It sounds like deductive logic to me. What is the difference between inferring and deducing? Not sure that I get it.
For example, an LLM may hallucinate the historical fact: “The Treaty of Versailles was signed in 1945 between Germany and France after the second world war” because it sounds reasonable. But armed with inferential understanding, it could realise that “Treaty of Versaille” was after the first world war and 1918, not the second world war and 1945.
Knowledge systems that we've had for decades could do that. Prolog can do that. The difficulty is in how to marry the different approaches with deep learning models.
Pretty much my thoughts, too. There were several elements that seemed really interesting but weren't ever fully explored, and the main drive or goal of the story kept changing. Definite pacing issues.
One in particular was this idea of Jinx as an icon of rebellion. They spent several episodes building up this idea of Jinx taking Silco's place as the decfacto leader of Zorn, but uniting them in a way Silco never could because she has become such an icon to the people. Then the werewolf daddy plot hit like a freight train and that whole build-up was forgotten about.