I said my example was contrived because I didn’t test the prompt (admittedly I should have tried to).
I still think there’s a lack of explainability to the whole model though, and I struggle to understand how we could continue improving these models without understanding how they fundamentally make their decisions.
That being said, after reading some more output from GPT-3, it is more coherent than I remembered.
Seems to have nailed it.
Here's the result:
--- Bob went to the store to get apples for his restaurant. He needed to cook food for an important dish. Bob came back home, and cut the apples using a
knife. He needed to cut the apple into pieces, so he could use them to make some tasty food.
Bob cut the apple, and put it inside a pot. He filled the pot with water, and put it on the stove. The stove was hot and started to cook the apple. ---