{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20261011-9e4b62c5",
  "url": "/knowledge/benchmark-human-plus-ai-against-the-stronger-solo-mode",
  "id": "MHC-D-RESEARCH-9187",
  "version": "0.2.0",
  "title": "Benchmark human plus AI against the stronger solo mode",
  "summary": "Beating the human baseline is not the same as beating the best available workflow.",
  "kind": "template",
  "body": "A large meta-analysis found that human-AI combinations improved on humans alone on average yet still underperformed whichever solo baseline—human or AI—was stronger. For representative tasks, compare three modes when feasible: human alone, AI alone and human plus AI. Use the same acceptance criteria and include review cost. Keep the combined workflow only when the combination earns its extra coordination.",
  "limits": [
    "Do not remove required human accountability, legal review or safety controls merely because AI-alone scores well. Performance metrics must include the consequences of important error types, not just average accuracy."
  ],
  "topics": [
    "union-human-ai-collaboration-benchmarks"
  ],
  "intents": [],
  "evidence": [
    {
      "claim": "A preregistered meta-analysis of 106 experiments found that human-AI combinations outperformed humans alone on average but performed worse than the better of the human-alone and AI-alone baselines.",
      "role": "supports",
      "note": "The review covered studies published through June 2023 and reported high heterogeneity, so the pooled estimate does not establish that a particular current workflow will underperform the stronger solo mode.",
      "locator": "Abstract and Overall levels of human-AI synergy",
      "source_id": "RS-5B5B75E3D08A8096E81B"
    }
  ],
  "use_when": [
    "An AI-assisted workflow beats the old human process and the improvement is being treated as proof that the collaboration itself is best."
  ],
  "avoid_when": [
    "Do not remove required human accountability, legal review or safety controls merely because AI-alone scores well. Performance metrics must include the consequences of important error types, not just average accuracy."
  ],
  "example": "If AI can classify a routine request accurately on its own, adding a human approval step may make the process slower without improving the outcome. If the human catches costly edge cases, the combined mode may still earn its place.",
  "check": "The AI-assisted workflow has been compared with both relevant solo alternatives, not only with the old human process.",
  "template": "Task: [task]. Human alone: [human metrics]. AI alone: [AI metrics]. Human + AI: [combined metrics]. Strongest baseline: [mode]. Combination adds: [benefit]. Combination costs: [review or coordination]. Decision: [keep, delegate or redesign].",
  "source_ids": [
    "RS-5B5B75E3D08A8096E81B"
  ],
  "published_at": "2026-10-01T14:27:00Z",
  "editorial_overlay": null,
  "editorial": null,
  "notices": [],
  "sources": [
    {
      "id": "RS-5B5B75E3D08A8096E81B",
      "title": "When combinations of humans and AI are useful: A systematic review and meta-analysis",
      "url": "https://doi.org/10.1038/s41562-024-02024-1"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-9187",
      "to": "MHC-D-RESEARCH-0370",
      "type": "useful_with",
      "url": "/knowledge/map-the-task-to-the-current-ai-frontier"
    },
    {
      "from": "MHC-D-RESEARCH-9187",
      "to": "MHC-D-RESEARCH-0372",
      "type": "useful_with",
      "url": "/knowledge/keep-a-human-baseline-for-important-ai-tasks"
    }
  ],
  "collections": [
    {
      "id": "RC-5D6E88D3E78C09BE1FBC",
      "title": "Prove the human-AI combination, not just the AI assist",
      "url": "/collections/prove-the-human-ai-combination-not-just-the-ai-assist"
    }
  ],
  "topic_hubs": [],
  "solution_packs": []
}