What's up y'all, made a small eval tool for jev: The goal is to have something to help me keep track of my

Evaluationby soos2026-09-18

What's up y'all, made a small eval tool for jev: https://x.com/Dayhaysoos/status/2100968892591968320 The goal is to have something to help me keep track of my improvements or regressions. Everything stored locally on an SQL database

Links

Post by @Dayhaysoosx.comI wanted an easier way to test my jev requests and see if my results are improving, so I built jevals! It's a local workbench for testng the Noul, Choice, and Score primitives. You can mix requests as well. You can run a

open source discussion

More in Evaluation

Return probabilities, not labels — 80/10/10 beats "orange"I’m building Aurapunk, an open-source multi-agent IDE.Tested jev against deepseek v4.1 flash on norwegian text.