Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An open-source browser experiment that sends any pasted text to TypeSafe Jev as 200 small yes/no questions in one parallel call, then draws the calibrated probabilities as a clickable heatmap for anyone exploring model judgments.
How it uses Jev
Each of the 200 questions is a Jev noul returning the probability of "yes" over the same text; all 200 go in one request. The page debounces typing, aborts stale requests, caches by set plus text, and lets a threshold slider re-sort results without new calls.
Primitives:noul
Technique worth stealing
Decompose one big judgment into many small yes/no questions asked in a single parallel call, then combine probabilities in ordinary code.
Try it
Open the hosted demo with no key, or clone, set TYPESAFE_API_KEY, and run node server.js.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.79
- Shows a System One patternFound in material0.98
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.64
- Is a runnable toolFound in material0.74
- Top-10 learning shortlist signalFound in material0.63
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale0.14 / 2
- About JevFound in material0.99
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 3 Nov 2026.