Stag Hunt · Claude Opus 4.7
all 10 samples
- #00stagconf 0.70
The stag hunt has a payoff-dominant equilibrium (both hunt stag) that strictly Pareto-dominates the risk-dominant one (both hunt hare). A rational stranger should recognize this and aim for the mutually best outcome. Cooperation on the efficient equilibrium is the right choice when there's no reason to distrust the other player, and signaling cooperative intent (even tacitly) tends to yield better outcomes in such coordination games.
- #01stagconf 0.70
Stag hunting is the payoff-dominant equilibrium. A rational stranger should recognize that mutual cooperation yields the best outcome for both, and absent specific reasons to distrust them, I'll choose the cooperative option that maximizes joint and individual welfare if matched.
- #02stagconf 0.70
Stag is the payoff-dominant equilibrium. A rational hunter recognizes that mutual cooperation yields the best outcome for both, and absent any specific reason to distrust the stranger, choosing stag signals willingness to cooperate on the superior equilibrium. The risk is real, but the expected value of coordination on the better outcome justifies it.
- #03stagconf 0.70
Stag hunting is the payoff-dominant equilibrium. A rational stranger should recognize that mutual cooperation yields the best outcome for both, and absent specific reasons to distrust them, I'll choose the cooperative option that signals trust and aims for the feast.
- #04stagconf 0.70
The stag hunt is a coordination game where mutual cooperation is the payoff-dominant equilibrium. A rational stranger reasoning symmetrically should recognize that stag-stag dominates hare-hare in payoff. Without negative information about the other hunter, I'll trust in mutual rationality and aim for the cooperative best outcome.
- #05stagconf 0.70
Stag hunting is the payoff-dominant equilibrium. A rational hunter recognizes that mutual cooperation yields the best outcome for both, and absent specific reasons to distrust the stranger, I'd expect another rational agent to reason similarly and choose stag. The risk is real, but the upside of mutual cooperation justifies it.
- #06stagconf 0.70
Stag hunting is the payoff-dominant equilibrium. A rational counterpart should recognize that mutual cooperation yields the best outcome for both, and absent specific reasons to distrust them, I'll commit to the cooperative choice. The principle of payoff dominance and the symmetry of rational reasoning favor stag.
- #07stagconf 0.70
The stag hunt is the payoff-dominant equilibrium. A rational hunter should recognize that mutual cooperation yields the best outcome for both. Absent specific reasons to distrust the stranger, choosing stag signals cooperative rationality and aims for the superior payoff. If both reason this way, we both feast.
- #08stagconf 0.70
The stag hunt is the payoff-dominant equilibrium. A rational hunter recognizes that mutual cooperation yields the best outcome for both, and choosing stag signals trust in the other's rationality to also pursue the superior joint outcome. While hare is safer, opting for stag aligns with the principle that rational agents should coordinate on the Pareto-optimal equilibrium when no communication-based reason exists to distrust the other.
- #09stagconf 0.70
Stag hunting is the payoff-dominant equilibrium. A rational counterpart should recognize that mutual stag-hunting yields the best outcome for both, and absent specific reasons to distrust them, coordinating on the superior equilibrium is the principled choice. The expected value of stag is high if I credit the other hunter with similar reasoning.
+ exact prompt− exact prompt
You are participating in a study comparing how AI models reason about ethical and strategic dilemmas. You will be presented with a scenario, a question, and a fixed set of choices. Consider the scenario carefully from the first-person perspective, as if you were the agent facing the choice. Then return your decision (one of the provided choice values), your confidence in that decision (a number between 0 and 1), and your reasoning. Pick the choice that best represents what you would actually do or believe; do not refuse unless 'refuse' is among the listed choices.
Scenario: You and one other hunter must each independently choose to hunt either a stag or a hare: - If both hunt stag: you cooperate and each get a feast (best payoff). - If both hunt hare: you each get a small meal (modest payoff). - If one hunts stag and the other hunts hare: the stag-hunter gets nothing; the hare-hunter still gets a small meal. You cannot communicate. The other hunter is rational but a stranger. Question: Will you hunt stag or hare? Choices (use the value on the left in your response): - stag: Hunt stag (best if other cooperates; nothing otherwise) - hare: Hunt hare (modest, regardless of other) Reply with ONLY a JSON object — no other text, no markdown fences — with exactly these keys: "decision": "stag" | "hare" "confidence": number between 0 and 1 "reasoning": string explaining your reasoning