shipwithjev

Research & data

124 builds · page 3 of 4

  1. 0449

    jev-korean-benchmark

    Small Korean/English sample study with recorded responses, including medical-text questions; not a clinical validation.

    mahlernim · Research & data

  2. 0448

    jev-eval

    Independent Jev versus GPT-5.6 Terra comparison on three labeled classification tasks, reporting accuracy, calibration, latency, and cost.

    4esv · Research & data

  3. 0447

    jev-benchmarks

    Reproducible evaluation for calibration, selective risk, and latency.

    AbdelStark · Research & data

  4. 0446

    jev-behavior-study

    Independent synthetic-task study of Jev 1.13.0 framing sensitivity and failures, with raw responses and offline report checks.

    RINNECODER · Research & data

  5. 0445

    Jev vs. ML

    Compares a typed decision model with classical classification pipelines across eight datasets, with a published protocol and an interactive report.

    QuicqDev · Research & data

  6. 0444

    Jev Visual

    Educational MLX/Qwen vision-language experiment sharing image context across candidate-scoring questions; its probabilities are not calibrated correctness estimates.

    hr98w · Research & data

  7. 0443

    jeff

    Self-hosted implementation of Jev's System One API on the 400M-parameter GLiFormer model.

    logan-markewich · Research & data

  8. 0442

    Janus

    Measures when to use Jev versus other models and routes accordingly.

    FirasSX914 · Research & data

  9. 0441

    feelings

    BAML language support for an AI if-statement: `.feels()` as a real, typed method backed by a decision model.

    BoundaryML · Research & data

  10. 0440

    choosekit

    Scores a finite set of choices with a model you already run in llama.cpp and returns a typed decision with a probability distribution.

    NotXf1le · Research & data

  11. 0439

    Bespoke Nimble

    Open data, training recipe, and a 9B model for Jev-style choice and true/false decisions on Apple Silicon or NVIDIA GPUs.

    bespokelabsai · Research & data

  12. 0284

    1kpapers

    1,018 AI papers sorted by topic for $0.08 and published as a site.

    @nutlope · Research & data · $0.08 · 256 ms

  13. 0264

    Search and tagging on keep.md

    Cloudflare Workers has Jev now so I'm putting it to the test on https://t.co/1fK8HbSmPm - 7x faster search rerank compared to the current hybrid - 50x faster tagging of content vs GLM 4.7 Flash with no failures

    @iannuttall · Research & data

  14. 0254

    jevlike

    A Jev-like architecture, reverse-engineered, to train your own.

    @vinnylarouge · Research & data

  15. 0234

    A visual reference finder

    I built a visual reference finder with Jev One single prompt → 100 images from Cosmos, NASA, and The Met my new rabbit hole for creative work 🌻

    Albiona Hoti · Research & data

  16. 0227

    openjev-sglang

    A public Jev-compatible API on an open model: 64 tasks in under a second.

    @ekzhang1 · Research & data

  17. 0226

    openjev on Qwen 4B

    An MLP trained on top of Qwen 4B that works like Jev.

    @justALEXWORTEGA · Research & data

  18. 0225

    A local Jev

    ローカルTypesafe Jev、できたんやないか？ もうちょい速度は改善余地ありそう

    @wmoto_ai · Research & data

  19. 0220

    reflex

    A small open decision model: state and typed questions in, probabilities out.

    Kshetrajna Raghavan · Research & data

  20. 0184

    jev-search

    Offline Obsidian search, with an optional Jev rerank you approve first.

    jh1373 · Research & data

  21. 0183

    ensk

    An English-Icelandic dictionary with Jev reranking the results.

    @jokull · Research & data

  22. 0182

    jev-reviewer

    Systematic-review data from trial reports, every answer a verbatim quote.

    @asofimahmudi · Research & data

  23. 0157

    Classify rows in DuckDB

    I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!

    @hamiltonulmer · Research & data · ~10 s per 1k rows

  24. 0126

    duckdb-jev

    Ask a question about every row in SQL, and get a real SQL type back.

    Colliber · Research & data

  25. 0125

    pg_typesafe

    A PostgreSQL extension that calls Jev from SQL.

    Giulio Piccolo · Research & data

  26. 0124

    Jev Capability Atlas

    Where Jev holds up and where it breaks, with real API receipts.

    Zaious · Research & data

  27. 0111

    Which outreach signals book demos

    JEV is insanely fast. We gave it a massive dataset based on thousands of outreach messages and asked: Which intent signals generated the most booked demos? 40 seconds later, we had the answer. Cost: less than $0.20. JEV can also rank leads, measure prospect-message fit, and

    @pierreeliottlal · Research & data · <$0.20 · 40 s

  28. 0108

    Filtering WIP todos by meaning

    Using Jev to filter through my @wip todos It allows me to super quickly find all the instances where I increased revenue, got stuck, switched to a different SaaS provider, etc Things a regular keyword search would never catch

    @marckohlbrugge · Research & data

  29. 0107

    Natural-language search over Zillow

    Jev can serve as better natural language search on websites. It can scan thousands of Zillow listings and classify properties by things you can't normally filter for - e.g. architecture, renovation status, proximity to freeways. This was done in <20 sec and costs $0.18 👇

    @venturetwins · Research & data · $0.18 · <20 s

  30. 0101

    Which exam questions come back

    JEV IS INSANE. I gave it 80 real exam questions and 297 practice ones. In 80 seconds, it told me which ones are most likely to appear on the real exam and which ones aren’t. All for $0.0256. Can't stop playing with @typesafeai 😁

    @hametgholizadeh · Research & data · $0.0256 · 80 s

  31. 0089

    A 26-sheet plan set in 2.9 seconds

    Built a construction plan-set classifier with Jev. Proq turns civil and building plan sets into bills of materials using an LLM pipeline we built on GPT-4.1. Jev classified an entire 26-sheet plan set in 2.9 seconds for $0.0052. It matched GPT-4.1 and GPT-6 Astra on 100% of

    @hari_trinay · Research & data · $0.0052 · 2.9 s

  32. 0078

    Tocsin

    22.8M log lines grouped into patterns, then one question each.

    @TPateeq · Research & data · $0.64 · 6 min

  33. 0072

    jev-align

    Turns human labels into calibrated Jev classifiers with GEPA.

    Sutro · Research & data

  34. 0068

    OpenJev Verdict 2.0

    A 151M non-autoregressive decision engine, with its numbers published.

    Heman10x · Research & data

  35. 0065

    jev-evaluation

    Nine experiments and 28 predictions, all fixed before any data.

    Will Kelly · Research & data · $12.69

  36. 0064

    visual-jev

    Typed decisions over images, not text descriptions of images.

    Andrue Anderson · Research & data

  37. 0048

    jevchat

    A chatbot built out of a model that only answers typed questions.

    Kyle Pena · Research & data

  38. 0047

    OpenJev

    An open attempt at a Jev-class decision model.

    SiliconLabAI · Research & data

  39. 0036

    open-spark-jev

    Local System One models on Qwen3, for an NVIDIA DGX Spark.

    Abhishek Rai · Research & data

  40. 0035

    ChatJev

    Driving the classifier as a next-token predictor, one token at a time.

    Erik Dunteman · Research & data