All projects

jev-probe

Shoaib-Asghar/jev-probe

Testing environment for TypeSafe's Jev model. It applies controlled perturbations (typos, adversarial text, reordering) to test cases, executes real API calls, and logs the raw JSON responses to DuckDB. Includes a web dashboard to track probability shifts, latency, and cost against an LLM baseline.

Python
Stars
0
Forks
0

Why it is listed

Exploration harness compares Jev and baseline LLM decision consistency under meaning-preserving input perturbations and records confidence, cost and latency metrics.

Related projects

  • jev-demo

    JEV Studio is a small Next.js evaluation lab for turning natural-language input into structured signals with the Typesafe SystemOne API.

    Shared topics: jev-model

  • what-the-jev

    What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.

    Shared topics: jev-model

  • typed-decision-bench

    Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.

    Shared topics: jev-model