#foundation-model

Google Research trained SensorFM on more than one trillion minutes of consented wearable data from five million people. The model beat feature-engineered baselines on 34 of 35 health prediction tasks, pointing to a more general route for wearable health AI.

A high-scoring Hacker News post spotlights FDM-1, a video-native computer action model trained on an 11-million-hour dataset. The release emphasizes automatic action labeling with IDM and large-scale forking-VM evaluation for long-horizon interaction tasks.