Wednesday 18 December, 2024
Harry Potter? Yawn…
King’s Cross station in London is the terminus for the fast trains from Cambridge, so I pass through it quite a lot. In a brilliant marketing move years ago someone had the idea of capitalising on the fact that ‘Platform 9¾’ was the platform from which the Hogwarts express departed its way northwards to the famous academy. Accordingly, every day that I pass through the station I see the huge queues of Potter fans waiting to have their photos taken under the platform sign before entering the merchandising shop.
This photograph, taken one morning last May, is one of my favourites. I noticed that one of the kids in the queue was fed up waiting in line (and was obviously tired, perhaps from travelling). As I watched, he yawned. Snap! One of those Cartier-Bresson moments.
Quote of the Day
“The two most beautiful words in the English language are: ‘Cheque enclosed.’”
Dorothy Parker
I wonder how many people nowadays know what a ‘cheque’ was/is.
Musical alternative to the morning’s radio news
UB40 | Swing Low Sweet Chariot
Long Read of the Day
The AI Calculation Debate
A new paper by Cass Sunstein.
Cass Sunstein is one of those annoying scholars who produces a book or two every year as well as numerous academic papers. What’s annoying is that most of them are pretty good. So when I came across this paper — which he finished writing less than a week ago — I settled down to read.
It all started, it seems, with a conversation he (CRS) had with ChatGPT.
CRS: 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!
CRS: 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.
CRS: 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…
Sunstein uses this exchange as a jumping-off point for a long and interesting disquisition on why attempts to predict careers, romances and political revolutions are impossible. I enjoyed his journey through these puzzles, but then perhaps it’s the kind of thing that only academics like, so feel free to ignore the link!
On a lighter note. There’s a nice story Sunstein once told against himself. He’s married to Samantha Power, who was the US Representative to the United Nations during Obama’s presidency. When the UN was in session, she and Cass had a suite in some posh New York hotel, and he noticed that the staff always addressed him as “Mr Power”. One morning, when he was going out by himself he asked the concierge to get him a taxi.
The conversation then went like this:
Concierge: “Under what name, Sir?”
Cass: “Sunstein”.
Concierge looks at him quizzically.
Cass: “What’s puzzling you?”
Concierge: “Nothing, Sir. It’s just that you look awful like Mr Power.”
Linkblog
Something I noticed, while drinking from the Internet firehose.
You can buy a car on Amazon now. Well, only in the US, and it has to be a Hyundai. Oh, and even Prime subscribers can’t get it delivered. They have to collect it from a dealership. Weird. Link