S1 Robot Demo: Zero-Finetuning Execution of New Tasks from One Video
deepakpathak · x · 2026-08-28
A case shared by Joe Harris highlights the rapid adaptation of robot S1, requiring zero fine-tuning or post-training. By showing S1 a video demo of a new task, it infers the goal and translates it to its own body for execution. Skild moved from a potting demo to autonomous execution in just 11 minutes, with one prompt matching the efficacy of 380 post-training examples. S1 performed unseen workflows lasting up to 10 minutes and spanning dozens of steps, such as making pancakes, brewing coffee, and potting plants. While the average per-step success rate is 66% on internal benchmarks, this marks a shift where robots can be retasked rapidly via prompts.
More from Embodied
- Avride (ex-Yandex self-driving): 600k deliveries & 100k autonomous rides — demian_ai · 2026-08-28
- Tesla Optimus supply chain scaled for 70k units, silence signals commitment — JOBhakdi · 2026-08-28
- AI tennis ball machines are so good they might steal coaching jobs — EddyVGG · 2026-08-28
- 8.64s Robot Overtakes Field After Slow Start in Race — TansuYegen · 2026-08-28
- China Demonstrates Flying Taxi That Lands Outside Office Buildings — TansuYegen · 2026-08-28
- SkildAI releases S1, a robotics foundation model for one-shot learning — deepakpathak · 2026-08-28