I hope we can reach a point where there's enough research on the negative effects of social media (or more specifically which features of it e.g. scrolling videos) that we can inform people from a young age.
I would guess the training data (conversational as opposed to coding specific solutions) is weighted towards people finding errors in others work, more than people discussing errors in their own. If you knew there was an error in your thinking, you probably wouldn't think that way.
I've built something along these lines. It utilises OCR to extract text content, indexes it for RAG, uses a separate service to identify/match concepts to reference data in an RDF knowledge graph, and displays the original source documents with the references to KG concepts overlayed.