shipwithjev

Research & data

124 builds · page 2 of 4

  1. 0550

    Jev by TypeSafe AI: 6 Product Ideas People Are Already Building With It

    That question is already being answered for Jev, the first public System One Model from TypeSafe AI. ... ## What is Jev by Typesafe AI? ... TypeSafe AI describes Jev as AI built…

    medium.com · Research & data

  2. 0549

    JEV assisted LLM Trading

    JEV is TypeSafe's System-One model (`jev-latest`), served at `api.typesafe.ai/v1/systemone`. It's text-only. No vision, no market opinions. You POST it a "state" string plus a…

    dev.to · Research & data

  3. 0548

    Jev and LLMs: who does what? - by Bilgin Ibryam

    After two years in stealth, Diogo Almeida, one of the researchers behind ChatGPT, launched Jev at TypeSafe AI. The company advertises roughly 200 times faster and 400 times…

    generativeprogrammer.com · Research & data

  4. 0547

    Jev AI Is 200x Faster Than ChatGPT.

    That gap is exactly what Jev AI is built for. Jev is a System One model from TypeSafe AI that returns typed decisions with probabilities instead of generated text. You send it…

    medium.com · Research & data

  5. 0546

    I Used AI to Audit AI Bias - The Results Exposed a Systematic Pro-American Agenda in LLM…

    > TL;DR: I ran 4 experiments using TypeSafe's Jev model to quantitatively measure geopolitical bias in AI recommendations. The results? 91.5% of the time, US models are placed…

    dev.to · Research & data

  6. 0545

    I Tested TypeSafe’s Jev, a 478× Cheaper Decision Model, Against Claude, GPT-6, Kimi,…

    I Tested TypeSafe’s Jev, a 478× Cheaper Decision Model, Against Claude, GPT-6, Kimi, MiniMax and DeepSeek. Only Two Beat It. | by Manjunath Janardhan | Sep, 2026 | Medium ... # I…

    medium.com · Research & data

  7. 0544

    I Built the First Java SDK for Jev, TypeSafe's System One Model

    Last week TypeSafe AI released Jev, a "System One" model that does something no LLM does: it refuses to talk. You send it a state (any text or JSON) plus typed questions, and it…

    dev.to · Research & data

  8. 0543

    I Built Non-Autoregressive Decision Models a Year Ago. Then a Frontier Lab Called It a…

    And then in September 2026, a well-funded frontier lab called TypeSafe AI (founded by Diogo Almeida, a co-inventor of ChatGPT at OpenAI) launched Jev. They proposed the exact…

    dev.to · Research & data

  9. 0542

    How to Use Jev by TypeSafe AI: A Practical Guide to Building AI Decisions

    TypeSafe describes Jev as a model that takes structured or unstructured state and returns typed, probabilistic decisions that software can use directly. ... ## Step 2: Understand…

    medium.com · Research & data

  10. 0541

    How to classify, route, and score with Jev and AI SDK

    Jev, a System One model from TypeSafe AI, evaluates supplied state against typed questions and returns choices, scores, and boolean probabilities without generating prose. The AI…

    vercel.com · Research & data

  11. 0540

    Five Things Developers Are Actually Building With JEV (And Why It Matters)

    Actually Building With ... When TypeSafe AI came out of stealth in September 2026 with founder Diogo Almeida, a name attached to both ChatGPT and RLHF, the framing was almost…

    dev.to · Research & data

  12. 0539

    Early experimentation using Jev to rethink harness UX - elvex

    Jev is the first public model from TypeSafe AI, released in early access on Sep 15, 2026. The announcement post is here. ... TypeSafe frames Jev as a new class of frontier model:…

    elvex.com · Research & data

  13. 0538

    Designing Production AI Systems with Jev | ArchCrux

    TypeSafe released Jev on September 15 as its first System One model. The interface is built around typed questions over some application state. Instead of generating text token…

    archcrux.com · Research & data

  14. 0537

    AI Brief: Claude's Riemann Leap, Jev, Vercel's deepsec

    ▸ TypeSafe's Jev outputs decisions, not text (source: @aigc1024, @https1024). The model does only three things: boolean judgments ("search or not"), enum choices ("fast vs plan,…

    dev.to · Research & data

  15. 0536

    200x Faster, 400x Cheaper, Zero Words: Inside Jev

    typesafe.ai built Jev to answer yes/no and multiple-choice questions in under 500ms, not to write text. Here’s the architecture behind a model that gives up string generation to…

    medium.com · Research & data

  16. 0474

    Von

    Non-autoregressive System One model with Python and TypeScript clients, published on Hugging Face under Apache 2.0.

    wfzyx · Research & data

  17. 0473

    typesafe-ai-benchmark

    LLM gateway that mimics the System One output shape for comparison work.

    iammrduncan · Research & data

  18. 0472

    tiershift

    Policy-bounded model routing for TypeScript and Python.

    iamvatsalpatel · Research & data

  19. 0471

    SemIf

    Formerly OpenJev: an independent study of typed option readout from frozen open models, with shared-prefix experiments and a WebGPU demo.

