proomt

Search

Search posts, papers, and topics

All posts

Hacker News front pageAmal-David12 min readintermediate

Jev – a curation of Jev demos on X, tools, skills, and integrations

Read on github.comHN 88·34 comments

Summary

A curated list of 36 open‑source projects, demos, and tools built with the Jev decision‑making model, including SDKs, browser/desktop automation, agent integrations, and creative games, plus a quick‑start Python example.

  • Jev is a typed‑decision model that returns yes/no probabilities or scores, not free‑form text.
  • Official TypeSafe SDKs exist for JavaScript/TypeScript and Python; a quick‑start snippet shows a ticket‑routing request.
  • The repo catalogs 36 reviewed projects across categories: SDKs/skills, browser/desktop tools, agent tools, apps/integrations, games, and independent models.
  • Many integrations combine Jev with existing automation frameworks (Playwright, Cua driver, Home Assistant) or other LLMs for UI control.

Jev demonstrates a practical pattern for using typed decision models to augment automation and agent workflows, offering a concrete alternative to text‑generation LLMs when the problem reduces to selecting among discrete options.

5/10
llmautomationtypescriptpythonml infraagents

Related reading

  2. I turned Jev into a (lousy) chatbot

    jevchat is a Python CLI that turns the Typesafe Jev API into a symbol‑level chatbot by repeatedly asking Jev which next character to emit. It offers interchangeable sampling strategies and alphabets, live generation stats, and a benchmark mode that quantifies performance trade‑offs.

    Hacker News front pagegithub.com5 minHN17349

  3. Reverse-engineered Jev-like model

    Jevlike is an open‑source starter model that scores a list of text options in a single forward pass. It provides a minimal architecture (option queries, shared dot‑product scorer), synthetic data generation, training/evaluation CLI, and examples on Doom and chess. The repo supports a byte‑level encoder or a frozen Hugging‑Face encoder (e.g., Qwen2.5‑0.5B), runs on CPU/MPS/CUDA, and reports benchm…

    Hacker News front pagegithub.com4 minreleaseHN16224

  4. Introducing System One Models and Jev

    TypeSafe AI announced its first “System One” model, Jev, a non‑text‑generating LLM that outputs type‑safe structured decisions with calibrated probabilities. It claims 40‑200× lower latency (70‑500 ms) and 100‑500× lower cost versus frontier LLMs, no hallucinations, and parallel sampling. The post includes a side‑by‑side demo, a custom “workflow” benchmark comparing Jev to GPT‑5.6/6 and other mod…

    Hacker News front pagetypesafe.ai9 minHN1824480lobste.rs26

  5. TypeSafe AI's Jev now available on AI Gateway

    Vercel AI Gateway now offers Jev, a probabilistic decision model that returns typed choices, scores, and booleans instead of raw text. TypeSafe AI reports it runs up to 193× faster and 445× cheaper than standard LLMs, exposed via the experimental evaluate API in AI SDK 7.

    Vercelvercel.com2 minrelease

  6. Jev is the fastest-adopted model in AI Gateway history

    Vercel reports that the Jev decision model was adopted by 13% of paid teams within its first day, outpacing prior model launches. Jev claims to be up to 194× faster and 445× cheaper than general‑purpose LLMs while returning structured, probabilistic decisions.

    Vercelvercel.com1 minHN21