freezetheflame/jev-ecosystem-research
Jev (TypeSafe AI System One) 生态调研：开源复现规模、JevBench v1.4.2.2 全量解读、可获取性与许可证陷阱、router 生态、Jev+安全科研切入点
No inclusion rationale available yet
View cited sourceThree measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.
Shared topics: benchmark, rag
Empirical zero-shot benchmark of TypeSafe Jev (v1.13.0) on low-resource Sinhala and Singlish NLP benchmarks (SOLD, SinhalaMMLU, NSINA)
Shared topics: benchmark, decision-model
Pre-registered benchmark: can a 2B local model (Gemma 4 E2B) answer web questions without making things up when a decision model (TypeSafe Jev) makes every call? SearXNG for search, MemPalace for verbatim memory, seven arms including open local judges. Spec and thresholds fixed before any run.
Shared topics: benchmark, rag