Astra likely trained raw motor control and could outdo custom VLAs, argues researcher
teortaxesTex · x · 2026-09-27
- teortaxesTex positively judges that OpenAI trained Astra for raw motor control, likely letting it cope without tactile feedback.
- Given enough tools, he believes it would easily beat custom VLAs aside from latency — while admitting uncertainty.
Related event: GPT-6 Astra Trained on Raw Motor Control May Outperform Specialized VLAs(2 posts)→
More from Embodied
- Stanford runs OpenAI's GPT-6 Astra on a Unitree G1 robot to tidy an unseen kitchen — alex_verem · 2026-09-28
- ETH Zurich trains robotic hand to walk on its five fingers across 14 surfaces — burny_tech · 2026-09-28
- Builder brings a physical Codex Pet to San Francisco for OpenAI Dev Day — paw_lean · 2026-09-28
- Researchers debate GPT-6 Astra: a generalist VLA that could beat custom VLAs — YouJiacheng · 2026-09-28
- Eric Jang: now is the window to test OSS models on robotics before the gap closes — ericjang11 · 2026-09-28
- 10 NeurIPS 2026 robotics papers to watch: VLA inference and long-horizon tasks — shaohua0116 · 2026-09-28