{
  "id": 3341907,
  "title": "Skild AI unveils S1, a robotics foundation model that it says can learn tasks never seen during pretraining, using a single video demo, without fine-tuning (Skild AI)",
  "url": "https://urgent.news/2026/08/25/skild-ai-unveils-s1-a-robotics-foundation-model-that-it-says-can",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-25T19:55:01.000Z",
  "source": {
    "name": "Techmeme",
    "slug": "techmeme",
    "url": "https://www.skild.ai/blogs/s1"
  },
  "original_language": "en",
  "account": "Skild AI has introduced S1, a robotics foundation model capable of learning tasks not seen during pretraining using just a single video demonstration, without any fine-tuning. This development follows the evolution of language modeling, which saw the shift from BERT to GPT-3, where models gained the ability to learn from just one or a few examples. Skild AI's S1 is designed as an in-context learner for robotics, enabling it to execute tasks after observing a video demonstration. The model's pre-training across diverse tasks enables it to understand the intent behind the demonstration, allowing it to perform unseen tasks without further fine-tuning. In-context learning for robotics aims to perform a task by demonstrating it, similar to how humans learn tasks through demonstration rather than language alone. The hard part is evaluating a model's in-context capabilities, as it depends on the context of the task in relation to the training data and the duration of the task. Skild AI's S1 has demonstrated in-context learning on extremely long-horizon tasks that were never seen during pretraining, marking a significant step forward in robotics and AI.",
  "summary": "UNSEEN TASKS10-MINUTE HORIZONSONE VIDEO PROMPTNO POST-TRAINING — The evolution of language modeling provides a blueprint …",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}