{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "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": 143,
  "pageCount": 213,
  "prevPage": 142,
  "nextPage": 144,
  "slideType": "market_landscape",
  "function": "compare_options",
  "density": "dense",
  "nDataPoints": 4,
  "notes": "The slide uses a bar chart to illustrate the price disparity between proprietary models (Runway, Luma, etc.) and open-source/cheaper alternatives.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "bar_chart_vertical",
    "screenshot"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/143",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-143",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Text-to-video tends to come with lower GPU requirements than LLMs, creating an opportunity for cheaper Chinese offerings like Kuaishou’s Kling, unconstrained by copyright fears, or highly capable open source models like CogVideoX.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d1c-c1f5c1d349b6",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.5,
        "x": 0.05,
        "y": 0.48
      },
      "kind": "chart",
      "text": "Cost per second comparison",
      "attrs": null,
      "subkind": "bar-vertical",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "33dd8db4-8a31-477f-967e-1872518816cf",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.3,
        "x": 0.65,
        "y": 0.45
      },
      "kind": "image",
      "text": "Social media post about CogVideoX",
      "attrs": null,
      "subkind": "screenshot",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "840d2efd-5c69-4869-9557-240d27557277",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Cost per second: $0.02",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d1c-c87f4f81319a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.95,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "US text-to-video start-ups sell subscription plans based on credits, but with a single second of video burning through 5 Runway or Pika credits, users have to make sure they master the art of prompting quickly. Text-to-video tends to come with lower GPU requirements than LLMs, creating an opportunity for cheaper Chinese offerings like Kuaishou’s Kling, unconstrained by copyright fears, or highly capable open source models like CogVideoX.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1328e0a1-ab8e-48bb-9eda-3c14f8817e64",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "quote",
      "text": "CogVideoX 5B - Open weights Text to Video AI model is out, matching the likes of luma/ runway/ pika! Powered by diffusers - requires less than 10GB VRAM to run inference! - Valbhav (VB) Srivastav",
      "attrs": null,
      "subkind": null,
      "toolName": "Authority citation",
      "toolSlug": "authority-citation",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d1c-c4d7f52ec5d8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.7,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "But high-end model providers face a squeeze from cheap and OS competitors",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9c4f3f5c-c1d8-48c5-9d7d-9f2926b3507f",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-1055-74e0-a95a-11b35b369a4d",
      "evidence": "Title 'But high-end model providers face a squeeze from cheap and OS competitors'",
      "confidence": 85
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 153,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e35-5f2398b8d1d0",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Exec summary + Research + Industry sections inventory the year",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 174,
      "from": 86,
      "beatId": "019dd95a-0682-776c-8e35-73133c63a096",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "Discoveries",
      "beatSlug": "voyage-return-discoveries",
      "evidence": "Industry + Politics findings on NVIDIA, regulation, geopolitics",
      "position": 3,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 147,
      "from": 137,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3e-5d103aecde20",
      "evidence": "Law 90%, Apple+OpenAI, Unsloth, Recursion-Exscientia, video gen race, Kling, mRNA, Ray-Ban, Rabbit R1",
      "position": 16,
      "objective": "Show AI penetration into law/medicine/devices/glasses verticals",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 65,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}