Jev’s Architecture Unmasked — archerhume

kept by kotsakis sep 22

By probing Jev's API with 10k calls, the author infers Jev is a causal transformer (possibly sparse MoE) that reads shared state and outputs decision probabilities directly without text generation.

Jev is to tool use what RAG is to context
RAG pre-selects model input context while Jev pre-selects model output options; both constrain the model to a developer‑defined frame, contrasting with fully agentic models that decide dynamically.
also on typesafe, Jev, #ai, #developer-tools
Jev is an honest game changer.
Jev, a constrained decision model, matched Grok's 89.6% accuracy on 48 game questions while cutting latency 84% and cost 88.5% by using a selective Gemini fallback.
also on Jev, #software-engineering, #developer-tools
Jev, Prolog, Pi, and the dream of probabilistic logic programming
The integration of Jev with DeepClause and its Pi extension enables scalable probabilistic logic programming for expert‑system applications like SOP2AGENT.
also on Jev, #software-engineering, #developer-tools