Classifies AI Research Papers

Jev classified 1,018 AI research papers by choosing from 24 topics after DeepSeek V4 Flash summarized them. The author reported $0.08 total for Jev, 256ms median latency, and just over $4 of inference.

View on X cost$0.08 total; just over $4 of inferencetime256ms median latency

0xMarioNawfal@RoundtableSpace𝕏

Classifying 1,018 AI research papers with Jev cost $0.08 total at 256ms median latency, with DeepSeek V4 Flash handling summaries first and Jev picking from 24 topics, all for just over $4 of inference. https://t.co/vXkUerSaXE

Sep 18, 2026X postsView on X

Also filed under Triage & routing

Jev-Assisted Codex Model and Effort Routing
The project provides Jev-assisted model and reasoning-effort routing for local Codex Desktop and CLI.
Plain-English Gmail Filter Judge
The project uses Jev (TypeSafe) to judge Gmail filters written in plain English.
Framework-Agnostic Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using TypeSafe’s Jev decision model to speed up agent loops.
MCP Tool Router with Jev and MCTS
Harness-router is a lightweight tool router that uses Jev for fast tool selection and Monte Carlo Tree Search for harder multi-step decisions. It uses MCP as the tool interface and falls back when routing is uncertain.