proomt

Search

Search posts, papers, and topics

All posts

Hacker News front page2 min readrelease notesintermediate

OpenJev

Read on openjev.comHN 709·288 comments

Summary

OpenJev is a browser‑only demo that lets you load small LLM checkpoints (e.g., MiniCPM‑5 2B, Qwen3 0.6B) onto your GPU and compare two inference paths: reading raw logits for a set of options versus prompting the model to emit a JSON with option probabilities token‑by‑token. The page reports model sizes, download times, balanced accuracy on a few benchmarks, and wall‑clock timings measured with `…

  • Running LLMs in‑browser is feasible for sub‑4 B parameter models when a GPU is available.
  • Directly reading logits is faster than generating JSON token‑by‑token, but both can be timed client‑side.
  • Quantization (GGUF) reduces memory and may impact both quality (balanced accuracy 44‑88 %) and latency.
  • No data leaves the browser; the demo relies on cached Hugging Face weights and client‑side inference.

Local inference removes server‑side latency, privacy concerns, and cost, but the trade‑off is limited model size and variable accuracy. OpenJev showcases a concrete comparison of two inference strategies that could inform UI design for decision‑support tools built on edge LLMs.

4/10
llmperformancefrontendml infragpu

Related reading

  1. Laya the open source version of Jev

    Laya is an open‑source, bidirectional‑encoder model family for ultra‑fast, calibrated decision‑making (choice, score, boolean) over structured schemas. It runs 6‑8× faster than the closed‑source Jev, supports 100+ languages via three checkpoints, and includes a lightweight router that selects the appropriate checkpoint before inference. Benchmarks show higher accuracy, far better calibration (ECE…

    Hacker News front pageconvaiinnovations.com8 minreleaseHN1326313lobste.rs2

  2. 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

  3. 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

  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. 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