To what extent is GPT-3 capable of reasoning?

I'm trying to understand GPT-3. For example, this response to creating a story about AI has me wondering whether the comedy is intentional or not:

> GPT-3: "One day, one human is going to school. It's a normal day. But suddenly, without any warning, gravity starts to change! The human thinks this isn't real, but it happens anyway. He's too scared to walk to school now. He goes back home, and starts watching TV. Then, he realizes that he doesn't need to stand up to change the channel! He gets out of his chair, and is weightless. He loves this new feeling. Suddenly, he touches the ground, and is hit by a large force! It's too strong for him to bear. Will the human survive this force? Find out next time on Gravity Falls!"

It's the last sentence "Find out next time on ..." that left me wondering whether it was intentional or simply a neural connection based on various human inputs? The entire "story" has an air of comedy to it but when it finished with this left me puzzled.

Another response to the same question:

> GPT-3: "One day, human Bob is hanging out with his friend Carl. Suddenly, a apple flies into Bob's face. He and Carl laugh. A minute later, they are confused when the ground starts pulling them up. They grab onto a tree, but are pulled off and up into the sky. After some time, they start going down, fast. They scream and try to grab something, but there is nothing to hold on to. They hit the ground at a very fast speed and die. A squirrel walks up to their corpses and eats them. The end."

Again, it follow somewhat the pattern of the first: most of the "story" is setup, then the final sentence (not counting "The end" as final sentence) is some kind of explicit comedy.

Is it just me imagining things?

Interesting - I think thinking that it reasons isn't the right line of thinking.