JevMade hello@JevMade.com
← Back to evaluation videos

JevMade field notes / Video guide

Le nouveau modèle d'IA JEV enflamme le web : vrai ou démo truquée ?

Shubham Sharma evaluates Jev across real automation scenarios including batch email sorting, video frame text moderation, inbound scoring, and edge-case classification failures.

Original by Shubham SHARMAEvaluationIntermediate15 min 13 sec Published Source reviewed

Before you press play

What you’ll find in the video

  1. Jev evaluates supplied options and returns probabilities rather than a conversational explanation.
  2. Shubham’s screening workflow extracts text from video frames before asking Jev whether that text contains sensitive information.
  3. The counting and date examples produce errors; Shubham recommends checking confidence rather than assuming every typed decision is correct.
Worth knowing

Gemini-assisted video/transcript review. These are exploratory demonstrations, not an accuracy or privacy audit. The suggested confidence cutoff is not a validated safety threshold, and the video-text workflow uses separate text extraction rather than native Jev vision.

Le nouveau modèle d'IA JEV enflamme le web : vrai ou démo truquée ?