proomt

Search

Search posts, papers, and topics

All posts

Hacker News front pagekyle-pena-nlp5 min readtutorialintermediate

I turned Jev into a (lousy) chatbot

Read on github.comHN 170·48 comments

Summary

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.

  • jevchat wraps the Typesafe Jev API as a symbol‑level chat model, sampling next symbols via probability distributions.
  • Supports multiple strategies (choice, bisect, buckets, refine) and alphabets (lower26, ascii, tokens, words1k, bpe5k) selectable via CLI flags.
  • Provides live stats (symbols/s, API latency) and can run beam search, temperature, repetition penalty, and ensemble queries.
  • Benchmark mode compares all mode combinations, showing hypothesis presentation triples top‑1 accuracy on character alphabets.

LLM engineers who want to experiment with low‑level token sampling and cost‑aware chat interfaces will find it useful.

6/10
clillmpythonsampling

Related reading

  1. 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

  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

  5. 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

  6. 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