---
id: "framework-world-model-architectures"
type: "framework"
source_timestamps: ["00:06:35", "00:10:20"]
tags: ["systems-architecture", "taxonomy"]
related: ["concept-semantic-retrieval", "concept-structured-ontology", "concept-signal-fidelity"]
sources: ["s15-block-layoffs"]
sourceVaultSlug: "s15-block-layoffs"
originDay: 15
---
# Three World Model Architectures

## Overview

The phrase '[[concept-world-model]]' currently obscures the fact that companies are building three fundamentally different architectures, each with distinct failure modes regarding how they handle the boundary between factual information and human judgment.

## The Three Architectures

### 1. Semantic Retrieval (Vector DBs) — see [[concept-semantic-retrieval]]

- **What it is**: Uses vector databases to embed and retrieve data based on semantic similarity.
- **Strengths**: Fast to deploy. Excellent for synthesizing status, detecting dependencies, generating reports.
- **Failure mode**: Cannot structurally distinguish between *finding* a document and *judging* its importance — see [[claim-semantic-retrieval-flaw]].

### 2. Structured Ontology (Palantir style) — see [[concept-structured-ontology]]

- **What it is**: Defines explicit objects and relationships before the AI can reason. Embodied by [[entity-palantir-d15]].
- **Strengths**: Highly accurate. Prevents hallucinations by restricting reasoning to the schema.
- **Failure mode**: Completely blind to new, emergent patterns outside its rigid schema — see [[claim-ontology-blindspot]].

### 3. Signal Fidelity (Jack Dorsey style) — see [[concept-signal-fidelity]]

- **What it is**: Builds the model exclusively on the highest-truth data exhaust (e.g., financial transactions). Embodied by [[entity-jack-dorsey]] at [[entity-block]].
- **Strengths**: Highly accurate baseline; pristine input data.
- **Failure mode**: Creates an illusion of authority — users assume causal reasoning is as flawless as the input data, which is rarely true. See [[claim-illusion-of-judgment]].

## How to Choose

No architecture is purely safe. Each has a distinct boundary failure. Selection should be matched to:

- **Scale**: Semantic Retrieval works at small scale where leaders can override ranking.
- **Regulation/precision needs**: Structured Ontology fits regulated, schema-stable domains.
- **Data exhaust quality**: Signal Fidelity fits businesses with naturally pristine telemetry (fintech, payments, sensors).

In practice, see [[framework-world-model-principles]] for the meta-principles that govern all three.

## Related

- [[framework-world-model-principles]]
- [[concept-interpretive-boundary]]
- [[question-ontology-discovery]]


## Related across days
- [[concept-openbrain-architecture]]
- [[concept-hybrid-memory-architecture]]
- [[framework-hybrid-memory-stack]]
- [[framework-intent-gap-layers]]
- [[arc-context-architecture-evolution]]