No VLA needed: gpt6 astra self-calibrates an SO-101 arm and sorts LEGOs in MuJoCo
mishig25 · x · 2026-09-15
Hugging Face's mishig25 released a reproducible SO-101 arm demo: instead of a VLA model, gpt6 astra self-calibrates the front camera and picks up three LEGO-like blocks into a box, all in MuJoCo simulation—no physical robot needed.
Resources are open on a Hugging Face bucket (README, scripts, verification):
- Ships a copy-paste prompt for your coding agent: read README, download files, use uv for env management, run calibration and the sorting demo, verify all three blocks land in the box;
- The controller sends six joint-position targets with physical gripper contacts; includes REPRODUCIBILITY. and a verification manifest.
Related event: gpt6 Controls SO-101 Robot Arm to Sort LEGO in MuJoCo(2 posts)→
More from coding & agent
- User builds 20-bot Grok suite to track wins, prep 1:1s and close promises — NicoVerderosa · 2026-10-30
- LangChain CEO opens Interrupt London with keynote on why orgs should own their intelligence — LangChain · 2026-10-30
- Simlock: open-source control plane gives parallel coding agents their own iOS/Android simulators — Scobleizer · 2026-10-30
- Keyfleet launches open canvas where personal AI agents team up with a shared USDC treasury — seanwbren · 2026-10-30
- Page-based project management for Grok Bots: keep chats short, history on Pages — AiJohnAllen · 2026-10-30
- How Oxide Computer uses LLMs internally — FAQ Friday #66 — Sethwinterroth · 2026-10-30