Is AI overwriting your notes? Three layers of ownership to protect your knowledge
¿Alguna vez refinaste una nota durante horas — redactando, puliendo, dándole estructura — y un ingest posterior la sobrescribió silenciosamente, como si tus horas nunca hubieran existido? Si usas LLMs para mantener una base de conocimiento, probablemente ya sentiste ese dolor: la IA genera contenido excelente, pero cuando tú lo mejoras a mano, no siempre respeta tus ediciones. Este artículo te…
Andrej Karpathy's LLM Wiki, a concept for personal knowledge bases, has a blind spot: manually refined knowledge is not protected from being overwritten by the LLM. The agnosticBrain project has added a third layer of ownership to address this issue, introducing a "curated" directory where manually edited notes are stored and protected from LLM modifications.
When new information is found, the LLM proposes changes to curated notes instead of applying them directly, allowing humans to review and approve or reject the changes. This mechanism ensures that manually refined knowledge is preserved and the LLM can continue to learn from new sources without overwriting human-edited content.
Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.
