全部项目

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
星标
1
派生
0

收录依据

用于 state 与类型化问题、提供 mock 及 System One 后端的 Jev 演示测试台。mock 无需 key,不应视为实时模型证据。

相关项目

  • 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.

    共同主题: calibration, classification, evaluation

  • jev-benchmarks

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

    共同主题: calibration, evaluation

  • jev-harness

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

    共同主题: bun, classification