Codex Hooked Up to Local VLM for Photo Organization
zakelfassi · x · 2026-07-15
The author mentions that this approach sounds like "AI insanity," but it's actually just their everyday way of expressing things. They recently built a practical workflow: connecting **Codex** to a local **VLM**, using an orchestrator to manage the vision model, and layering their own human judgment on top of the output. This pipeline is used to organize family photos and milestone materials like birthdays, archiving and supplementing them by dimensions such as subcategories and months.
More from coding & agent
- AI makes software easier to build, but it also lowers the floor on quality — paw_lean · 2026-07-21
- Fable coding run costs $6.69 for 67 lines of code in a 4-minute job — bytebot · 2026-07-21
- Cursor writes better code, but ChatGPT can still control the computer — vista8 · 2026-07-21
- Agents can remember facts, but still forget how to do the job — No_Advertising2536 · 2026-07-21
- Agent skills for project downgrade and troubleshooting tested in CLAD on LS 5.22 — stspanho · 2026-07-21
- Open-source B-roll skill turns scripts into 5-second vertical clips with Codex and Gemini — yangyi · 2026-07-21