---
title: "Captured: Claude — Memory Layer Discussion"
url: https://mdfy.app/ycd29v7A
updated: 2026-05-09T21:14:14.503Z
source: "mdfy.app"
---
# Captured: Claude — Memory Layer Discussion

> **You**: I'm thinking about authored memory vs extracted memory.
> Where does extracted memory fail?

> **Claude**: Three places, in order of severity:
>
> 1. **Misextraction** — the model picks up a passing comment as a
>    "preference" and re-inserts it forever. Hard to undo because
>    the user doesn't know it's there.
>
> 2. **Walled gardens** — extracted memory lives in the vendor's
>    DB. Switch vendors → memory doesn't follow. Lock-in by
>    accident.
>
> 3. **Audit trail** — extracted memory has no edit log the user
>    can reason about. Authored memory has commits, diffs, version
>    history.

> **You**: So when does extracted win?

> **Claude**: Casual personal use. "Remember that I'm vegetarian"
> doesn't need a versioning system. Authored memory wins for
> high-stakes, multi-AI, or long-lived knowledge.