# Jev in 25 Lines of Python — a parody that classifies with a 0.6B local model

> The NobodyWho team shows the basic trick behind typed-decision models fits in one short local script.

- Org: NobodyWho
- Date: 2026-09-22
- Category: article, tutorial
- Source: https://www.nobodywho.ai/posts/jev-in-25-lines/
- Canonical page: https://ai-tldr.dev/releases/nobodywho-jev-in-25-lines/

## In short

Duarte O. Carmo's parody post rebuilds the core of TypeSafe's Jev in 25 lines: Qwen3-0.6B via llama-cpp-python reads a multiple-choice prompt, and the logits of the answer letters become class probabilities.

## What it is

Jev in 25 Lines of Python is a self-described parody blog post from NobodyWho that answers the hype around TypeSafe's Jev decision model. Duarte O. Carmo's script gives a small local model an email and three labelled options — Legitimate, Spam, Phishing — and prints a probability for each. The post admits what it leaves out: no synthetic training data and none of Jev's calibration training.

## How it works

The script loads the Qwen3-0.6B GGUF from Hugging Face through llama-cpp-python, runs the prompt once, and reads the model's scores for the next token. It keeps only the logits for the tokens 'A', 'B' and 'C', applies a log-softmax over those three, and exponentiates them into probabilities. Nothing is generated and no API is called.

## Why it matters

Next-token scores over a fixed set of options are a cheap, private way to get a classifier out of any open model, and many teams forget they can skip text generation and JSON parsing. The post reached 546 points on Hacker News, and it links to fuller open Jev-style projects for readers who want the calibrated version.

## Who it's for

developers building local classifiers

## Try it

pip install huggingface-hub llama-cpp-python numpy

## Links

- [Blog Post](https://www.nobodywho.ai/posts/jev-in-25-lines/)
- [HN Discussion](https://news.ycombinator.com/item?id=49812769)
- [NobodyWho Repo](https://github.com/nobodywho-ooo/nobodywho)