Chain of Thought on AIBussin — AI applications, systems and books

Appendix 05: References: Foundational Research

Fri, 28 Aug 2026 10:00:00 +0100

    flowchart TD
    subgraph Research_Papers
        R1[Wei et al., 2022<br>Chain of Thought Prompting]
        R2[Gao et al., 2023<br>GRA Framework]
        R3[Zelikman et al., 2022<br>STaR]
        R4[Wu et al., 2024<br>xVerify]
    end

    subgraph Book_Chapters
        C4[Chapter 4: Beyond Prompting]
        C5[Chapter 5: Ghosted by the Machine]
        C9[Chapter 9: Council of Purpose]
        C10[Chapter 10: Second Pass]
        C13[Chapter 13: Machine Coding]
        C14[Chapter 14: MIRROR & Reflection]
        C15[Chapter 15: When It Doesn't Work]
        CApp[Appendix: Prompting Tools]
    end

    R1 --> C4
    R1 --> C5
    R1 --> C14

    R2 --> C9
    R2 --> C14
    R2 --> C15

    R3 --> C4
    R3 --> C5
    R3 --> C13

    R4 --> C10
    R4 --> C14
    R4 --> CApp

    style R1 fill:#e1f5fe,stroke:#333
    style R2 fill:#fff3e0,stroke:#333
    style R3 fill:#e8f5e9,stroke:#333
    style R4 fill:#fce4ec,stroke:#333
    style C4 fill:#f3e5f5,stroke:#333
    style C5 fill:#fff9c4,stroke:#333
    style C9 fill:#e0f7fa,stroke:#333
    style C10 fill:#c8e6c9,stroke:#333
    style C13 fill:#ffccbc,stroke:#333
    style C14 fill:#d1c4e9,stroke:#333
    style C15 fill:#b2dfdb,stroke:#333
    style CApp fill:#ffcdd2,stroke:#333

Wei et al., 2022. “Chain of Thought Prompting Elicits Reasoning in Large Language Models”
Relevance: Forms the backbone of your structured prompting techniques like MARS, GROWS, and CRITIC. CoT prompts are foundational for steering AI toward better reasoning.
Used in: Chapters 4 (Beyond Prompting), Chapter 5 (Ghosted by the Machine), Chapter 14 (Session Reflection)
https://arxiv.org/abs/2201.11903

Appendix 10: Prompting Techniques for Fiction Writing

Fri, 28 Aug 2026 10:00:00 +0100

🧰 Prompting Patterns That Matter

These prompting techniques help you offload more effectively, maintain creative control, and co-create something you’re proud of:

    flowchart TD
    Start([✍️ Write with AI]) --> A{What do you need?}

    A --> B[🧠 Structure & Logic]
    A --> C[🎭 Voice & Dialogue]
    A --> D[🔍 Review & Polish]
    A --> E[📢 Marketing & Publishing]

    B --> B1[Chain of Thought<br>Break tasks into steps]
    B --> B2[Structure-Based Prompts<br>Hero's Journey, Save the Cat]
    B --> B3[Socratic Q&A<br>Let AI question you]

    C --> C1[Role-Playing Prompts<br>Act as expert or character]
    C --> C2[Simulated Dialogue<br>Characters talk freely]
    C --> C3[In-Style Drafting<br>Continue in your voice]

    D --> D1[Iterative Refinement<br>Regenerate, tweak, improve]
    D --> D2[Context-Rich Prompts<br>Feed backstory & details]
    D --> D3[Continuity Checks<br>Track plot, characters, timeline]

    E --> E1[Blurb + Marketing Copy<br>Hooks, titles, social posts]

    style Start fill:#e1f5fe,stroke:#333
    style A fill:#fff3e0,stroke:#333
    style B fill:#e8f5e9,stroke:#333
    style C fill:#fce4ec,stroke:#333
    style D fill:#f3e5f5,stroke:#333
    style E fill:#fff9c4,stroke:#333

Chain of Thought Prompting: Break big tasks into small, logical steps. Ask the AI to list emotional beats, then write dialogue for each, then combine it. It keeps scenes focused and rich.
Role-Playing Prompts: Make the AI act as an expert (editor, coach, bestselling author). This tunes its output to match tone or perspective. Great for scene writing, critiques, or guidance.
Socratic Q&A Prompting: Ask the AI to question you about plot, character, and conflict. You’ll uncover deeper story logic by answering.
Structure-Based Prompts: Reference the “Hero’s Journey,” “Save the Cat,” or “Romancing the Beat.” The AI will match the story shape, helping with pacing and reader expectations.
Iterative Refinement: AI doesn’t always get it right first try. Ask it to regenerate, tweak for more emotion, remove clichés, or add a surprise twist.
Simulated Dialogue: Use AI as your characters in chat-like scenarios. Capture raw, authentic dialogue and emotional beats.
In-Style Drafting: Provide a paragraph you wrote and ask AI to continue in that tone. Helps preserve your voice.
Context-Rich Prompts: Always give character backstory or prior scene details. The more specific your prompt, the better the output.
Continuity Checks: Ask AI to list all characters, places, or events in a draft. Use it to catch plot holes or inconsistencies.
Blurb + Marketing Copy: After the draft, use AI to generate book blurbs, social media pitches, or title options.

🧰 Additional Prompting Patterns from Research

These prompting techniques extend what we’ve already covered — giving you even more tools to write, reflect, and refine your novel with AI. Think of these as “mid-process” accelerators that can be used anywhere across your workflow.

Advanced Agents From First Principles 01: Does Your AI Agent Fail on Complex Reasoning Tasks? Treat Chain of Thought as Computation, Not Proof

Sat, 08 Aug 2026 22:35:00 +0100

Most developers first encounter chain of thought as a prompting trick:

Think step by step.

That framing is too shallow for agent engineering.

For an advanced agent, the useful idea is not that the model should produce a long explanation. The useful idea is that a difficult task may benefit from intermediate computational state before the system commits to an action or answer.

That is a very different claim.

A reasoning trace can help a system decompose a problem, preserve intermediate conclusions, identify missing information, decide what to verify next, and expose places where search or tools should be used.

🎂 CAKE: Cognitive Amplification Knowledge Engine

Mon, 27 Apr 2026 21:17:19 +0100

We’re not teaching machines to think. We’re teaching ourselves to build thinking systems.

🎨 From AI Assistants to Controlled Cognitive Amplification

Most people use AI to write faster.
But the real opportunity isn’t speed.

It’s amplification.

A useful analogy is physical labor. A person can move earth with their hands, but only at a limited scale. A bulldozer does not replace the human it allows them to operate at a completely different level of throughput.

✨ TINY CRITICS: Lightweight Reasoning Checks for Large AI Systems

Sat, 29 Nov 2025 00:06:42 +0000

🥹 0. TL;DR

Large language models write fluent explanations even when they’re wrong. Verifying their reasoning usually requires another LLM slow, expensive, and circular.

We needed something different:

A miniature reasoning critic <50 KB trained on synthetic reasoning mistakes, able to instantly detect broken reasoning in much larger models.

The Tiny Critic:

trains on GSM8K-style reasoning traces generated by DeepSeek or Mistral
uses FrontierLens, and Visual Policy Maps (VPMs) to convert reasoning into canonical numerical features
is just a logistic regression with ~30 parameters
runs in microseconds
plugs into any agent
dramatically improves InitAgent, R1-Loops, and research-planning stability

This post tells the full story how we built it, why it works, and what we learned about the shape of reasoning.