{
  "docId": "019de06f-84e4-70e4-bce4-3c7c4f09a8ea",
  "docSlug": "602cc25b036280012a1a042017f6a35d",
  "documentTitle": "OpenAI | Product Presentation Deck | 20 slides",
  "authorId": "openai",
  "authorName": "OpenAI",
  "documentKindSlug": "conference-presentation",
  "documentKindLabel": "Conference presentation",
  "sourceTypeSlug": "investor_relations",
  "sourceTypeLabel": "Investor relations",
  "presentationDate": "2017-08-01 00:00:00",
  "orientation": "landscape",
  "aspectRatio": 1.7977529,
  "pageNumber": 10,
  "pageCount": 20,
  "prevPage": 9,
  "nextPage": 11,
  "slideType": "other",
  "function": "present_framework",
  "density": "sparse",
  "nDataPoints": 0,
  "notes": "The slide shows a binary choice interface used for training AI models, specifically for reinforcement learning.",
  "elementsJson": null,
  "metadataConfidence": 0.9,
  "imagePath": null,
  "slideHref": "/slides/019de06f-84e4-70e4-bce4-3c7c4f09a8ea/10",
  "deckHref": "/decks/019de06f-84e4-70e4-bce4-3c7c4f09a8ea",
  "deckJsonHref": "/decks/019de06f-84e4-70e4-bce4-3c7c4f09a8ea.json",
  "deckAnchorHref": "/decks/019de06f-84e4-70e4-bce4-3c7c4f09a8ea#slide-10",
  "components": [
    {
      "bbox": {
        "h": 0.7,
        "w": 0.68,
        "x": 0.16,
        "y": 0.15
      },
      "kind": "image",
      "text": "Two side-by-side simulation windows with 'Left is better' and 'Right is better' buttons above them.",
      "attrs": null,
      "subkind": "screenshot",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "08aec86e-fe4b-42eb-8ed4-3294fc144f33",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.6,
        "x": 0.1,
        "y": 0.88
      },
      "kind": "paragraph",
      "text": "Requires only a few hundred binary bits of feedback!",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "8e78c0eb-5da5-430b-8531-6b79d7dcff89",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.1,
        "w": 0.4,
        "x": 0.05,
        "y": 0.05
      },
      "kind": "title",
      "text": "Human Feedback Training Process",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5e985509-e8b0-4410-aa65-82e9fc9676bf",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Process flow",
      "slug": "process-flow",
      "agent": null,
      "layer": "slide",
      "matchId": "9f7c2a90-5eab-477b-aa4d-36f5694096eb",
      "evidence": "image/screenshot: Two side-by-side simulation windows with 'Left is better' and 'Right is better' buttons above them.",
      "confidence": 0.7
    }
  ],
  "frameworks": [
    {
      "name": "reinforcement-learning-from-human-feedback",
      "slug": null,
      "matchId": "19c5ff67-57ca-4a5d-ade2-2718efa28e53",
      "evidence": "The slide depicts the binary choice mechanism central to RLHF.",
      "confidence": 0.95
    }
  ],
  "arcBeats": [
    {
      "to": 11,
      "from": 8,
      "beatId": "72a1fd78-bc62-4d21-a603-262dd269d030",
      "arcName": "Problem-Agitate-Solution",
      "arcSlug": "problem-agitate-solution",
      "beatName": "Solution",
      "beatSlug": "problem-agitate-solution-solution-provide-relief",
      "evidence": "The deck proposes a solution using human feedback training processes and provides evidence to support it.",
      "position": 2,
      "confidence": 0.9,
      "parentBeatName": "Resolution",
      "parentBeatSlug": "resolution"
    }
  ],
  "loops": [
    {
      "to": 14,
      "from": 8,
      "name": "Jobs To Be Done",
      "slug": "53-jobs-to-be-done",
      "bestFor": "Product innovation, market entry, competitive positioning",
      "matchId": "fdcd1287-c4f6-4816-863c-2281b6ffccea",
      "evidence": "The deck proposes a solution using human feedback training processes and provides evidence to support it.",
      "position": 1,
      "objective": "How can we train an ML system to align with human preferences and values?",
      "structure": "The Customer's Job -> Current Solutions (Hired/Fired) -> Unmet Needs -> Our Solution Fit",
      "confidence": 0.7,
      "description": "Reframe the problem around what the customer is trying to accomplish, not what they're buying"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}