{
  "lesson": "10-ai-control-subversion",
  "title": "AI Control - Safety Despite Subversion",
  "questions": [
    {
      "stage": "pre",
      "question": "Which best captures the difference between alignment and AI control?",
      "options": [
        "They are synonyms",
        "Control is about hardware; alignment is about software",
        "Alignment asks whether U is trustworthy; control asks whether we can safely use U without trusting it",
        "Control replaces the loss function while alignment changes the optimizer"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What does the AI Control threat model assume?",
      "options": [
        "U is untrusted strong, T is trusted weak, H is bounded trusted human labor",
        "Only U exists",
        "U and T are both adversarial",
        "All three resources (U, T, H) are trusted"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What is the key risk in Untrusted Monitoring that Trusted Editing avoids?",
      "options": [
        "T cannot edit text",
        "Hardware contention",
        "Two instances of U can collude or share priors, so the protocol must spend budget on collusion-resistance",
        "Humans cannot be audited"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "On the Greenblatt et al. (ICML 2024) code-backdoor task, what does Trusted Editing achieve relative to Untrusted Monitoring?",
      "options": [
        "It only wins at zero human budget",
        "They are exactly equivalent",
        "It is strictly worse",
        "It strictly Pareto-dominates: higher usefulness at every safety level"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which of the following is NOT one of the lesson's three fundamental limits of control?",
      "options": [
        "Control produces aligned models as a byproduct",
        "Trusted weak models eventually lag U",
        "Control may fail at higher capability levels if U can manipulate T or reason about H's audit distribution",
        "Humans do not scale"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "What does a Control Safety Case argue?",
      "options": [
        "That U is trustworthy",
        "That T is more capable than U",
        "That under worst-case assumptions about U, the deployment protocol bounds the probability of an unacceptable outcome",
        "That the model passed a manual jailbreak test"
      ],
      "correct": 2,
      "explanation": ""
    }
  ]
}