what-the-jev
keta1930/what-the-jev
What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.
- 星标
- 13
- 派生
- 1
收录依据
介绍 Jev/TypeSafe System One 任务的展示资料集。按学习资源收录,不认证示例所称效果。
keta1930/what-the-jev
What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.
介绍 Jev/TypeSafe System One 任务的展示资料集。按学习资源收录,不认证示例所称效果。
Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control — plus a living audit of the Jev ecosystem.
共同主题: benchmark, evals, llm-evaluation
Evaluation tools for Jev-compatible decision models, covering accuracy, calibration, hidden instructions, padding and consistency.
共同主题: benchmark, decision-model, llm-evaluation
Independent, reproducible benchmark: a decision model (jev), eight constrained LLMs, and deterministic baselines on typed decisions - accuracy, calibration, latency, cost, failure modes
共同主题: benchmark, decision-models, llm-evaluation