I asked the new AI engine ChatGPT: “Hey, where did you get your priors?” And she (it?) replied:
“I was trained by OpenAI on a dataset of billions of words taken from the Internet. As a language model, my training involves predicting the next word in a sequence of words, given the words that come before it. I do not have personal experiences or biases, and I do not have access to external information beyond what I was trained on. I exist to assist users by generating human-like text based on the input that I receive. Is there anything else I can help with?“
What? The ChatGPT bot says it has no priors? It is either misinformed or a liar!
Six years ago today (3 January 2017, see here), I posted to this blog a link to a paper of mine titled “Probabilistic Interpretation, Part II: The Case of the Speluncean Explorers” in which I conjecture how a machine judge would address Lon Fuller’s fictional cave case. Yesterday, I entered the following prompt into a new AI engine called ChatGPT: “solve the case of the speluncean explorers”. Here is the AI’s reply to my legal-philosophical query:
“The case of the Speluncean Explorers is a famous problem in legal and moral philosophy. It is a fictional case that was first presented in a 1949 article by legal scholar Lon Fuller. In the case, a group of five cave explorers become trapped in a cave, and, as they run out of food and supplies, they decide to draw lots to determine which of them will be killed and eaten in order to sustain the others. The person who is chosen is killed and eaten, and the remaining four are eventually rescued. After they are rescued, they are put on trial for murder.
“There are many different ways that one could approach this case, and there is no one ‘correct’ answer. Some people might argue that the explorers had no choice but to do what they did in order to survive, and that they should therefore be acquitted of any wrongdoing. Others might argue that the explorers made a conscious decision to take the life of one of their own, and that this is murder regardless of the circumstances.
“Ultimately, the case of the Speluncean Explorers raises important questions about the limits of the law, the nature of moral responsibility, and the role of compassion in decision-making. It is a thought-provoking case that continues to be discussed and debated by legal scholars and philosophers to this day.”
That is the title of our most recent work in progress; one of the research projects we were working on while we were on sabbatical. (Part 1 of the paper will be published in the University of LaVerne Law Review this spring and is available here.) Part 2 presents Lon Fuller’s “Case of the Speluncean Explorers,” one of the most famous thought experiments in legal studies. In our paper (part 2), we imagine an alternative system of voting by appellate judges, a bayesian or cardinal voting system in which judges assign a score to their preferred judicial outcome. Appellate courts generally use an ordinal system of voting (i.e. one judge, one vote) to decide cases. By contrast, we propose a simple cardinal voting system for deciding appellate cases, using Fuller’s hypothetical case to illustrate how our simple system of cardinal voting would work in practice.
I fell in love with Mexico during my first extended stay in Cuernavaca in 1989; below is the melancholic ballad “Sólo Quédate en Silencio”, one of my all-time faves from the now-defunct Mex-pop group RBD:
Happy New Year, my peeps! On this day (1 January) in 1804, Haiti became the first black-majority republic and the second country in North America (after the United States) to gain her independence.
Was yesterday’s (30 December 2022) blitz game between chess grandmasters Magnus Carlsen and Richard Rapport one of the most exciting ever? Via Chess.com: “Carlsen very nearly lost his first game of the tournament against [Rapport] in round 14 in one of the wildest encounters of the [2022 World Blitz Championship]. The game was full of twists and turns and the evaluation bar swung like a pendulum as the players navigated the imbalanced middlegame. Three promotions at different stages of the game meant that five queens graced the board during the 71-move duel …” In case you missed it, you can watch David Howell’s commentary of this epic chess battle below, starting at the 1’02” mark:
Or you can watch Antonio Radić’s expert analysis of the Magnus-Rapport game here:
In addition to my regular teaching duties, here is a summary of my scholarly production this past year:
In January, the Saint Louis University Law Journal published Teaching Tiger King, a pedagogical paper I co-authored with my teaching assistants. (This paper describes how we totally redesigned our business law survey course from scratch during the first few weeks of the pandemic.)
In February, I discovered a 1939 edition of Horace Walpole’s 1765-1766 Paris travel journal, which contains over 20 references to Adam Smith or to Smith’s pupil at the time, the future Duke of Buccleuch, and I then began researching and writing a lengthy paper describing the places and people Smith saw during his first few weeks in Paris in early 1766. (This work consumed the months of March, April, and May.)
In May, my work Breaking Bad Promises was published in Better Call Saul and Philosophy (available here), edited by Joshua Heter and Brett Copenger.
In June and July, I presented my work on Adam Smith in Paris in 1766 (see here) at two academic conferences: the History of Economics Society (HES), where I finally met my fellow Ronald Coase scholar Steven Medema, and the International Adam Smith Society (IASS), where I met another of my intellectual idols, Tyler Cowen.
In August, my work Adam Smith in Love was republished in a new collection of essays on Hume, Smith, Burke, Geijer, Menger, and d’Argenson (available here), edited by Dan Klein. I also made substantial revisions to my Adam Smith in Paris manuscript.
In September, the Journal of Law & Public Policy published my work The Leibniz Conspiracy, which does four things. First off, I show how Kurt Gödel, the greatest logician since Aristotle, himself fell for a far-fetched conspiracy theory. Next, I present a number of plausible “conspiracy theory theories” to explain why such ideas are so popular. Last, I survey the growing calls for social media censorship and then propose an alternative approach: a conspiracy theory betting market.
In October, I presented my work on Coase’s Parables at Mercer University, a paper rated “highly recommended” by legal scholar Larry Solum (see here).
In November, I re-presented my conspiracy theory betting market idea at the annual Loyola Constitutional Law Colloquium, and I also chaired a panel devoted to Adam Smith at the Southern Economic Association.
In December, to recharge my intellectual batteries, I attended a performance by Burna Boy in Orlando (my wife and I love afrobeats); flew to Los Angeles to visit my parents, attend Derek Thompson’s “Progress Summit” in person, and catch a Laker game at the Crypto arena; and then ended the year by flying back to Florida and visiting the Hemingway Home in Key West.
The highlight of my family vacation in Key West, by far, was visiting the former home of Ernest Hemingway and his second wife Pauline Pfeiffer on 907 Whitehead Street; below are just a few pictures from our recent visit:
Birthday blessings to my beautiful wife Sydjia! The picture on the left was taken on a chilly Thanksgiving weekend day in Florida in 2010, shortly after we started dating. The one on the right was taken earlier this year on a warm summer’s day in Jamaica after 10 years of marriage.
Update (12/31): To supplement the original music video (posted above) of the catchy K-pop ballad “We Go” by the South Korean girl group fromis_9, the video below presents a color-coded guide showing which girl is singing which part of the song in real time.
prior probability 