Open Dataset Teaches AI to Design Atomically Precise Diamond NEMS Parts
_Stocko_ · x · 2026-11-12
A new open-source repo, DiamondMachineParts (MIT license), publishes a library of molecular machine parts with structure and simulation files — gears, bearings, clutches, springs, grippers, a prototype motor, and a rod-logic 1-bit full adder — for teaching AI to design atomically precise diamond NEMS. The author fed the full 250MB archive to an AI assistant, which performed a programmatic inventory of the entire library; the author called the result "much better than I expected." The dataset is publicly available for reuse.
More from Embodied
- CoRL 2026 SPIN workshop talk: robots learning through interaction and why structure aids scale — GeorgiaChal · 2026-11-12
- Fable 5.2 digital twin nails real-robot rollout, aiming for sim RL training and evals — DominiqueCAPaul · 2026-11-12
- CoRL 2026 SPIN workshop talk: Learning by Trying, physical reasoning from puzzles to contact — leto__jean · 2026-11-12
- Shenzhen's Robonova opens pre-orders for bionic humanoid companion Eva, ships Q1 2027 — CyberRobooo · 2026-11-12
- Lisa Su joins Fei-Fei Li at CoRL 2026 to discuss robotics and physical AI — drfeifei · 2026-11-12
- Tesla Robotaxi crosses 5M autonomous miles with zero airbag deployments — XFreeze · 2026-11-12