{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "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": 182,
  "pageCount": 213,
  "prevPage": 181,
  "nextPage": 183,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "balanced",
  "nDataPoints": 0,
  "notes": "Part of the State of AI 2024 report.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "paragraph"
  ],
  "metadataConfidence": 0.9,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/182",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-182",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "New capabilities bring new vulnerabilities. Incumbents and specialist labs have upped research into jailbreaking, designing potential fixes and creating the first red-teaming benchmarks.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d20-58f8145e63c1",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.6,
        "w": 0.96,
        "x": 0.02,
        "y": 0.3
      },
      "kind": "list",
      "text": "OpenAI proposed a fix to the “ignore all previous instructions” attack via ‘instruction hierarchy’. Anthropic’s work on multishot jailbreaking points to the potential of ‘Cautionary Warning Defense’. Gray Swan AI have piloted the use of ‘circuit breakers’. Haize Labs worked with Hugging Face to create the first ever red teaming resistance benchmark. There are philosophical debates about whether jailbreaking benchmarking datasets and evals will be fruitful.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "bb35916c-bf85-41ff-87ad-64096a994bd0",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.08,
        "w": 0.96,
        "x": 0.02,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "New capabilities bring new vulnerabilities. Incumbents and specialist labs have upped research into jailbreaking, designing potential fixes and creating the first red-teaming benchmarks.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c6c37d00-9f31-4638-8413-a3ecdca11f8a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.75,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "As the attack surface widens, developers up research into jailbreaking...",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "dc272499-84c7-4922-a550-83a92c99eb95",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-1055-74e0-a95a-928cd1ef27ea",
      "evidence": "Title 'As the attack surface widens, developers up research into jailbreaking...'",
      "confidence": 88
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 204,
      "from": 154,
      "beatId": "019dd95a-0682-776c-8e35-605159a069e6",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Implications (So What)",
      "beatSlug": "triple-take-the-implications-so-what",
      "evidence": "Politics + Safety sections explore consequences and risks",
      "position": 2,
      "confidence": 78,
      "parentBeatName": "Reflection",
      "parentBeatSlug": "reflection"
    },
    {
      "to": 204,
      "from": 175,
      "beatId": "019dd95a-0682-776c-8e35-74f05e198faf",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "The Return",
      "beatSlug": "voyage-return-the-return",
      "evidence": "Safety section returns to risks/governance debate",
      "position": 4,
      "confidence": 55,
      "parentBeatName": "Resolution",
      "parentBeatSlug": "resolution"
    }
  ],
  "loops": [
    {
      "to": 186,
      "from": 182,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3e-76aa50b143e8",
      "evidence": "Attack surface, Pliny red team, LLM-on-LLM patching, adversarial robustness, stealth attacks",
      "position": 22,
      "objective": "Show jailbreaking arms race across attack surfaces",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 75,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}