Trendora
vien

Jev

Trial

Platforms

TypeSafe AI's early-access frontier model optimized for structured outputs and calibrated confidence.

Why it's here

Placed in Trial: 6 article(s) of evidence from 4 source(s), led by model releases, with 6 in the last 30 days. Confidence 64%.

Evidence (6)

  • 5Hacker News·9/29/2026research
    Jeeves: reasoning improves Jev-like decision models

    Jeeves is an open-source project from PostHog that explores how adding reasoning can improve Jev-like decision models. The repository presents the approach and implementation details for applying reasoning to decision-making systems.

  • 6Hacker News·9/28/2026model_release
    Jeff: 0.8B decision models trained at home

    Jeff is an open-source project for Jev-compatible decision models with 0.8 billion parameters, trained at home and reported to run in about 30 milliseconds. The release appears aimed at making small, fast decision models easier to experiment with and deploy locally.

  • 4Hacker News·9/27/2026research
    Critique of AI confidence scores and failure handling

    The article argues that AI systems with confidence scores can create false trust if users do not have calibrated thresholds, evaluation pipelines, and clear cost models for uncertainty. It contrasts ordinary software failures, where ownership and root causes are usually identifiable, with opaque AI outputs that can simply be dismissed as acceptable error.

  • 4Hacker News·9/25/2026open_source
    Show HN: Jev Plays Pokémon Red

    A Hacker News user shared an open-source project that uses Jev to play Pokémon Red and streams the game live with token and cost tracking. The project was built to push the system beyond simpler games like Tetris and is available on GitHub for others to explore or extend.

  • 6The New Stack·9/21/2026open_source
    Kev: a tiny Jev-like decision model family built on Qwen3.5

    Kev is an open-source family of small decision models inspired by Jev, built on top of Qwen3.5. The project appears aimed at lightweight model experimentation and practical decision-making tasks, and has drawn substantial Hacker News attention.

  • 7Simon Willison·9/15/2026model_release
    TypeSafe AI launches System One models and Jev

    TypeSafe AI has introduced System One Models, a new model class aimed at producing fast, structured decisions for software automation. Its first early-access model, Jev, is presented as an alternative to chat-oriented LLMs, emphasizing calibrated probabilities, structured outputs, and lower latency.