{
  "docId": "019dd923-5e88-73ef-bd5d-0d0f98caffe1",
  "docSlug": "5df6bd1b0447b5f6",
  "documentTitle": "2025 Air Street Capital The State of AI Report 2025",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 48,
  "pageCount": 313,
  "prevPage": 47,
  "nextPage": 49,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 4,
  "notes": "The slide contains a placeholder box for a video or image. The content highlights the technical evolution from static clip generation to interactive, closed-loop world modeling.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "paragraph",
    "other"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0d0f98caffe1/48",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1#slide-48",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "World models predict the next frame from state and your actions, enabling closed-loop interactivity and minute-scale consistency.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-41ac-7180-a81f-532ebc3055b3",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.287,
        "w": 0.383,
        "x": 0.549,
        "y": 0.383
      },
      "kind": "image",
      "text": null,
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "539716ce-adb7-487d-8190-eeee68385237",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.48,
        "x": 0.04,
        "y": 0.36
      },
      "kind": "list",
      "text": "GDM's Genie 3 generates explorable environments from a text prompt at 720p / 24 fps and its consistent for a few mins.\nSupports promptable world events (e.g. change weather, spawn objects with persistence).\nShows early use for training embodied agents and even imagined worlds within the imagined world.\nOdyssey's public research preview streams a new frame every ~40 ms (up to ~30 fps) for 5+ minute sessions and the user can provide inputs on their device to navigate through the world. See video:",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5a4d0346-b523-4738-8420-44c2d21f5f0e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.12,
        "w": 0.95,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "Prior clip models (Sora, Gen-3, Dream Machine, Kling) render fixed videos you can't steer mid-stream. World models predict the next frame from state and your actions, enabling closed-loop interactivity and minute-scale consistency. Crucially, no game engines were harmed!",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5c96bd2d-a9d3-4b44-8225-557686fc2f7e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.75,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "World models step out of the clip: real-time, interactive video arrives",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "3ccae5b5-dc8b-455a-bf90-c323230aca3d",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "AIDA Model",
      "slug": "aida-model",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "a6c878a6-8a99-4735-b69a-61fc09fe7e44",
      "evidence": "The components of the slide, such as the title, headline, and callout, are structured to grab attention, generate interest, create desire, and encourage action, which are the key elements of the AIDA model.",
      "confidence": 0.7
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 189,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-9f380673831f",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Sections 1-2 lay out research findings and industry data with charts and case studies.",
      "position": 1,
      "confidence": 70,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 89,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-ac68557d958b",
      "arcName": "The Onion",
      "arcSlug": "onion",
      "beatName": "First Layer",
      "beatSlug": "onion-first-layer",
      "evidence": "Research section unpacks technical layer beneath the headlines.",
      "position": 2,
      "confidence": 45,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}