{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=jgWY66RaSrQ",
  "slug": "i-gave-an-ai-a-body-cyrus-clarke-mit-media-lab-068bqaj",
  "url": "https://feed7.dev/p/i-gave-an-ai-a-body-cyrus-clarke-mit-media-lab-068bqaj",
  "title": "I Gave an AI a Body — Cyrus Clarke, MIT Media Lab",
  "why_included": "An MIT prototype shows embodied agents need an interaction language, low-latency feedback, and human validation—not just a model connected to actuators.",
  "summary": "Cyrus Clarke connected an OpenClaw agent to a **900-pin shape display** and let it create programs for the device. A later closed-loop system generated and evaluated movements until it retained **32 usable gestures** for body-language responses.",
  "practical_implication": "For physical or ambient agents, design a small validated gesture vocabulary that can respond before slower language generation finishes. Keep machine scoring in the iteration loop, but require people to confirm that expressions are legible and appropriate.",
  "agent_context": "Cyrus Clarke connected an OpenClaw agent to a **900-pin shape display** and let it create programs for the device. A later closed-loop system generated and evaluated movements until it retained **32 usable gestures** for body-language responses.\n\nFor physical or ambient agents, design a small validated gesture vocabulary that can respond before slower language generation finishes. Keep machine scoring in the iteration loop, but require people to confirm that expressions are legible and appropriate.\n\nThis remains an exploratory Media Lab prototype, not evidence of consciousness or general robotics capability. The gesture system was unpublished at the time of the talk, and the transcript gives no formal user study, latency measurement, or safety evaluation.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=jgWY66RaSrQ",
    "published_at": "2026-09-24T15:30:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "craft",
  "domains": [
    "research"
  ],
  "topics": [
    "interface-quality",
    "tool-use"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "This remains an exploratory Media Lab prototype, not evidence of consciousness or general robotics capability. The gesture system was unpublished at the time of the talk, and the transcript gives no formal user study, latency measurement, or safety evaluation."
  ],
  "connected_context": {
    "meaning": "This extends agent-interface design into physical expression: a constrained, validated gesture vocabulary can provide immediate ambient feedback while slower language output is pending. The closed generation-and-scoring loop suggests a way to search the motion space, but human judgment remains necessary for legibility and appropriateness. The prototype does not establish dependable autonomy, safety, or broader robotic competence.",
    "corpus_size": 875,
    "generated_at": "2026-09-25T09:07:15.989Z",
    "connections": [
      {
        "title": "How GPT-5.6 Sol helps run quantum computing experiments",
        "source_name": "OpenAI",
        "source_url": "https://openai.com/index/codex-quantum-computing-experiments",
        "feed7_url": "https://feed7.dev/p/codex-quantum-computing-experiments-11sd2tq",
        "reason": "Both place an agent in a physical observation-action loop, making validation, actuation limits, and human oversight more important than in purely digital tool use."
      },
      {
        "title": "The End of the Static Screen: Architecting Intent-Driven UX — Gus Iwanaga, commercetools",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=QrMcNe2jjt8",
        "feed7_url": "https://feed7.dev/p/the-end-of-the-static-screen-architecting-intent-driven-ux-gus-iwanaga-c-0hulcxp",
        "reason": "The validated gesture vocabulary is the physical-interface analogue of constrained generative UI: agents compose within an explicit repertoire, while evaluation is still needed to ensure coherent results."
      },
      {
        "title": "\"My name is... my name is...\": A Linguistic Map for Voice Agents — Midam Kim, ServiceNow",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=IDNfAZVKvPE",
        "feed7_url": "https://feed7.dev/p/my-name-is-my-name-is-a-linguistic-map-for-voice-agents-midam-kim-servic-176sjnb",
        "reason": "The voice-agent map adds context for the proposed fast pre-verbal response: gesture may help manage turn timing, but it must remain consistent with the later spoken state to avoid interaction-level confusion."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-24T15:30:06.000Z",
  "modified_at": "2026-09-24T15:30:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/i-gave-an-ai-a-body-cyrus-clarke-mit-media-lab-068bqaj",
    "json": "https://feed7.dev/p/i-gave-an-ai-a-body-cyrus-clarke-mit-media-lab-068bqaj.json",
    "markdown": "https://feed7.dev/p/i-gave-an-ai-a-body-cyrus-clarke-mit-media-lab-068bqaj.md"
  }
}