proomt

Search

Search posts, papers, and topics

All posts

Hacker News front pagef1 min readrelease notesintro

Jev-Leftpad

Read on github.comHN 228·87 comments

Summary

A joke npm package that pads strings by calling a TypeSafe LLM model, essentially replicating `padStart()` with unnecessary API calls. Not production‑ready and offers no real engineering insight.

  • The package uses a TypeSafe AI SDK to request a single choice for how many spaces to prepend, limited to 0‑10 spaces.
  • Each call incurs an external API request, can fail, and is slower and more costly than native `padStart()`.
  • Tests mock the AI, so they run without an API key or credit usage.
  • Author explicitly warns against using it in production.

Demonstrates a frivolous use of LLM APIs for trivial tasks, highlighting cost, latency, and reliability concerns when over‑engineering simple functionality.

2/10
llmapi design

Related reading

  1. 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. 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

  4. 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 minHN17048

  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. OpenJev

    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 `…

    Hacker News front pageopenjev.com2 minreleaseHN709288