---
id: "concept-ai-wiki"
type: "concept"
source_timestamps: ["00:03:13", "00:04:50", "00:08:27"]
tags: ["knowledge-management", "system-architecture"]
related: ["concept-write-time-synthesis", "concept-error-baking", "concept-tutor-metaphor", "claim-wiki-breaks-at-scale"]
definition: "A knowledge system where an AI proactively synthesizes incoming information into persistent, cross-referenced markdown files, acting as a continuous writer and maintainer of a personal wiki."
sources: ["s11-wiki-vs-open-brain"]
sourceVaultSlug: "s11-wiki-vs-open-brain"
originDay: 11
---
# AI-Maintained Wiki

# AI-Maintained Wiki

> A knowledge system where an AI proactively synthesizes incoming information into persistent, cross-referenced markdown files, acting as a continuous writer and maintainer of a personal wiki.

## Overview

The **AI-Maintained Wiki** is a knowledge management architecture proposed by [[entity-andrej-karpathy-d11]] in which an AI agent acts as the *programmer* of a codebase of markdown files (see [[quote-ai-programmer-wiki]]). Rather than starting from scratch on every query, the AI actively reads new incoming sources, extracts the relevant information, and writes it into a persistent, cross-referenced set of topic pages. It auto-updates summaries, flags contradictions, and builds an evolving narrative of understanding.

Karpathy uses [[entity-obsidian]] as the visible display layer while the AI operates as the backend writer.

## Architectural Posture

The Wiki relies on [[concept-write-time-synthesis]] — the cognitive heavy lifting of connecting ideas happens at the moment data is ingested, not when a user asks a question. The user effectively reads a pre-compiled study guide, captured by [[concept-tutor-metaphor]].

## Strengths

- Highly readable, narrative-first knowledge artifact.
- Excellent for solo deep research (see [[claim-wiki-better-solo-research]]).
- Cheap and fast retrieval — answers are pre-baked.
- Cross-referencing emerges as a navigable graph.

## Weaknesses

- Susceptible to [[concept-error-baking]]: editorial mistakes get permanently locked into the file system.
- Acts like a *dashboard* — hides the raw facts behind AI editorial decisions (see [[contrarian-dashboards-hide-truth]]).
- Breaks at scale due to [[concept-race-conditions-ai]] and [[concept-wiki-staleness]] (see [[claim-wiki-breaks-at-scale]]).
- Smooths over [[concept-silent-contradictions]] rather than surfacing them.

## When to Use

Use a Wiki for solo, deep-research workflows where one user is reading ~10 academic papers over a couple of weeks and wants an evolving study guide. For team or multi-agent environments, prefer [[concept-openbrain-architecture]] or a [[concept-hybrid-memory-architecture]] (see [[action-choose-architecture-by-scale]]).

## Operational Loop

The day-to-day loop is captured in [[framework-ai-wiki-workflow]].


## Related across days
- [[concept-world-model]]
- [[concept-openbrain-architecture]]
- [[concept-unified-context-infrastructure]]
- [[arc-context-architecture-evolution]]