Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python harness that compares Typesafe's Jev with a cheap LLM and a frontier LLM on the same task, data and input, measuring quality, calibration, cost, latency, consistency and robustness, simulating a Jev-first cascade, and building an HTML report.
How it uses Jev
Jev is one arm among several (kind: jev, model: jev-1.15.0) in each run config. The harness sends the same task instructions and input to every arm, stores raw predictions, and compares them via metrics, cascade and report. The README does not specify which typed questions Jev receives.
Technique worth stealing
Jev-first cascade: run Jev, send only uncertain cases to a fallback LLM, simulated from stored predictions.
Try it
uv sync; source .env; uv run jev-eval prepare clinc150; uv run jev-eval run configs/smoke.yaml
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectunclear0.54
- Shows a System One patternFound in material0.75
- Describes handling uncertaintyFound in material0.71
- Reports measured numbersnot found in the excerpt0.09
- Is a runnable toolnot found in the excerpt0.18
- Top-10 learning shortlist signalnot found in the excerpt0.33
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 21 Oct 2026.