[News Explained] Skild AI S1: Can a Robot Learn a New Task From One Video?

Robot preparing to repeat a plant-potting task shown in one human video

Skild AI says S1 can execute unseen, long-horizon robot tasks from one video demonstration without task-specific weight updates. This article explains its 66% versus 9% internal benchmark, the human-recovery condition behind that metric, and what still must be proven for reliable factory deployment.

[Explainer] What Is a World Model? How Robots Imagine the Future Before Acting

Robot comparing several predicted futures before acting

A robot world model predicts how the environment may change under candidate actions, helping with planning, evaluation and training. This explainer covers action-conditioned prediction, real robot examples and why visually plausible futures still require closed-loop validation and independent safety controls.