WHAT NEW IN X11.04 WED

AI collections from X · 22 collections · 67,905 posts

jevIMAGE

Using Jev as a classifier to detect agent bad practices

The author built feedback tools that detect bad practices in agent output and treats Jev as a classifier model to judge whether an output violates them.

julian
@crucianijmArchived 2026.09.30Originally posted 2026.09.30
Using Jev as a classifier to detect agent bad practices
julian @crucianijmOriginally posted 2026.09.30
Open original on X

for the past couple weeks, I've been playing around with improving agent output through feedback tools that detect bad practices while working on this, Jev and a lot of competing classifier models came out, a natural fit for this problem

x.com/crucianijm/status/2105026835021279480Archived 2026.09.30 10:06