Skild's S1 robot foundation model switches tasks via prompt, no retraining needed
rohanpaul_ai · x · 2026-09-09
Skild AI's new robot foundation model S1 demonstrates "prompt steerability": in the same kitchen, different video prompts induce distinct action sequences, including the far out-of-distribution task of putting a plate in a toaster.
Key points:
- One video demonstration, frozen weights — behavior is steered entirely by the prompt
- This means new tasks no longer require new training, which the author argues could be one of the most economically important properties of robot foundation models
- Demo by Deepak Pathak shows 4 different prompt recipes driving different behaviors in one environment
Related event: Skild's robot foundation model S1: one .mp4 is the robot's .exe(7 posts)→
More from Embodied
- Munro Live Posts Full Cybercab Engineering Deep-Dive Video — yunta_tsai · 2026-10-27
- Tesla's Robotaxi Fleet Keeps Growing in Austin — yunta_tsai · 2026-10-27
- Building Halo Infinite Forge maps with local LLMs, DCjson and Blender MCP — swagonflyyyy · 2026-10-27
- SoftBank-Backed XAG Ships Drones With Autonomous Docks That Clean, Recharge and Refill — pstAsiatech · 2026-10-27
- Toyota Enters Humanoid Robot Race Against Tesla and China With 20 Years of Research — pstAsiatech · 2026-10-27
- Robot learning researcher joins Mila to work on physical AI and RL — pcastr · 2026-10-27