{
  "docId": "019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "docSlug": "bf350dd574c19997",
  "documentTitle": "2021 Air Street Capital The State of AI Report 2021",
  "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": 39,
  "pageCount": 188,
  "prevPage": 38,
  "nextPage": 40,
  "slideType": "client_example",
  "function": "illustrate_case",
  "density": "balanced",
  "nDataPoints": 0,
  "notes": "Includes visual examples of DALL-E outputs for specific text prompts.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "paragraph",
    "photo"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-fd5012384ae3/39",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3#slide-39",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Indeed, the exact framing of the text prompt has a large effect on the quality of the results.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d26-946c0f4e6721",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.5,
        "x": 0.48,
        "y": 0.35
      },
      "kind": "image",
      "text": "Visual examples of DALL-E outputs for 'an armchair in the shape of an avocado' and 'an illustration of a baby daikon radish in a tutu walking a dog'",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5e25782f-983d-436b-8dad-7ed6264faa57",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.45,
        "x": 0.02,
        "y": 0.32
      },
      "kind": "list",
      "text": "DALL-E is a 12B parameters version of GPT-3 trained on text-image pairs. It receives encoded images and texts in the form of a sequence of 1280 tokens, which it models autoregressively.\nTo produce the best samples from the text prompts, the researchers use CLIP to rerank the 32 best generated images of DALL-E, which consistently yields impressive visualizations.\nA natural question that arises from this and related research is the question of forming an effective prompt. Indeed, the exact framing of the text prompt has a large effect on the quality of the results.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "09ca602a-b4e9-484f-85a6-80d0d24557c0",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.08,
        "w": 0.45,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "OpenAI's DALL-E treats text-image pairs as a generative task and thus learns to generate believable images for a wide array of natural language prompts.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "864cdd27-b8f5-4f52-af4a-693e6a2ccc93",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.6,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "DALL-E draws what you want, but be sure to instruct it well",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "2a8e35ed-3a3f-4294-8111-031cc8ded711",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-0fd5-7148-8ed1-007fc7fe9687",
      "evidence": "Title 'DALL-E draws what you want, but be sure to instruct it well'.",
      "confidence": 78
    },
    {
      "name": "Metaphor & Analogy",
      "slug": "metaphor-analogy",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "019dd95a-0fd5-7148-8ed1-044857b63b75",
      "evidence": "Anthropomorphic 'instruct it well' framing.",
      "confidence": 60
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 152,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-0affbadec38e",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions p.5-6, Exec Summary p.7, then Sections 1-3 catalog evidence.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 152,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e35-1b3ee3a1c012",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Three sections accumulating evidence of accelerating progress.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 40,
      "from": 36,
      "name": "Aha Moment",
      "slug": "03-aha-moment",
      "bestFor": "Data-heavy sections, research findings, analytical arguments",
      "matchId": "019dd95a-07fe-70ce-8d3d-53192fc75199",
      "evidence": "Diffusion models > GANs, then CLIP, then DALL-E payoff.",
      "position": 5,
      "objective": "Reveal multimodal generative AI breakthrough",
      "structure": "The Problem/Question -> What the Data Shows -> The Insight",
      "confidence": 72,
      "description": "Establish a tension, present data, then deliver the insight that changes everything"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}