[Mike_12345]

Here's a prompt: "If there is a bob outside, and a bib inside, and the bib cannot see the bob, can the bob see the bib?"

Answer:

"If the bib cannot see the bob due to being inside, it is likely that the bob, which is outside, also cannot see the bib. The reason for the bib not being able to see the bob is presumably due to some kind of barrier, such as a wall or a window, which would likely obstruct the view for both the bib and the bob."

Prompt:

"What type of reasoning did you just apply to solve that task?"

Answer:

"In solving the task, I applied abductive reasoning. Abductive reasoning involves inferring the most likely explanation for a set of observations or statements. In this case, I inferred that a barrier (e.g., a wall or window) is the most likely explanation for why the bib cannot see the bob, and thus, the bob likely cannot see the bib either."

ChatGPT solves the problem by a mechanical reasoning process, not a "party trick". It's a machine, not a person at a party. Surely you don't believe that it has seen that exact sequence of questions and replies in its training set and is simply regurgitating. You can argue about whether its actually using "abductive reasoning" or not, but that is besides the point that it involves some mechanical reasoning process over an interpretation of the prompt. It's not a simple regurgitation.

AlphaZero learned to play Go starting with nothing but the rules of the game. What is it regurgitating there?