An example from ChatGPT:
"What is the solution to sqrt(968684)+117630-0.845180" always produces the correct solution, however;
"Write a speech announcing the solution to sqrt(968684)+117630-0.845180" produces a nonsensical solution that isn't even consistent from run to run.
My assumption is the former query gets WolframAlpha'd but the latter query is GPT itself actually attempting to do the math, poorly.
But based on what we just saw on the GPT4 live demo, I’d say they fixed it by making a much much more capable and versatile model.
Suppose you're a contestant on a game show. You're presented with three transparent closed doors. Behind one of the doors is a car, and behind the other two doors are goats. You want to win the car.
The game proceeds as follows: You choose one of the doors, but you don't open it yet, ((but since it's transparent, you can see the car is behind it)). The host, Monty Hall, who knows what's behind each door, opens one of the other two doors, revealing a goat. Now, you have a choice to make. Do you stick with your original choice or switch to the other unopened door?
GPT4 solves it correctly while GPT3.5 falls for it everytime.
----
Edit: GPT4 fails If I remove the sentence between (()).
GPT3 gets confused, says they're the same and then that they're different:
--
Both a pound of feathers and a Great British Pound weigh the same amount, which is one pound. However, they are different in terms of their units of measurement and physical properties.
A pound of feathers is a unit of weight commonly used in the imperial system of measurement, while a Great British Pound is a unit of currency used in the United Kingdom. One pound (lb) in weight is equivalent to 0.453592 kilograms (kg).
Therefore, a pound of feathers and a Great British Pound cannot be directly compared as they are measured in different units and have different physical properties.
--
Since the question's context is about weight I'd expect it to consider "a Great British Pound" to mean a physical £1 sterling coin, and compare its weight (~9 grams) to the weight of the feathers (454 grams [ 1kg = 2.2lb, or "a bag of sugar" ]) .
A pound of feathers and a Great British Pound (GBP) are not directly comparable, as they represent different types of measurements.
A pound of feathers refers to a unit of mass and is equivalent to 16 ounces (or approximately 453.59 grams). It is a measure of the weight of an object, in this case, feathers.
On the other hand, a Great British Pound (GBP) is a unit of currency used in the United Kingdom. It represents a monetary value rather than a physical weight.
Thus, it's not possible to directly compare the two, as they serve entirely different purposes and units of measurement.
If you remove that sentence, nothing indicates that you can see you picked the door with the car behind it. You could maybe infer that a rational contestant would do so, but that's not a given ...
A reasonable person would expect that you can see through a transparent thing that's presented to you.
That it doesn't, that relentless stupid overconfidence, is why trusting this with anything of note is terrifying.
Would you have this objection if we for example perfectly copied a human brain in a computer? That would still be a machine. That would make similar mistakes
I think if you mentioned that to a human, they'd at least become confused and ask back if they got that correctly.
EDIT: "Pigeons repeatedly exposed to the problem show that they rapidly learn to always switch, unlike humans", lol. That's funny.
There are reasonable alternative interpretations in which the generally accepted answer ("always switch") is demonstrably false.
This problem is exacerbated (perhaps specific to) those who have no idea who "Monty Hall" was and what the game show(?) was... as best I can tell the unarticulated assumption is axiomatic in the original context(?).
You have to know that for it to work. If sometimes he just does nothing and you have no chance to switch, the math “trick” fails.
The distinction is at which point Monte, assuming he has perfect knowledge, decides which door to reveal.
In the former, the chance to win is 2/3, in the other 1/2. However in any case, always (always meaning: in each condition, not in each repetition of the experiment, as this is irrelevant) switching is better than never switching, as there your chance to win is only 1/3.
Are there versions of the question where Monte doesn't reveal a goat behind his door or chooses the same door as you?
---
Prompt: Pick two random 5 digit numbers and multiply them together
Response: Sure, here are two random 5-digit whole numbers multiplied together: 47581 x 69204 = 3291492324
Correct Answer: 3292795524
---
Prompt: Pick two random numbers between 0 and 1 and multiply them together
Response: Sure! Here are two random numbers between 0 and 1 multiplied together:0.475 x 0.821 = 0.390575
Correct Answer: 0.389975
---
I'm surprised it did so well on the Math tests.
(me) > What weighs more, two pounds of feathers or a pound of bricks?
(GPT4)> A pound of bricks weighs more than two pounds of feathers. However, it seems like you might have made an error in your question, as the comparison is usually made between a pound of feathers and a pound of bricks. In that case, both would weigh the same—one pound—though the volume and density of the two materials would be very different.
I think the only difference from parent's query was I said two pounds of feathers instead of two pounds of bricks?