{
  "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": 43,
  "pageCount": 188,
  "prevPage": 42,
  "nextPage": 44,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "balanced",
  "nDataPoints": 4,
  "notes": "The slide contrasts formal theorem proving datasets with the new MATH dataset, highlighting the difficulty of the latter even for humans.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "screenshot"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-fd5012384ae3/43",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3#slide-43",
  "components": [
    {
      "bbox": {
        "h": 0.05,
        "w": 0.8,
        "x": 0.05,
        "y": 0.23
      },
      "kind": "callout",
      "text": "Models do poorly on competition mathematics problems that test for reasoning and problem solving ability.",
      "attrs": null,
      "subkind": "primary",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "43fe5fdd-098e-4f98-a1d6-ba0fa95cbbe5",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.6,
        "w": 0.45,
        "x": 0.52,
        "y": 0.3
      },
      "kind": "image",
      "text": "Visual examples of Metamath, DeepMind Mathematics, and MATH datasets.",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e094e19d-70d9-4687-923f-0da44b18bece",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.6,
        "w": 0.45,
        "x": 0.05,
        "y": 0.3
      },
      "kind": "list",
      "text": "Researchers from Berkeley introduce MATH, a dataset of math competition problems formulated in natural language. They test two models, GPT-2 and GPT-3, showing mediocre scores (3-7%). A CS PhD student achieved only 40%.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "99a5b913-58fe-4c68-92e2-12b57d76c83a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Accuracy score: 7%",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d28-0e07a4094241",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.7,
        "x": 0.05,
        "y": 0.15
      },
      "kind": "title",
      "text": "And don't expect language models to help you with your math tests either",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a36247fd-7070-45a8-9490-cad84b1f7b70",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "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": 51,
      "from": 41,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-576c8c35c986",
      "evidence": "Codex, math limits, truthfulness, prompt engineering, SuperGLUE, multilingual LLMs.",
      "position": 6,
      "objective": "Trace LLM frontier and the prompting paradigm",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 78,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}