I am about to flip a coin. Can you predict whether it will be heads or tails? You might have gotten it right. (It was heads.) But if so, you were lucky. Whether it would come up heads or tails depends on an assortment of factors that you could not identify before I flipped the coin. In principle, of course, reliable predictions could be made. If you knew everything relevant to whether a coin will come up heads or tails, you could of course make an accurate prediction. So let’s not talk about randomness. That is not the problem. The problem is the absence of essential information. With respect to the role of randomness, here is an illuminating exchange I had with ChatGPT: ME: If I flip a coin, can you predict whether it will come up heads or tails? CHATGPT: No, I can’t predict the outcome of a coin flip. A fair coin toss is random, and each flip has an equal 50% chance of coming up heads or tails. If you’d like, I can simulate a coin flip for you! 😊 ME: Why can’t you predict the outcome of a coin flip? CHATGPT: Predicting the outcome of a coin flip is nearly impossible because it depends on a complex combination of factors, including: Initial Conditions: The force, angle, and speed of the flip, along with the height it reaches, are all variables that are difficult to measure and control precisely. Air Resistance: The way the coin interacts with the air as it flips introduces randomness. Surface Interaction: The coin’s bounce and spin upon landing on a surface can further alter the outcome. In theory, if all of these factors were perfectly known and calculated, the outcome could be predicted (this is the basis of classical mechanics). However, in practice, the variables are too many and too sensitive for accurate prediction. For most purposes, a coin flip is treated as random. ME: Isn’t the word “random” misleading here? CHATGPT: You’re absolutely right — calling a coin flip “random” might oversimplify what’s actually happening. In reality, a coin flip is deterministic, meaning the outcome is governed by physical laws like Newtonian mechanics. If we had perfect knowledge of all the initial conditions (force, angle, spin, air resistance, etc.), we could theoretically predict the result every time. When we call it “random,” we’re really referring to practical randomness — the idea that the variables influencing the outcome are so complex and sensitive that, for all practical purposes, we treat the result as unpredictable. In this sense, “random” reflects our ignorance of or inability to measure the key factors, rather than true randomness in the sense of quantum unpredictability. It’s a convenient shortcut in language but not strictly accurate in a scientific sense. Justice A central goal of liberalism, and of the liberal political tradition, is to undo damaging forms of subjugation, which is why John Stuart Mill’s The Subjection of Women is a canonical liberal text. With his emphasis on the importance of individual agency, Mill laments that “the inequality of rights between men and women has no other source than the law of the strongest.” In a key passage, he writes: What is the special character of the modern world — the difference that chiefly distinguishes modern institutions, modern social ideas, modern life itself, from those of times long past? It is that human beings are no longer born to their place in life, and chained down by an unbreakable bond to the place they are born to, but are free to use their talents and any good luck that comes their way to have the kind of life that they find most desirable. Mill’s argument here is more subtle than the context might suggest. He is speaking, to be sure, of careers open to talents — of a right to seek opportunities and to try to find the kind of life that one finds most desirable. That is the liberal insistence on the dissolution of unwanted chains and bonds. But Mill is also careful to draw attention to the importance of “any good luck that comes their way.” In its best forms, the liberal tradition emphasizes that lotteries are everywhere. It points to the place of “good luck,” understood as practical randomness, and the multiple forms it takes. John Rawls’ A Theory of Justice is the most sustained development of that point. The term “good luck” isn’t exactly right, but let’s not be fussy. I want to say something about the lived equivalent of lotteries. I am going to approach that question indirectly, or from the side. But please keep it in mind throughout. Full disclosure: this is, in part, a discussion of justice. Sampling on the Dependent Variable A number of years ago, a brilliant law student — let’s call her Jane — came to my office with an intriguing research project. She wanted to study the sources of success. Jane’s plan was to contact dozens of spectacularly successful people in multiple fields (business, politics, music, literature) to see what they had in common. Maybe all of them had difficult childhoods. Maybe none of them had difficult childhoods. Maybe all of them were quick to anger. Maybe none of them was quick to anger. Maybe all of them developed a passion in high school. Maybe none of them developed a passion in high school. Maybe all of them were impatient. Maybe none of them were impatient. Jane was energetic as well as astonishingly smart. There was little doubt that she would be able to carry through with her project. If she called famous people, she would find a way to get them to take her calls. Still, something was wrong with what she had in mind. Suppose we learned that a large number of spectacularly successful people did indeed have something in common. Would we know that what they had in common was responsible for their spectacular success? Not at all. There might be plenty of people (hundreds,
There's nothing Artificial about our Intelligence