Distilling a frontier model into 4B params lifts robot arm success from 0 to 22.5%

ZeYanjie · x · 2026-11-17

Developer @ishanxnagpal distilled a large model (claimed as "GPT 6 Astra", unverified) into a tiny 4B parameter model to drive a robot arm. Before distillation, the small model couldn't finish a single task — at one point it decided the bowl right in front of it didn't exist. After, it went from 0 to 22.5% success on scenes it was never trained on. The author argues the future of robotics is agentic, with a thread promising more details.

Original post →

More from Embodied

Embodied channel →