Building an image rating tool with GPT Vision and Jev: what worked and what didn't

huangyun_122 · x · 2026-09-22

A hands-on walkthrough of building a photo rating toy tool with Jev: fetch public avatar photos via randomuser, use GPT Sol to convert images into text, then run scoring in Python with Jev.

Key finding: Jev itself has no vision capability — the actual judgment relies on GPT Sol's image-to-text conversion, while Luna fails at this. The author rates the result a miss (it didn't showcase Jev's judgment on raw text) and plans to switch approaches. Suggests an API relay for those without official OpenAI access.

Original post →

More from coding & agent

coding & agent channel →