Jev is just a classifier, and that is fine
a technical counterpoint arguing Jev is a representation model rather than something new, and that its latency follows mechanically from one prefill plus a single parallel token per question with logprobs.
何を判断するか
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
The community list's one-line summary does not say which question type this project uses. Read the source to find out — we would rather leave this blank than guess.
関連する実践と議論の他のプロジェクト
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.