[la64710]

To the second question chatGPT answered : The orange is in the kitchen, as that is where the plate, along with the orange, was moved.

Now a human can reason because a human can visualize in their mind that a plate is being moved without moving the orange. How is that kind of reasoning possible in LLMs which in my very basic understanding is predicting the next token.

[tagraves]

Here's the response chatGPT 4 gave for me:

> The orange remains in the living room. Moving the plate to the kitchen does not affect the location of the orange, since it was placed below the plate but not attached to it. Therefore, the orange stays where it was originally placed, which is in the living room.

You don't need to visualize it in your mind to understand the relationship between being _below_ and being _moved with_. Keep in mind that many people cannot visualize anything in their mind!

[la64710]

I have wondered how do people blind from birth create their mental world? Is it all dark with no color or light and only sound? No shapes? Or do they still form mental images from non visual sensory inputs?

[luma]

Make sure you're including the GPT version, there's a wide gulf between GPT4 and prior models. GPT-4 answers:

Q. If you place an orange below a plate in the living room, and then move the plate to the kitchen, where is the orange now?

A. The orange remains in the living room. Moving the plate to the kitchen does not affect the position of the orange.

----

Q. There are 31 books in my house. I read 2 books over the weekend. How many books are still in my house?

A. There are still 31 books in your house. Reading books does not change their quantity

----

Q. Julia has three brothers, each of them has two sisters. How many sisters does Julia have?

A. Julia has one sister. Each of her three brothers has two sisters, and Julia is one of them. The other one is her sister, making it a total of one sister for Julia.

[lern_too_spel]

In order to predict next tokens in text with greater and greater accuracy, some parameters of the language model must represent a model of the world.