Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A work-in-progress collection of self-contained experiments using Jev, TypeSafe's System One model, from coding agents like Claude Code. Includes a qualitative linter, a playground case, and talk slides, aimed at developers exploring fast small decisions in AI systems.
How it uses Jev
Jev answers typed questions about a state: Noul returns a yes probability, Choice returns one probability per option, Score returns a position on described levels. In experiments/01-qualitative-linter, one English rule judges each log line; Jev triages it and the agent fixes only flagged lines.
Primitives:choicescorenoul
Technique worth stealing
Shadow first, trust later: wire Jev log-only, measure against a baseline before it may block or act.
Try it
export TYPESAFE_API_KEY=... then open the repo in a coding agent and follow an experiment README.
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 projectFound in material0.85
- Shows a System One patternunclear0.50
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolnot found in the excerpt0.11
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale0.75 / 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 1 Oct 2026.