---
type: "post"
id: "introducing-s1-in-context-learning-for-robotics-analysis-85f282"
slug: "introducing-s1-in-context-learning-for-robotics-analysis-85f282"
title: "Introducing S1: In-Context Learning for Robotics"
description: "Skild AI is presenting video-conditioned in-context learning as a way to reduce the need for task-specific robot training."
retrieval_nugget: "Skild AI is presenting video-conditioned in-context learning as a way to reduce the need for task-specific robot training."
published_at: "2026-10-17"
updated_at: "2026-10-17"
record_date: "2026-10-17"
date_kind: "published_at"
topics: ["models","context-engineering"]
source_urls: ["https://www.skild.ai/blogs/s1"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:introducing-s1-in-context-learning-for-robotics-analysis-85f282"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:80e31e6fa8c6e1db58b089d522428a7d84538219ca71538762eaeaea98b4bd73","reviewed_at":"2026-10-17T04:00:57.712Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Skild AI is presenting video-conditioned in-context learning as a way to reduce the need for task-specific robot training.","observed_facts":[{"text":"Skild says S1 was pretrained on episodic data where tasks are specified through demonstrations.","source_urls":["https://www.skild.ai/blogs/s1"]},{"text":"Skild reports examples of out-of-distribution skills and long-horizon tasks lasting up to ten minutes, with the same model weights and no post-training for those examples.","source_urls":["https://www.skild.ai/blogs/s1"]}],"mechanism":"S1 receives a video demonstration as context and maps the demonstrated intent to actions in its current scene and embodiment, without changing model weights during the examples described.","why_now":"The company argues that current robotics workflows require substantial deployment-condition data and fine-tuning for each new task, making adaptation a bottleneck.","implications":["If independently reproduced across settings, demonstration-time adaptation could shift some robotics effort from collecting task-specific datasets toward producing and validating useful demonstrations."],"evidence_boundary":"These results are presented by Skild AI in its own blog; the supplied source does not provide independent replication or establish general deployment performance.","watch_conditions":["Watch for the promised deeper account of training and for evaluations that specify robot embodiments, task counts, success rates, and repeatability."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific Skild AI S1 claim; this creates a distinct record of its reported video-conditioned manipulation results."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/introducing-s1-in-context-learning-for-robotics-analysis-85f282/","markdown":"https://newruntime.com/posts/introducing-s1-in-context-learning-for-robotics-analysis-85f282.md","json":"https://newruntime.com/posts/introducing-s1-in-context-learning-for-robotics-analysis-85f282.json"}
---

# Introducing S1: In-Context Learning for Robotics

## Retrieval answer

Skild AI is presenting video-conditioned in-context learning as a way to reduce the need for task-specific robot training.

Skild AI is presenting video-conditioned in-context learning as a way to reduce the need for task-specific robot training. S1 receives a video demonstration as context and maps the demonstrated intent to actions in its current scene and embodiment, without changing model weights during the examples described. The company argues that current robotics workflows require substantial deployment-condition data and fine-tuning for each new task, making adaptation a bottleneck.

Skild says S1 was pretrained on episodic data where tasks are specified through demonstrations. It reports examples of out-of-distribution skills and long-horizon tasks lasting up to ten minutes, with the same model weights and no post-training for those examples. If independently reproduced across settings, demonstration-time adaptation could shift some robotics effort from collecting task-specific datasets toward producing and validating useful demonstrations. That implication is conditional: the post alone does not show that this reduces total deployment cost or works across robot types.

These results are presented by Skild AI in its own blog; the supplied source does not provide independent replication or establish general deployment performance. Watch for the promised deeper account of training and for evaluations that specify robot embodiments, task counts, success rates, and repeatability. The company’s claims make S1 worth tracking, but do not yet establish general-purpose capability.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Context Engineering](https://newruntime.com/topics/context-engineering.md): Explore the context-engineering topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)