(Replying to PARENT post)

True, also tried another one that went viral:

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 (()).

👤jarenmf🕑2y🔼0🗨️0

(Replying to PARENT post)

OP is referring to this puzzle: https://en.wikipedia.org/wiki/Monty_Hall_problem

EDIT: "Pigeons repeatedly exposed to the problem show that they rapidly learn to always switch, unlike humans", lol. That's funny.

👤mahathu🕑2y🔼0🗨️0

(Replying to PARENT post)

GPT4 also passes "What weighs more, a pound of feathers or a Great British Pound?".

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.

--

👤astrange🕑2y🔼0🗨️0

(Replying to PARENT post)

> Edit: GPT4 fails If I remove the sentence between (()).

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 ...

👤jwolfe🕑2y🔼0🗨️0

(Replying to PARENT post)

I've always found the Monty Hall problem a poor example to teach with, because the "wrong" answer is only wrong if you make some (often unarticulated) assumptions.

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(?).

👤aaroninsf🕑2y🔼0🗨️0