Circuit Breakers / Inference Interventions

{
  "id": "circuit-breakers",
  "numericId": null,
  "path": "/knowledge-base/responses/circuit-breakers/",
  "filePath": "knowledge-base/responses/circuit-breakers.mdx",
  "title": "Circuit Breakers / Inference Interventions",
  "quality": 64,
  "readerImportance": 42.5,
  "researchImportance": 38,
  "tacticalValue": null,
  "contentFormat": "article",
  "tractability": null,
  "neglectedness": null,
  "uncertainty": null,
  "causalLevel": null,
  "lastUpdated": "2026-03-13",
  "dateCreated": "2026-02-15",
  "llmSummary": "Circuit breakers are runtime safety interventions that detect and halt harmful AI outputs during inference. Gray Swan's representation rerouting achieves 87-90% rejection rates with 1% capability loss, while Anthropic's Constitutional Classifiers block 95.6% of jailbreaks with 0.38% over-refusal increase. However, the UK AISI challenge found all 22 tested models eventually broken (62K/1.8M attempts succeeded), and novel token-forcing attacks achieve 25% success rates, highlighting fundamental limitations of reactive defenses.",
  "description": "Circuit breakers are runtime safety interventions that detect and halt harmful AI outputs during inference. Gray Swan's representation rerouting achieves 87-90% rejection rates with only 1% capability loss, while Anthropic's Constitutional Classifiers block 95.6% of jailbreaks. However, the UK AISI challenge found all 22 tested models could eventually be broken, highlighting the need for defense-in-depth approaches.",
  "ratings": {
    "novelty": 4.5,
    "rigor": 7,
    "actionability": 6.5,
    "completeness": 7.5
  },
  "category": "responses",
  "subcategory": "alignment-interpretability",
  "clusters": [
    "ai-safety"
  ],
  "metrics": {
    "wordCount": 3224,
    "tableCount": 21,
    "diagramCount": 5,
    "internalLinks": 5,
    "externalLinks": 37,
    "footnoteCount": 0,
    "bulletRatio": 0.09,
    "sectionCount": 39,
    "hasOverview": true,
    "structuralScore": 15
  },
  "suggestedQuality": 100,
  "updateFrequency": 21,
  "evergreen": true,
  "wordCount": 3224,
  "unconvertedLinks": [
    {
      "text": "Anthropic Constitutional Classifiers",
      "url": "https://www.anthropic.com/research/constitutional-classifiers",
      "resourceId": "ce3ac91af6150e19",
      "resourceTitle": "Constitutional Classifiers: Defending against universal jailbreaks (https://anthropic.com/research/constitutional-cla..."
    },
    {
      "text": "Constitutional Classifiers",
      "url": "https://www.anthropic.com/research/constitutional-classifiers",
      "resourceId": "ce3ac91af6150e19",
      "resourceTitle": "Constitutional Classifiers: Defending against universal jailbreaks (https://anthropic.com/research/constitutional-cla..."
    },
    {
      "text": "Anthropic Constitutional Classifiers",
      "url": "https://www.anthropic.com/research/constitutional-classifiers",
      "resourceId": "ce3ac91af6150e19",
      "resourceTitle": "Constitutional Classifiers: Defending against universal jailbreaks (https://anthropic.com/research/constitutional-cla..."
    },
    {
      "text": "Anthropic Constitutional Classifiers",
      "url": "https://www.anthropic.com/research/constitutional-classifiers",
      "resourceId": "ce3ac91af6150e19",
      "resourceTitle": "Constitutional Classifiers: Defending against universal jailbreaks (https://anthropic.com/research/constitutional-cla..."
    },
    {
      "text": "Anthropic Research",
      "url": "https://www.anthropic.com/research/constitutional-classifiers",
      "resourceId": "ce3ac91af6150e19",
      "resourceTitle": "Constitutional Classifiers: Defending against universal jailbreaks (https://anthropic.com/research/constitutional-cla..."
    },
    {
      "text": "Constitutional Classifiers",
      "url": "https://www.anthropic.com/research/constitutional-classifiers",
      "resourceId": "ce3ac91af6150e19",
      "resourceTitle": "Constitutional Classifiers: Defending against universal jailbreaks (https://anthropic.com/research/constitutional-cla..."
    },
    {
      "text": "CAIS Research",
      "url": "https://safe.ai/",
      "resourceId": "a306e0b63bdedbd5",
      "resourceTitle": "CAIS Surveys"
    },
    {
      "text": "JailbreakBench",
      "url": "https://jailbreakbench.github.io/",
      "resourceId": "f302ae7c0bac3d3f",
      "resourceTitle": "JailbreakBench: LLM robustness benchmark"
    }
  ],
  "unconvertedLinkCount": 8,
  "convertedLinkCount": 0,
  "backlinkCount": 1,
  "hallucinationRisk": {
    "level": "low",
    "score": 30,
    "factors": [
      "no-citations",
      "high-rigor",
      "conceptual-content"
    ]
  },
  "entityType": "approach",
  "redundancy": {
    "maxSimilarity": 19,
    "similarPages": [
      {
        "id": "output-filtering",
        "title": "AI Output Filtering",
        "path": "/knowledge-base/responses/output-filtering/",
        "similarity": 19
      },
      {
        "id": "refusal-training",
        "title": "Refusal Training",
        "path": "/knowledge-base/responses/refusal-training/",
        "similarity": 18
      },
      {
        "id": "representation-engineering",
        "title": "Representation Engineering",
        "path": "/knowledge-base/responses/representation-engineering/",
        "similarity": 17
      },
      {
        "id": "intervention-effectiveness-matrix",
        "title": "Intervention Effectiveness Matrix",
        "path": "/knowledge-base/models/intervention-effectiveness-matrix/",
        "similarity": 16
      },
      {
        "id": "sparse-autoencoders",
        "title": "Sparse Autoencoders (SAEs)",
        "path": "/knowledge-base/responses/sparse-autoencoders/",
        "similarity": 16
      }
    ]
  },
  "coverage": {
    "passing": 7,
    "total": 13,
    "targets": {
      "tables": 13,
      "diagrams": 1,
      "internalLinks": 26,
      "externalLinks": 16,
      "footnotes": 10,
      "references": 10
    },
    "actuals": {
      "tables": 21,
      "diagrams": 5,
      "internalLinks": 5,
      "externalLinks": 37,
      "footnotes": 0,
      "references": 3,
      "quotesWithQuotes": 0,
      "quotesTotal": 0,
      "accuracyChecked": 0,
      "accuracyTotal": 0
    },
    "items": {
      "llmSummary": "green",
      "schedule": "green",
      "entity": "green",
      "editHistory": "red",
      "overview": "green",
      "tables": "green",
      "diagrams": "green",
      "internalLinks": "amber",
      "externalLinks": "green",
      "footnotes": "red",
      "references": "amber",
      "quotes": "red",
      "accuracy": "red"
    },
    "ratingsString": "N:4.5 R:7 A:6.5 C:7.5"
  },
  "readerRank": 355,
  "researchRank": 359,
  "recommendedScore": 171.11
}

No external links