すべてのプロジェクト

here-we-go-jev

creativoma/here-we-go-jev

Local playground and test bench for TypeSafe's Jev System One model: typed questions, calibrated-probability answers, and side-by-side comparison with an LLM baseline.

TypeScript
スター
1
フォーク
0

掲載理由

state と型付き質問を試す Jev テスト画面で、mock と System One を備える。mock はキー不要で、実モデルの証拠ではない。

関連プロジェクト

  • system-one-playground

    Run the new wave of decision models (Laya, Decider, Kev, Jev) side by side on your Mac. Structured input in, calibrated probabilities out, with honest accuracy, calibration, latency and memory numbers.

    共通トピック: calibration, classification, evaluation

  • jev-benchmarks

    Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

    共通トピック: calibration, evaluation

  • jev-harness

    Harness for TypeSafe's Jev decision model: typed questions over datasets via OpenRouter, JSONL answers, summary reports.

    共通トピック: bun, classification