Jev introduces a new shape of LLM—System One, aka Decision Modelskept by eddie • sep 22TypeSafe AI launched Jev, a decision model that outputs probabilistic numbers for yes/no, choice, and score queries, priced at $0.042 per million input tokens.AboutTypesafe.ai · jev-2048 · jev-leftpad · jevchat · Jev · QwenFiled#ai-agents#ai-coding#automation#developer-toolsRelatedJev introduces a new shape of LLM—System One, aka Decision ModelsThe piece presents Jev, a TypeSafe AI decision‑model that turns text inputs into probabilistic scores for yes/no, choice, and rating tasks, explores its low cost, bias risks, and community hacks.also on jev-2048, jev-leftpad, jevchat, Typesafe.ai, Jev, #ai-coding, #developer-toolsJev, Prolog, Pi, and the dream of probabilistic logic programmingThe integration of Jev with DeepClause and its Pi extension enables scalable probabilistic logic programming for expert‑system applications like SOP2AGENT.also on Typesafe.ai, Jev, #ai-coding, #developer-toolsJev means structured output is interesting againThe author contends that Jev’s speed comes from simple single‑token structured output, suggesting the technique is easily replicable and not a major breakthrough.also on Jev, Qwen, #developer-toolsJev is to tool use what RAG is to contextRAG 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 Jev, #ai-agents, #developer-toolsI Tried to Trick Pangram. I Lost. - by Brandon SovranBrandon Sovran tried multiple methods to make AI-generated text appear human to Pangram detector, but every attempt was still flagged as 100% AI.also on Qwen, #developer-tools
Jev introduces a new shape of LLM—System One, aka Decision Models