BROADCASTS.com

It\u2019s every blogger\u2019s curse to return to the same arguments again and again. Matt Yglesias has to keep writing \u201cmaybe we should do popular things instead of unpopular ones\u201d, Freddie de Boer has to keep writing \u201cthe way culture depicts mental illness is bad\u201d, and for whatever reason, I keep getting in fights about whether you can have probabilities for non-repeating, hard-to-model events. For example:

• What is the probability that Joe Biden will win the 2024 election?

• What is the probability that people will land on Mars before 2050?

• What is the probability that AI will destroy humanity this century?

The argument against: usually we use probability to represent an outcome from some well-behaved distribution. For example, if there are 400 white balls and 600 black balls in an urn, the probability of pulling out a white ball is 40%. If you pulled out 100 balls, close to 40 of them would be white. You can literally pull out the balls and do the experiment.

In contrast, saying \u201cthere\u2019s a 45% probability people will land on Mars before 2050\u201d seems to come out of nowhere. How do you know? If you were to say \u201cthe probability humans will land on Mars is exactly 45.11782%\u201d, you would sound like a loon. But how is saying that it\u2019s 45% any better? With balls in an urn, the probability might very well be 45.11782%, and you can prove it. But with humanity landing on Mars, aren\u2019t you just making this number up?

Since people on social media have been talking about this again, let\u2019s go over it one more depressing, fruitless time.

https://www.astralcodexten.com/p/in-continued-defense-of-non-frequentist