{
  "docId": "019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "docSlug": "cc8183ec02431b7a",
  "documentTitle": "2022 Air Street Capital The State of AI Report 2022",
  "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": 22,
  "pageCount": 114,
  "prevPage": 21,
  "nextPage": 23,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 4,
  "notes": "The slide highlights the competitive landscape of LLMs applied to software engineering tasks.",
  "elementsJson": [
    "headline_text",
    "action_title",
    "bullet_list",
    "process_diagram"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc/22",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc#slide-22",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "OpenAI's Codex, which drives GitHub Copilot, has impressed the computer science community with its ability to complete code on multiple lines or directly from natural language instructions.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a214-a87c5f825458",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.65,
        "w": 0.22,
        "x": 0.75,
        "y": 0.25
      },
      "kind": "diagram",
      "text": "Data flow diagram showing GitHub/CodeContests input, Pre-training/Fine-tuning, and Sampling/Evaluation process.",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "97cc50df-86ba-4a9b-ac24-290eb7af2445",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.7,
        "w": 0.7,
        "x": 0.03,
        "y": 0.22
      },
      "kind": "list",
      "text": "OpenAI's Codex, which drives GitHub Copilot, has impressed the computer science community with its ability to complete code on multiple lines or directly from natural language instructions. This success spurred more research in this space, including from Salesforce, Google and DeepMind.\nWith the conversational CodeGen, Salesforce researchers leverage the language understanding of LLMs to specify coding requirements in multiturn language interactions. It is the only open source model to be competitive with Codex.\nA more impressive feat was achieved by Google's LLM PaLM, which achieves a similar performance to Codex, but with 50x less code in its training data (PaLM was trained on a larger non-code dataset). When fine-tuned on Python code, PaLM outperformed (82% vs. 71.7% SOTA) peers on Deepfix, a code repair task.\nDeepMind's AlphaCode tackles a different problem: the generation of whole programs on competitive programming tasks. It ranked in the top half on Codeforces, a coding competitions platform. It was pre-trained on GitHub data and fine-tuned on Codeforces problems and solutions. Millions of possible solutions are then sampled, filtered, and clustered to obtain 10 final candidate submissions.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9e46ebb8-202d-49bd-be16-12609eea5824",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.5,
        "x": 0.03,
        "y": 0.14
      },
      "kind": "title",
      "text": "Corporate AI labs rush into AI for code research",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "3859312b-35e1-4c17-aa19-9a6b0fe39be0",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-1055-74e0-a955-c836650b9ab2",
      "evidence": "Title 'Corporate AI labs rush into AI for code research' states the trend.",
      "confidence": 80
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 80,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-2557e3799e96",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions, exec summary, Research and Industry sections inventory the state of AI.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 93,
      "from": 11,
      "beatId": "019dd95a-0682-776c-8e35-35abf646aa8b",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Industry, Politics sections accumulate signals.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 29,
      "from": 22,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-a20c665fe3de",
      "evidence": "Codex, Transformer alternatives, Minerva, BIG-Bench, Chinchilla, emergence, tool-use, compute eras stack as evidence.",
      "position": 3,
      "objective": "Survey LLM research frontier — transformers, scaling, emergence, compute eras",
      "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
}