Like, you can quickly lookup related ideas based on what came before and after, causes, effects, just like calling relationships a graph database.
Documents can’t be queried efficiently like that, you need a database.
I take the article's point more directly. It's just a straighter line to have clear communication through documentation than to fuddle around with the perfect memory setup.
LLMs are like the main character in Memento, constantly leaving notes to themselves. The document meta is better than just using context, but becomes very repetitive and token inefficient.
I just think a graph DB might be more efficient for keeping track of the relationships between those notes than a tree directory filled with docs.