EEG foundation model trained on public datasets, paired with a ~$50 BCI device
melnykowycz · x · 2026-09-28
Developer kanair reports training an EEG foundation model on public brain-signal datasets worldwide, with key improvements yielding surprisingly strong results.
The plan: combine the model with an ultra-cheap ($50) EEG device and BCI games to build a data flywheel—more users generate more brain data, improving the model and attracting further adoption.
More from Embodied
- Chinese rescue drone flies at 30 mph to deliver flotation for two 80 kg adults — rohanpaul_ai · 2026-09-28
- Micron-scale robots that move, think and communicate can now be fabricated on standard semiconductor equipment — BlackHC · 2026-09-28
- RollerCoaster Tycoon goes spatial: 1999 pixel game rebuilt with voxels on Specs — stspanho · 2026-09-28
- RoboSSM: State-Space Models Enable Robots to Keep Improving at Test Time Without Fine-Tuning — yifengzhu_ut · 2026-09-28
- Robotics pioneers split on humanoid timelines: action data, not LLMs, is the bottleneck — Scobleizer · 2026-09-28
- Berkeley's TRACE robots trace monochrome data center cables via bidirectional tracing — berkeley_ai · 2026-09-28