Your AI Does the Hard Work Then Deletes It. Every Session.

The speaker examines Andre Karpathy's recently viral personal wiki idea (which received 41,000 bookmarks) and compares it to their own OpenBrain system. Karpathy's approach addresses a core problem: AI currently rediscovers knowledge from scratch every time you ask a question, doing cognitive work and then throwing it away. His wiki solution has AI actively write and maintain organized notes that preserve connections and synthesis over time, essentially compiling knowledge once rather than re-deriving it on every query.

The fundamental architectural difference lies in timing: Karpathy's wiki is a 'write-time' system where AI does heavy synthesis work when information comes in, creating pre-built understanding you can browse later. OpenBrain is a 'query-time' system that stores information faithfully in structured databases and does the thinking fresh when you ask questions.

Each approach has distinct strengths and weaknesses. The wiki excels for solo researchers doing deep synthesis work on 100-10,000 documents, academic research, and situations where connections between sources matter more than individual facts. However, it breaks at scale, struggles with multi-agent access, can't handle precise structured queries, and risks error compounding when AI synthesis decisions become trusted as truth.

OpenBrain wins for structured operations, multi-agent access, high volume data, and precise queries across thousands of entries. But it can struggle with deep synthesis quality and browsability since it's deliberately headless. The speaker proposes a hybrid solution: keeping OpenBrain as the authoritative structured store while adding a wiki compilation layer on top that generates browsable synthesis on demand from the underlying database, providing the benefits of both approaches without the drawbacks.