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.
More from coding & agent
- Nat Friedman: Muse was built from scratch but inspired by openclaw, bought hundreds of Mac minis — firstadopter · 2026-09-22
- Haiku 4.5 bluntly states it lacks persistent memory; dev plans custom memory engines — RileyRalmuto · 2026-09-22
- Paradigm teases Limite as a high-throughput multi-agent solver with Rainfall harness — tensorqt · 2026-09-22
- Dev open-sources Convoy, a Linear-style task board for orchestrating AI coding agents — Budget_Map_3333 · 2026-09-22
- AAV open-sources a runtime security layer for AI agent actions with MCP approvals — CarlosMarreroAAV · 2026-09-22
- Google Cloud shares 4 evaluation engineering lessons from building agent plugins — rseroter · 2026-09-22