jevPOST
Jev can't guarantee results without training; you have to test on your own data
The author says Jev is a general-purpose classifier that can't promise results up front, so users must test it on their own data and criteria, though it does return confidence scores and is fast.
Matija Sosic
@MatijaSosicArchived 2026.09.18Originally posted 2026.09.18
Matija Sosic @MatijaSosicOriginally posted 2026.09.18
Another good question on Jev that keeps popping up: "If I don't need to train it, how can I be sure it works?" The answer is: you can't. You need to test it on your data and your criteria and verify that it works for you. It's a one-size-fits-all classifier. Just like you can't know whether an LLM's output is correct, you can't know with Jev either. But at least you get a confidence score, and it's fast.
This post quotes another post: x.com/matijasosic/status/2100190746389135772
x.com/matijasosic/status/2100635155513635088Archived 2026.09.18 10:14