{
  "docId": "019dd923-5e88-73ef-bd5d-06b04d219fea",
  "docSlug": "dd91c78f6570bf29",
  "documentTitle": "2023 Air Street Capital The State of AI Report 2023",
  "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": 28,
  "pageCount": 163,
  "prevPage": 27,
  "nextPage": 29,
  "slideType": "industry_trends",
  "function": "analyze_data",
  "density": "dense",
  "nDataPoints": 3,
  "notes": "The slide uses three separate line charts to illustrate data exhaustion timelines for different data types.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "line_chart"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-06b04d219fea/28",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-06b04d219fea",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-06b04d219fea.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-06b04d219fea#slide-28",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Assuming current data consumption and production rates will hold, research from Epoch AI predicts that “we will have exhausted the stock of low-quality language data by 2030 to 2050, high-quality language data before 2026, and vision data by 2030 to 2060.”",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a222-2dc375c77b34",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.54,
        "x": 0.23,
        "y": 0.53
      },
      "kind": "chart",
      "text": "Figure 1: ML data consumption and data production trends for low quality text, high quality text and images.",
      "attrs": null,
      "subkind": "line",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "3a02e52d-bc66-4c06-bb84-89fb9186a5a2",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Data exhaustion date: 2026",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a222-30b2acfdbd3f",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.92,
        "x": 0.04,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "Assuming current data consumption and production rates will hold, research from Epoch AI predicts that “we will have exhausted the stock of low-quality language data by 2030 to 2050, high-quality language data before 2026, and vision data by 2030 to 2060.” Notable innovations that might challenge the hypotheses in the article are speech recognition systems like OpenAI’s Whisper that could make all audio data available for LLMs, as well as new OCR models like Meta’s Nougat. It is rumored that plenty of transcribed audio data has already been made available to GPT-4.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "26e0e1df-d97c-4aa1-be4f-25c30eae0998",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.45,
        "x": 0.04,
        "y": 0.14
      },
      "kind": "title",
      "text": "Are we running out of human-generated data?",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a63a9529-5fcc-4d87-88ae-cc1871f79b6e",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Curiosity Gap",
      "slug": "curiosity-gap",
      "agent": "Storyteller",
      "layer": "block",
      "matchId": "019dd95a-1055-74e0-a957-3d8d54feb6c7",
      "evidence": "Question title 'Are we running out of human-generated data?' opens a gap.",
      "confidence": 70
    },
    {
      "name": "Data Story Arc",
      "slug": "data-story-arc",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "5c1dc49d-6e62-4291-873f-890fa768498c",
      "evidence": "Assuming current data consumption and production rates will hold, research from Epoch AI predicts that “we will have exhausted the stock of low-quality language data by 2030 to 2050, high-quality language data by 2050”.",
      "confidence": 0.7
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 120,
      "from": 11,
      "beatId": "019dd95a-0682-776c-8e35-41afd44ef59f",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Research + Industry sections inventory model, compute, funding facts.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 120,
      "from": 11,
      "beatId": "019dd95a-0682-776c-8e35-523bfb7f96e6",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Escalating capabilities, compute concentration and capital flows.",
      "position": 2,
      "confidence": 45,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 31,
      "from": 22,
      "name": "Zoom In",
      "slug": "06-zoom-in",
      "bestFor": "Technical deep-dives, case studies, detailed analysis",
      "matchId": "019dd95a-07fe-70ce-8d3d-ea04ad01cb62",
      "evidence": "Slides drill from emergent-capability mirage into context-length, memory and data-exhaustion details.",
      "position": 3,
      "objective": "Zoom into the data and context-length bottleneck",
      "structure": "The Big Picture -> Key Area of Focus -> Specific Detail -> Implication",
      "confidence": 72,
      "description": "Start broad, then progressively focus on specific details that prove your point"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}