Has anyone tried Jev as a relevance filter for RAG?
builders ask whether Jev works as a retrieval relevance filter and reranker, probing the boundary the reported negative reranking result already hinted at.
它做什么判断
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
Inferred from this project's own one-line summary in the community list — it reads as a SCORE + NOUL decision. Read the source to confirm.
更多相关实践与讨论项目
Introducing System One Models and Jev (Hacker News)1,800-point launch thread whose ~480 comments debate whether typed decisions replace LLM calls for classification, routing, and verification.Launch thread by Diogo Almeidathe 63k-like announcement from TypeSafe's founder arguing RLCD-trained decision models are a shorter path to economic value than chat models.Model router built with Jev948-like demo where Jev decides which model should serve a request before it is forwarded.MLP on Qwen 4B mimicking Jevbuilder reports that a small MLP trained on top of Qwen 4B already reproduces Jev-like decision behaviour.