What it is
A curated index of independent tests of Jev (TypeSafe System One), grouped by calibration, consistency, perturbation, injection, abstention, failure modes, and language. It links original sources, reports their numbers as author findings, and keeps task benchmarks without a robustness angle in a separate data file.
How it uses Jev
The README does not describe how Jev is used in code; it is a catalogue of external tests, not an implementation. Entries report how Jev's answers or probabilities change with question wording, option order, repeated calls, language, injected text, or unanswerable inputs, and whether returned probabilities are calibrated.
Primitives:choicescorenoul
Technique worth stealing
Group independent robustness tests by the property they measure, report author numbers, and separate task benchmarks.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.78
- Shows a System One patternno0.08
- Handles uncertaintyno0.08
- Measuredno0.20
- Runnableno0.05
- Worth recommendingno0.23
- Model replicano0.02
- Problem scopescore on a 0–2 scale1.04
- About Jevyes0.99
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.