• The "Memory" Misconception: The author argues that calling AI's ability to access personal notes (like in Obsidian) "memory" is a fundamental misunderstanding of how the technology works.
• Database vs. Markdown: Many tutorials suggest that a collection of Markdown files can act as a "second brain" or memory for AI, but the author contends that Markdown files lack the structure and queryability of a true database.
• The Retrieval Problem: AI doesn't "remember" your notes; it performs a retrieval process (often RAG—Retrieval-Augmented Generation). If your data is messy or unorganized, the AI's "memory" will be equally fragmented and unreliable.
• Context Window Constraints: Users often confuse a large context window with true memory. Loading thousands of notes into a prompt is inefficient and often leads to the AI losing track of specific details (the "lost in the middle" phenomenon).
• Call for Better Infrastructure: The author advocates for moving away from simple folder-based storage toward more robust data structures (like Supabase or structured databases) if users want AI to actually "know" and utilize their personal information effectively.
• The Obsidian Delusion: Specifically targets the trend of using Obsidian as an AI backend without acknowledging the technical limitations of flat-file retrieval for complex reasoning tasks.

I am donating a ticket to the PKM Summit in Utrecht, Netherlands on 20 and 21 March for a student at a Dutch institution for higher ed. On the off-chance that some one is following hypothes.is for my or the PKM tag's feed, mentioning it here too. Ping me before 20-2 if you want to apply.