{
  "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": 52,
  "pageCount": 313,
  "prevPage": 51,
  "nextPage": 53,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 2,
  "notes": "Includes a visual example of the model's output.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "paragraph",
    "screenshot"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0d0f98caffe1/52",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1#slide-52",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Despite being a video model, Sora 2 can \"solve\" text benchmarks when framed visually.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-41ac-7180-a81e-65aca53a81c6",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.2,
        "x": 0.76,
        "y": 0.395
      },
      "kind": "image",
      "text": "Visual example of Sora 2 output",
      "attrs": null,
      "subkind": "photo",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "88ab3975-c9bf-408f-92f3-0e561b56eed8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.68,
        "x": 0.02,
        "y": 0.37
      },
      "kind": "list",
      "text": "Sora 2 is trained and post-trained on large-scale video so the model keeps track of objects and cause-and-effect over time. Shots link together more coherently, bodies and materials behave more plausibly, and audio is generated in step with the visuals to sell the scene.\nDespite being a video model, Sora 2 can “solve” text benchmarks when framed visually. EpochAI tested a small GPQA Diamond sample and Sora 2 reached 55% (vs 72% for GPT-5) by prompting for a video of a professor holding up the answer letter. Four videos were generated per question and any clip without a clear letter was marked wrong.\nA likely explanation is a prompt-rewriting LLM layer that first solves the question and then embeds the solution in the video prompt, similar to re-prompting used in some other video generators.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "64f73741-b43a-40ea-95ab-b480f19d9070",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "GPQA Diamond accuracy: 55%",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-41ac-7180-a81e-68dd8df706de",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.68,
        "x": 0.02,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "OpenAI's second-gen Sora adds synchronized dialogue and sound, stronger physics, and much tighter control over multi-shot scenes. It can also insert a short “cameo” of a real person with their voice and appearance into generated footage, and launches alongside an invite-only iOS app for creation and remixing.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "fbb498e3-6106-4ff2-8c54-b51f81986a58",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.95,
        "x": 0.02,
        "y": 0.13
      },
      "kind": "title",
      "text": "OpenAI launches Sora 2: controllable video-and-audio inches toward a world simulator",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "4442fd04-14fa-4e92-be11-148509d2f489",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "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
}