About the paper - academics are often not experts of real world use and hence “research it”.

This might explain why prompts written by the public are providing startlingly good results.

GPT definitely seems to reason to some extent, especially where you invite it to reason along with you in an area of intersectional information that does not exist in its training.

If there are some tests average users could try in their reasoning type conversations with gpt I’d be very happy to try them out