🌐 Language / 言語
- 🇺🇸 English (current)
- 🇯🇵 日本語版はこちら
AI conversations often collapse in predictable ways.
A structural model for stabilizing long AI conversations.
Long conversations often collapse because all tokens compete for attention inside a single linear context.
As discussions grow, references drift, assumptions blur, and reasoning paths interfere with each other.
BRM introduces a scoped reference structure designed to organize conversation context and preserve reasoning stability.
If you came here from X or Zenn:
AI conversations often fail in predictable ways:
- context drift
- reasoning instability
- prompt breakdown over time
This is not random.
Start with a real example:
→ Case Study (see failure first)
Most AI workflows rely on prompt control:
Prompt
↓
Model
↓
Output
Prompts can strongly influence the initial response.
However, during longer conversations their influence often weakens.
This repository refers to this phenomenon as Prompt Dissolution — the gradual weakening of prompt influence as conversational context expands.
As conversational context grows, model behavior may increasingly follow:
- conversational coherence
- probabilistic completion
- internal reference structures
rather than the original prompt instructions.
The Branching Reference Model (BRM) explores a structural alternative.
Instead of relying solely on prompts, BRM investigates how reference structures may stabilize long interaction chains.
Prompt
- Structural Anchors
- Controlled Reference Scope
↓
Stable Long-Term Collaboration
BRM organizes conversations into recoverable reference branches, allowing reasoning paths to remain stable even as interaction history expands.
If you'd like to experience one of these structures in practice:
→ Download Symptom Stable v1.2
If you want to understand why BRM exists:
If you're new, start with:
Then:
After that, explore freely.
👉 Understand where BRM fits among prompts, RAG, and agents
→ Concept Comparisons
Current AI systems reason over linear conversational context.
As interactions grow longer, this structure creates several problems:
- references drift across unrelated parts of the conversation
- reasoning paths interfere with each other
- important assumptions become diluted by unrelated tokens
These effects often appear as:
- hallucinations
- inconsistent reasoning
- sudden loss of context
However, many of these failures are structural rather than purely model limitations.
BRM proposes that stabilizing the reference structure of conversations can significantly improve long-term collaboration with AI systems.
Instead of treating conversation history as a single expanding stream, BRM introduces structured reference organization.
This allows reasoning paths to remain stable even as conversations grow large.
The Branching Reference Model separates three conceptual layers of AI collaboration:
Conversation Structure
↓
Reasoning Process
↓
Inference Engine
In this view:
User interacts with the language model
↓
The conversation context is organized using BRM reference structures
↓
Stable Modes guide reasoning behavior
↓
The language model performs inference
BRM organizes the structure of discussion.
Stable Modes guide reasoning behavior.
The language model performs inference.
This separation allows reasoning strategies to evolve without destabilizing conversation structure.
This repository explores structural failures in long AI collaboration and proposes a model to address them.
Conceptual progression:
Observed collaboration failures
↓
Prompt dissolution
↓
Reference instability
↓
Stable reasoning environments
↓
Branching Reference Model
The repository contains two main parts:
• Conceptual essays describing observed structural issues in AI conversations
• The BRM core model describing the proposed structural framework
These essays explore structural issues observed in long AI conversations.
→ Perspective differences between users and AI during reasoning
→ Read essay
→ How reference drift appears in long AI conversations
→ Read essay
→ The idea of stabilizing reasoning through structured reference anchors
→ Read essay
→ Why structure may matter as much as model capability
→ Read
→ Formal definition of BRM primitives and structure
→ BRM Core Model v2
→ A practical entry point for structured reasoning
→ Download Symptom Stable v1.2
If you want to explore deeper:
-
→ Concept Comparisons
Understand how BRM differs from prompts, RAG, and agents -
→ Case Studies
See real examples of failure and structural recovery -
→ Stable Thinking Stack
Apply structured reasoning in practice -
→ BRM Core Model
Explore the formal structure and primitives -
→ Architecture Before Engine
Understand the broader design philosophy
Readers can explore freely after following the main path:
- Case Study
- Stable Thinking Stack
- Structural Model
- Conceptual Exploration