WHAT NEW IN X11.05 THU

AI collections from X · 23 collections · 69,408 posts

jevVIDEO

JevBench soft-launches as unit tests for Jev decisions

JevBench runs your Jev question against examples you have already labeled and shows where Jev disagrees, with a free no-signup Playground of recorded Jev runs.

Yusuke
@yusukelpArchived 2026.09.29Originally posted 2026.09.28
Yusuke @yusukelpOriginally posted 2026.09.28
Open original on X

Soft-launching JevBench today. looking for honest feedback. JevBench is unit tests for Jev decisions. It runs your Jev question against examples you've already labeled and shows where Jev disagrees. The free Playground has real recorded Jev runs, no signup. Try it and tell me where it's confusing (link in comment👇)

x.com/yusukelp/status/2104583000457675181Archived 2026.09.29 10:06