---
title: "Classification"
description: "2 posts about Classification, summarised, each linking to the original."
---

# Classification
> 2 posts about Classification, summarised, each linking to the original.

## Articles

### [Decision Models in Hugging Face](https://yomu.fyi/post/decision-models-in-hugging-face.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Aritra Roy Gosthipaty, Lysandre, Pedro Cuenca, Tom Aarsen
- Published: Nov 10, 2026
- Type: Explainer

Decision models evaluate a state against typed questions—choice, score, or noul—and return a probability distribution over predefined answers without generating text. Unlike traditional classifiers, they accept runtime-defined labels, and unlike zero-shot classifiers, they handle multiple typed questions per request. The interface is State + Questions + Allowed Answers → Decisions + Probabilities, with models like JEV-9B available on the Hugging Face Hub under a dedicated tag, and the ecosystem includes encoder-based and generative backbone models. Hugging Face’s transformers library supports inference via a pipeline and fine-tuning via the Trainer API, with a toy example fine-tuning JEV-9B to route support requests to billing, shipping, or technical categories using cross-entropy loss. Decision models make decisions and probabilities first-class outputs, optimized for reliable, calibrated decisions in software, and are designed to be more efficient than prompting LLMs for structured tasks.


### [Cost per task: Using cheap classifiers to route across Gemini models and thinking levels](https://yomu.fyi/post/cost-per-task-using-cheap-classifiers-to-route-across-gemini-models-an.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sergio Villani
- Published: Nov 3, 2026
- Type: Benchmark

Per-token API prices are falling, but engineering bills for autonomous coding agents keep climbing because the dominating metric is now cost per successful task, not price per million tokens. A lightweight routing layer can intercept routine decisions before they reach an expensive reasoning model, preventing unnecessary deep-reasoning spend. The article tests TypeSafe’s Jev classifier in front of Google Antigravity’s model calls, using a single atomic Noul question to route tasks. On a 50-question coding-agent benchmark, the Jev router achieved 100% accuracy on 34 unseen held-out tasks and 96% overall, while a frozen regex and prompt-length heuristic dropped to 70.6% on unseen tasks. The most cost-effective approach is to start with a fast model on a light thinking setting, then add a near-free classifier to send only hard tasks to a stronger model.
