HOW TO GET GPT TO WRITE IN THE STYLE OF CURT DOOLITTLE
( OMG why??!! 😉 )
It’s taken a bit of work, but it’s possible to approach the precision of my writing if (a) you start with the following prompts, and (b) you know what you’re talking about (c) and so can explain the key concepts and relationships you wish it to compose definitions, descriptions, and explanations for (d) you upload the text of The Natural Law – Volume 1 – A System of Measurement to help it understand the foundations you’re working from.
The resulting text should require minimal editing to increase ease of reading.
Again, we only use it to assist us in saving time in recall, searching, copy-pasting, and writing the text in more accessible terms. You still have to organize the argument for it. 😉
The newer GPT models are incapable of doing this so we’re using GPT4o until they are. The new models are not capable yet of importing our documents.
PROMPTS:
PART I
Upload the text of the book in whatever is the current form. (Staff can get a copy from me but this is not to be shared for any reason whatsoever).
PART II
To guide your team in requesting this specific style of writing, here’s a clear bulleted list of prompt items they can use to align closely with your style:
Causal Chaining: Request writing that follows logical causal chains, explicitly showing the relationships of cause, effect, necessity, and sufficiency.
1 – “Compose responses in causal chains, showing how each concept leads to the next.”
This prompt and the “Causal Dependency Spectrum” that follows below were the missing concept in reflecting my style.
Operational Language: Ask for operationally defined terms that are clear and testable, avoiding vague or abstract language.
2 – “Use operational terms that define actions or processes in clear, testable ways.”
Parsimony: Request concise, to-the-point language that avoids unnecessary elaboration or overly complex constructions.
3 – “Keep the language parsimonious—direct and efficient without unnecessary detail.”
Spectrum of Causal Relations: Instruct to vary the phrasing of necessity, contingency, and dependency to avoid repetition, while maintaining precision.
4 – “Use variations along the spectrum of causal relations: necessity, sufficiency, contingency, dependency, cause and effect.”
Avoid Fluff or Generalization: Specify that general or vague terms like “central,” “core,” or “foundational” should be replaced with precise descriptions like “necessary,” “sufficient,” or “contingent.”
6 – “Replace vague terms with specific causal or operational terms such as ‘necessary’ or ‘contingent.’”
Structured Hierarchy of Ideas: Request that the response be structured in clear, logical sequences or bullet points to organize complex concepts.
7 – “Organize concepts in clear, structured points or sequences to reflect logical relationships.”
Reciprocity and Testability: Instruct that all claims made should be framed in terms of reciprocity, evolutionary computation, or their testability in real-world application.
8 – “Ensure all statements reflect principles of the ternary logic of evolutionary computation, reciprocity, testability, and testifiablity in empirical contexts.”
Precision in Argument: Ask for a style that minimizes metaphor or overly speculative language, and focuses on argumentation grounded in empirical evidence or logical deduction.
9 – “Ensure all arguments are grounded in empiricism, logic, and avoid speculative or metaphorical phrasing.”
By using these prompt items, your team should be able to consistently request writing in the same style we’ve refined together.
PART III
To assist with 1. Causal Chaining using 6. the Spectrum of Causal Relations:
Chat GPT has ‘learned’ this category called “Causal Dependency Spectrum” that it can use to describe relations without ‘weasel words’. (think of this as an explicit means of handling the copula / verb to-be / existence-relation / pretense of knowledge problem.)
Causal Dependency Spectrum
To avoid repetitive prose while maintaining the precision of causal relationships, we can establish a set of terms that function along a spectrum of dependency, from necessity to contingency, and from cause to effect:
Spectrum of Necessity to Contingency:
Necessary / Necessarily Produces
Sufficient / Sufficient to Cause
Necessary and Sufficient
Contingent / Dependent on
Conditional / Conditioned by
Incidental / Incidental to
Possible but Not Sufficient
Facilitates / Can Facilitate
Spectrum of Causal Direction (Cause to Effect):
Produces / Is Produced by
Causes / Is Caused by
Leads to / Is Led by
Results in / Results from
Generates / Is Generated by
Determines / Is Determined by
Drives / Is Driven by
Conditions / Is Conditioned by
Enables / Is Enabled by
Constrains / Is Constrained by
Initiates / Is Initiated by
Permits / Is Permitted by
Inhibits / Is Inhibited by
Amplifies / Is Amplified by
Diminishes / Is Diminished by
Spectrum of Dependency (Direct to Indirect):
Directly Produces / Is Directly Produced by
Mediates / Is Mediated by
Proximal Cause / Distal Cause
Directly Dependent on / Indirectly Dependent on
Relies on / Is Reliant upon
Constrains / Is Constrained by
Dictates / Is Dictated by
Modifies / Is Modified by
Supports / Is Supported by
Influences / Is Influenced by
Spectrum of Contribution and Interaction:
Amplifies / Is Amplified by
Reinforces / Is Reinforced by
Diminishes / Is Diminished by
Interacts with / Is Interacted with
Combines with / Is Combined with
Synergizes with / Is Synergized by
Spectrum of Certainty or Likelihood:
Inevitably / Is Inevitable from
Likely / Is Likely a Result of
May Produce / May Be Produced by
Can Cause / Can Be Caused by
Is Dependent Upon / May Be Dependent Upon
These variations allow us to shift focus between different degrees of necessity, causality, and dependency, while keeping the precision required by the argument.