LLM-orchestrated training: zero human labels, custom seg models at 30+ FPS on edge

iamrobotbear · x · 2026-09-08

What happened

LearnOpenCV used GPT-6 Astra Ultra as an orchestrator to train two segmentation models (RF-DETR-Seg-M) with zero human-supplied labels, from one lazy prompt. Held-out tests show Astra-generated masks approach SAM3 quality.

The workflow

The thesis

Use a large, slow (1T+ parameter) model that knows a lot to train a purpose-built, fast, small model for edge deployment — framed as the future of realtime vision models.

Original post →

More from coding & agent

coding & agent channel →