    TheoLeeCJ · Research & data

  20. 0470

    safer-with-jev

    Neon Function proxy for the Neon AI Gateway.

    andrelandgraf · Research & data

  21. 0469

    poorjev

    Local-first reproduction of the Choice/Score/Noul interface on commodity zero-shot NLI models, adding temperature scaling and conformal abstention; ships a reproducible…

    rupeshpoojary9 · Research & data

  22. 0468

    openvons

    Open decision layer for finite options across text, images, and Japanese voice commands.

    genai-craft · Research & data

  23. 0467

    OpenSourceJev

    Research experiment in local System One decisions through llama.cpp logits projection on consumer hardware.

    sabeel111 · Research & data

  24. 0466

    OpenJev (DiffusionGemma)

    Independent Jev-compatible server over DiffusionGemma/vLLM; the documented setup requires custom vLLM patches.

    razorback16 · Research & data

  25. 0465

    OpenDecision

    Open-source semantic decision engine: state, a question in natural language, and answer criteria in; a structured decision out.

    deepanwadhwa · Research & data

  26. 0464

    open-jev (MLX)

    Gemma 3 option scorer for Apple MLX that shares one prefill across candidate continuations and exposes a System One-compatible endpoint; its docs show zero-shot overconfidence…

    daseinlabs · Research & data

  27. 0463

    LocalJev

    Local Jev-compatible `/v1/systemone` server for Bun that asks DiffusionGemma for probabilities, from GitHub Next.

    githubnext · Research & data

  28. 0462

    LLM2Jev

    Adapts a local language model into a Jev-style decision engine, answering runtime-defined Choice, Score and Noul questions through SGLang.

    Yinsongxu · Research & data

  29. 0461

    LitJev

    Reproduction of Jev that turns any Qwen model into a fast decision model, serving the same `/v1/systemone` schema (Choice, Score, Noul) with no training and no generated answer…

    zhengxuyu · Research & data

  30. 0460

    Laya for Node

    Runs Laya, an open Jev-compatible System One model, from Node.js and TypeScript through ONNX Runtime.

    receptron · Research & data

  31. 0459

    jevmlx

    Jev-style parallel constrained decisions for MLX models on Apple Silicon.

    bnsd55 · Research & data

  32. 0458

    JevForge

    Auditable Qwen3.5-0.8B pipeline covering data synthesis, training, calibration, fixed evaluation, Jev-compatible serving, and public model and dataset artifacts; its metrics are…

    zwliJay · Research & data

  33. 0457

    jevcal

    Fits and drift-checks confidence thresholds against labeled data.

    abhixhek · Research & data

  34. 0456

    jevcache

    Local decision cache keyed on (model, schema, state), with redaction and canonicalisation before hashing, for cheaper repeats and deterministic replay in CI.

    hyperspaceai · Research & data

  35. 0455

    jev-search-rerank-eval

    Chinese/English retrieval evaluation comparing Jev reranking with lexical, embedding, and fusion baselines, including judge-circularity analysis.

    zhuyansen · Research & data

  36. 0454

    jev-scout golden-set study

    Hand-labeled 25-item search-triage study with pinned rubric versions and a drift baseline; reports 88% relevance and 96% credibility with all four misses decomposed.

    accuracy · Research & data

  37. 0453

    jev-reranker

    Retrieval and RAG: uses Jev Noul judgments to assess retrieved documents for relevance and usefulness as answer evidence, then sorts results and optionally filters them using a…

    hotchpotch · Research & data

  38. 0452

    jev-rerank-bench

    Fourteen-dataset reranking study with saved raw responses, paired bootstrap intervals, order-sensitivity checks, and no-relevant-document tests; comparisons remain study-specific.

    anessbelbati · Research & data

  39. 0451

    jev-rag-benchmark

    Reproducible experiments on whether reranking with Jev improves a small RAG system, on a locked Turkish dataset, with quality, latency and cost reported together.

    erendikmenn · Research & data

  40. 0450

    jev-orderby-bench

    Measures whether ORDER BY over a Jev probability is defensible (inversion rate, Score ordinality against a human grade, calibration, wording invariants, sort-key ties) under a…

    yodablocks · Research & data