Underground Deal Wire Review

Leeco used Jev to judge underground deal wires with intentional misspellings designed to evade platform detection. The batch covered 267 wires and 4,005 judgments, with 63% pushed to nobody.

View on X cost$0.0206 for the whole batchtimep50 724ms · fastest 515ms

Leeco@leecobaby𝕏

Pointed Jev at the dirtiest Chinese text I know: underground deal wires. Sellers misspell everything on purpose to dodge platform detection — 券 written as 卷, 津贴 as 琻壁, 元 as 亓. Regex is dead there. 267 wires × 15 questions = 4,005 judgments p50 724ms · fastest 515ms · $0.0206 for the whole batch 63% got pushed to nobody Text only. Building this into a subscription service.

Sep 21, 2026X postsView on X

Examples include 券 written as 卷, 津贴 as 琻壁, and 元 as 亓. The build is text-only, and Leeco is building it into a subscription service.

Also filed under Triage & routing

Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using Jev AI. It is designed to speed up agent loops by routing decisions without relying on large generative LLMs at every step.
Local Candidate Scoring with Jev
Bev performs local Jevfire-style candidate scoring using ternary models and a System One API. Its probabilities are candidate-relative.
Team Agent Workspace for Routing and Model Selection
Agentconnect is a team agent workspace that uses Jev typed decisions for response routing and model selection.
Desktop AI Assistant with Jev Plugin
PyGPT is a desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.