The Prisoner’s Dilemma and the Coase Theorem are two widely-cited ideas in economics and law. As it happens, one of my papers is titled “Does the Prisoner’s Dilemma Refute the Coase Theorem?,” which I co-wrote with my colleague and friend Orlando I. Martinez-Garcia back in 2014. We therefore fed the same question in the title of our paper into ChatGPT and got back this super-formal and uncreative response (see below) telling us that these two concepts are not directly related:

The Prisoner’s Dilemma and the Coase Theorem are two different concepts in economics. The Prisoner’s Dilemma is a game theory scenario in which two individuals must decide whether to cooperate or defect, with the outcome depending on the decisions of both players. The Coase Theorem, on the other hand, states that if property rights are well-defined and transaction costs are low, the allocation of resources in a market will be efficient regardless of the initial distribution of property rights. The two concepts are not directly related, and the Prisoner’s Dilemma does not refute the Coase Theorem. However, the presence of externalities, public goods, and the absence of well-defined property rights, the Coase Theorem doesn’t hold.

Unhappy with this answer, we then posed the following question to ChatGPT: “Could the prisoners in the Prisoner’s Dilemma avoid defecting if they could bargain with each other?” (i.e. if the prisoners could engage in Coasian bargaining) and got back a different answer:

If the prisoners in the prisoner’s dilemma are able to communicate and negotiate with each other, it is possible that they may be able to come to an agreement to not defect and cooperate with each other instead. However, this outcome would depend on the specific details of the situation, such as the level of trust between the prisoners and their willingness to cooperate. In some cases, the prisoners may still defect even if they can communicate, if they feel that the benefits of defecting outweigh the benefits of cooperating.

Note the last line of ChatGPT’s response: “In some cases, the prisoners may still defect even if they can communicate, if they feel that the benefits of defecting outweigh the benefits of cooperating.” By comparison, our 2014 paper concludes that “even when the prisoners are allowed to communicate and bargain with each other, there is some positive probability that they might not strike a Coasean bargain” and more specifically that “the probability of defection is a function of various factors, including such things as uncertainty, exponential discounting, and elasticity.”

In my next post, we will see how ChatGPT responds to an esoteric question about jury voting that I posed in the title of another paper of mine: “Why don’t juries try range voting?“