synthesis-quality benchmark: three candidate models x 30 subjects (13 academic subjects, 17 world-language courses), using a per-phase...; the 3.4x floor sat at Math-content model bake-off for the retrieval-answering service: built a four-model x math-course direct A/B harness (80 MCQs); one candidate model came out....

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
1Ran a per-subject synthesis-quality benchmark: three candidate models x 30 subjects (13 academic subjects, 17 world-language courses), using a per-phase benchmark harness plus an NLI model-server; produced a detailed report with per-subject winners and good/bad example content nodes16.0h95m10m10.1x96.0x
2Ran an entailment-floor re-validation/salvage pass that rescued 27 of 33 partial content packages, backfilled activities across 4 files, ran a lessons generator, wired up auto-promotion, and did documentation cleanup20.0h130m12m9.2x100.0x
3Beta-tier package expansion (44 to 106): migrated the content-generation pipeline to a new candidate model (question sets, exam tips, plus a new post-extraction lessons generator), root-caused a provider-contention issue, provider dedup (merged duplicate provider identifiers, consolidated overlapping test-prep categories), then ran a 29-package synthesis batch through the auto-promotion pipeline28.0h185m18m9.1x93.3x
4Per-domain model routing for the retrieval-answering service via a config registry: math-domain content (detected via a content-type signal) now routes to a reasoning-tier candidate model; added an answering-service role, a content-type override, a model-resolution helper, and extra max-tokens headroom for reasoning responses; wired the routing through the relevant services and smoke-tested math-domain answering; tests green3.5h35m3m6.0x70.0x
5Per-category response-budget right-sizing for the retrieval-answering service: cut the reasoning max-tokens budget from 16384 to 2048 and made the token budget configurable per category in the model-routing registry (a config resolver returns model plus budget, with a per-response override, extensible to other test-prep categories via a content-signal map); ran an accuracy/latency A/B between two candidate models on math content (75-76% vs 77% accuracy, about 15x latency difference); 2 services, tests green2.5h40m3m3.8x50.0x
6Math-content model bake-off for the retrieval-answering service: built a four-model x math-course direct A/B harness (80 MCQs); one candidate model came out best on accuracy and latency (92.5% accuracy, fastest at about 0.5s). Switched math routing to a two-model fallback list, added a new inference provider plus fallback-list resolution and extra reasoning headroom to the model-routing registry; 2 services, 54+84 tests green2.0h35m4m3.4x30.0x

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 day's leverage distribution matters more than the headline figure. The 10.1x ceiling came from Ran a per-subject synthesis-quality benchmark: three candidate models x 30 subjects (13 academic subjects, 17 world-language courses), using a per-phase...; the 3.4x floor was Math-content model bake-off for the retrieval-answering service: built a four-model x math-course direct A/B harness (80 MCQs); one candidate model came out.... 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 broad benchmark that produced a single comprehensive report sat at the top; the fine-grained model bake-offs at the bottom were measurement-heavy and iterative, with repeated A/B accuracy and latency runs that resist compression.

The supervisory leverage figure (86.4x 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 6 tasks, the day produced roughly 1.8 weeks of senior-engineer-equivalent throughput in 8.7 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.