{
  "apiVersion": "v1",
  "passage": {
    "id": "humanlayer-context-window-guideline-100000-tokens-under-60-hardest-problems-2026",
    "text": "if you're just getting started with AI, try to keep it around 100,000 tokens. For larger million context window, we … this up to … 200,000 tokens, but I've regularly tried to keep it under 60 for the hardest problems. I've regularly gone over 300K for things where I'm just kind of riffing with the agent, and I'm just … too lazy to compact it and move on and do a new one.",
    "context": "Horthy is answering the moderator's question on whether context rot and context engineering are solved now that context windows are larger.",
    "speaker": "Dex Horthy",
    "speakerId": "dex-horthy",
    "speakerUrl": "https://the-ai-record.com/people/dex-horthy",
    "speakerLevel": "executive",
    "role": "CEO, HumanLayer",
    "voice": "person",
    "organization": "HumanLayer",
    "organizationId": "humanlayer",
    "organizationUrl": "https://the-ai-record.com/organizations/humanlayer",
    "aiVendor": true,
    "work": {
      "title": "The Great Loops Debate",
      "type": "talk",
      "date": "2026-07-17",
      "publisher": "AI Engineer (YouTube)",
      "locator": "28:36",
      "url": "https://www.youtube.com/watch?v=c35YoMdnI78"
    },
    "grade": "B",
    "gradeMeaning": "The organization's own post, paper or talk.",
    "verification": {
      "status": "verified",
      "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
      "reviewedOn": "2026-11-04"
    },
    "topics": [
      "developer-productivity",
      "coding-agents"
    ],
    "functions": [
      "engineering"
    ],
    "figures": [
      {
        "metric": "context-guideline-new-users",
        "value": 100000,
        "unit": "tokens",
        "period": "as the speaker states it",
        "definition": "context size the speaker says to stay around when just getting started with AI",
        "level": "n/a"
      },
      {
        "metric": "context-guideline-large-windows",
        "value": 200000,
        "unit": "tokens",
        "period": "as the speaker states it",
        "definition": "context size the speaker says the guideline rises to for million-token context windows",
        "level": "n/a"
      }
    ],
    "url": "https://the-ai-record.com/passages/humanlayer-context-window-guideline-100000-tokens-under-60-hardest-problems-2026",
    "json": "https://the-ai-record.com/api/v1/passages/humanlayer-context-window-guideline-100000-tokens-under-60-hardest-problems-2026.json"
  },
  "notice": [
    "Every passage is reproduced word for word from the cited source.",
    "Check the verification status: \"reported\" means not yet confirmed by an independent second reader.",
    "Organizations flagged aiVendor sell AI tools or services and have a reason to publish flattering numbers.",
    "An empty result means the archive holds nothing on it, not that nobody has said anything."
  ]
}