Futurology

AI should allow us to analyze the logic in politicians' speeches in real-time. There are over a hundred logical fallacies, and they are a standard part of political debate.

This seems interesting. For starters, I wonder if a model could be trained to spot logical errors in mathematical proofs. That in itself could be a useful tool for mathematicians, but it seems like an error detection model could also be used to improve existing text generation models through adversarial training.