Let’s look at a few things that appear random, but have subtle underlying behaviors that turns magic into math.
Computer Generated Random Numbers
True vs. pseudo-random numbers There are two principal methods used to generate random numbers. The first method measures some physical phenomenon that is expected to be random and then compensates for possible biases in the measurement process. Example sources include measuring atmospheric noise, thermal noise, and other external electromagnetic and quantum phenomena. For example, cosmic background radiation or radioactive decay as measured over short timescales represent sources of natural entropy (as a measure of unpredictability or surprise of the number generation process).
The second method uses computational algorithms that can produce long sequences of apparently random results, which are in fact completely determined by a shorter initial value, known as a seed value or key. As a result, the entire seemingly random sequence can be reproduced if the seed value is known. This type of random number generator is often called a pseudorandom number generator.
[When I worked at The Big House, the pseudorandom number generator was critical in our simulation of CPU designs. We’d run millions of simulations of random instruction sequences. When one failed, we’d use the seed from the initial simulation to recreate the test on a (hopefully) patched design.]
A typical day at The Big House.
Images
Let’s put our AI colleagues through their paces. We asked Gemini and Elder G to create totally random image prompts, ignoring any information they’d collected about us.
Good morning! It’s great to hear from you. Exploring the concept of “random” sounds like a wonderful way to start the day.
I’m happy to participate in this experiment. To generate this image, I’ve used a technique to create an unexpected scene without relying on any prior knowledge of your preferences or specific history. I simply let random variables combine to form a unique composition.
Gemini
Sora
Hot Pot
Elder G
Perchance
Perchance has a button that creates random prompts. The following are Perchance images based on the following prompts
paranormal dessert shop frequented by odd patrons
italian woman, bedroom mirror selfie, smudged shirt, brush in hand, creative look
indian man, study selfie, headphones, amused
sacred forest populated by cursed trees
[this prompt produced so many interesting images, we decided to include several] woman, in a tattoo parlor, getting inked, excited, close-up
Coin Toss
A coin toss looks random, but in strict physics it is not. A tossed coin obeys the very ordinary rules of classical mechanics: gravity, angular momentum, air resistance, and the exact way the coin leaves the hand.
If you knew all the starting conditions perfectly, Newton’s laws could predict the outcome.
In other words: A coin toss is deterministic, not inherently random. Humans simply lack the precision to measure and control all the variables.
Elder G:
Researchers Diaconis, Holmes, and Montgomery analyzed coin tossing and found that a typical toss has a slight bias toward the starting face, about 51% probability. The coin tends to land the way it began because of how it is caught.
So even normal coin flips are not perfectly 50/50.
Stage Magicians Go Further
Magicians can push this farther with techniques like:
Thumb toss with controlled rotation
Catch-and-flip methods (secretly turning the coin during the catch)
Two-headed coins (the oldest trick in the book)
But even without trick coins, skilled performers can achieve very high success rates with controlled flips.
Here’s an interesting video where the secret of the predetermine coin flip is revealed. It is surprisingly simple, and after several hours of practice, we achieved a 50% success rate.
Card Shuffle!
The number of possible combinations of a deck of cards is 52! (52 factorial). Big, big number!