Sakana AI's Smart Cellular Bricks featured in Scientific American: 197 bricks self-identify and self-repair
SakanaAILabs · x · 2026-09-17
Scientific American's latest issue features Sakana AI's Smart Cellular Bricks research, led by Sebastian Risi with IT University of Copenhagen and Autodesk. Each of 200 simple cubes runs the same small neural network and talks only to direct neighbors — no central controller, no sense of position. From purely local exchanges, the collective converges on the correct global shape, locates damage, and guides its own repair, achieving 100% accuracy across 197 physical bricks.
Related event: Sakana AI's Smart Cellular Bricks Published in Nature Communications(2 posts)→
More from Embodied
- NVIDIA Launches V2D Challenge to Teach Robots From Video — YunzhuLiYZ · 2026-09-17
- Ex-Tsinghua/BIGAI team's generalist dexterity policy beats Astra on RoboDojo — chris_j_paxton · 2026-09-17
- GPT-Policy: In-Context Robot Learning with VLM Agents, No Gradient Updates — Dongzhou Cheng · 2026-09-17
- World Labs' Atlas Scans by Generative Guessing; NeRF Creator Admits Productization Is Hard — cen6wkf · 2026-09-17
- CXMT's LPDDR5X lands in flagship phone as Nubia ships $885 Doubao AI handset — pstAsiatech · 2026-09-17
- Embodied-data startup Aiood AI raises nine-figure RMB round to build full-stack robot training data infra — 创业邦 · 2026-09-17