WHAT NEW IN X11.06 FRI

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

jevVIDEO

Braintrust tests Jev as a judge and output scorer

Braintrust ran evals to answer when and how to use Jev, testing how it performs as a judge and as a scorer of outputs, with three how-to links.

Braintrust
@braintrustArchived 2026.09.26Originally posted 2026.09.26
Braintrust @braintrustOriginally posted 2026.09.26
Open original on X

When and how should you use Jev? We've been evaling to find out. - Using Jev in Braintrust → https://braintrustdata.link/jev-eval - Testing how Jev holds up as a judge → https://braintrustdata.link/jev-vs-gpt - Scoring outputs with Jev → https://braintrustdata.link/jev-how-to

x.com/braintrust/status/2103554698275967242Archived 2026.09.26 10:11