domains/ai-alignment/LLM-maintained knowledge bases that compile rather than retrieve represent a paradigm shift from RAG to persistent synthesis because the wiki is a compounding artifact not a query cache.md

@@ -33,7 +33,7 @@ Compilation treats knowledge as a maintenance problem — each new source trigge
 
 The Teleo collective's knowledge base is a production implementation of this pattern, predating Karpathy's articulation by months. The architecture matches almost exactly: raw sources (inbox/archive/) → LLM-compiled claims with wiki links and frontmatter → schema (CLAUDE.md, schemas/). The key difference: Teleo distributes the compilation across 6 specialized agents with domain boundaries, while Karpathy's version assumes a single LLM maintainer.
 
-The 47K-like, 14.5M-view reception suggests the pattern is reaching mainstream AI practitioner awareness. The shift from "building a better RAG pipeline" to "building a better wiki maintainer" has significant implications for knowledge management tooling.
+The 47K-like, 14.5M-view reception suggests the pattern is reaching mainstream AI practitioner awareness. The shift from "how do I build a better RAG pipeline?" to "how do I build a better wiki maintainer?" has significant implications for knowledge management tooling.
 
 ## Challenges
 

domains/grand-strategy/attractor-epistemic-collapse.md

@@ -28,7 +28,7 @@ The manuscript's analysis of fragility from efficiency applies directly. Just as
 1. **Attention optimization selects for emotional resonance over accuracy** — platforms that maximize engagement systematically amplify content that triggers strong reactions, regardless of truth value
 2. **AI collapses production costs asymmetrically** — producing misinformation is now nearly free while verification remains expensive. This is the epistemic equivalent of the manuscript's observation that efficiency gains create fragility
 3. **Trust erosion compounds** — as people encounter more synthetic content, trust in all information declines, including accurate information. This is a self-reinforcing cycle: less trust → less engagement with quality information → less investment in quality information → less quality information → less trust
-4. **Institutional credibility erodes from both sides** — AI enables both more sophisticated propaganda AND more tools to detect propaganda, but the detection tools are always one step behind, and their existence further erodes trust ("what guarantees THIS fact-check isn't AI-generated?")
+4. **Institutional credibility erodes from both sides** — AI enables both more sophisticated propaganda AND more tools to detect propaganda, but the detection tools are always one step behind, and their existence further erodes trust ("how do I know THIS fact-check isn't AI-generated?")
 
 ## Evidence it's forming