{
  "kind": "framework",
  "value": "reinforcement-learning-from-human-feedback",
  "collectionKey": "slides:framework:reinforcement-learning-from-human-feedback:all-document-kinds:all-producers:all-orientations",
  "filters": {
    "documentKinds": [],
    "sourceTypes": [],
    "orientations": []
  },
  "total": 1,
  "page": 1,
  "pageSize": 24,
  "pageCount": 1,
  "rows": [
    {
      "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,
      "slideType": "other",
      "function": "present_framework",
      "notes": "The slide shows a binary choice interface used for training AI models, specifically for reinforcement learning.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "The slide depicts the binary choice mechanism central to RLHF.",
      "slideHref": "/slides/019de06f-84e4-70e4-bce4-3c7c4f09a8ea/10",
      "deckHref": "/decks/019de06f-84e4-70e4-bce4-3c7c4f09a8ea",
      "deckAnchorHref": "/decks/019de06f-84e4-70e4-bce4-3c7c4f09a8ea#slide-10",
      "loopMatches": [
        {
          "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"
        }
      ],
      "arcBeatMatches": [
        {
          "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"
        }
      ],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    }
  ]
}