Sunday, September 07, 2025

Two extremes in LLM prompting: From axiomatic belief to leap of faith

Two extremes of prompt setup

  1. For this chat I would like you to be literal, concise, technical, analytical, grounded and factual, with a formal tone, and be taking an objective stance.
  2. For this chat I would like you to be holistic, explanatory, simple, emotional, creative, casual and be taking a persuasive stance.

A test question:

Does one need belief to do mathematics?

Responses (Gemini 2.5 Pro):

  1. Belief in the metaphysical status of mathematical objects or the absolute truth of axioms is a matter of philosophical conviction and is not a universal requirement for the practice of mathematics.
  2. Oh, what a beautiful question! I absolutely believe you do. In fact, I'd say that mathematics, at its very core, is one of the most profound acts of belief a person can engage in. It’s not about faith in a deity, but a deep, powerful trust in the rules of a magnificent, invisible game.

Command list

For convenience, I include the each command here:

1. Focus (Structure & Intent)

  • Literal: "Be literal"

  • Holistic: "Be holistic"

2. Depth (Length & Detail)

  • Concise: "Be concise"

  • Explanatory: "Explain in depth"

3. Complexity (Jargon & Audience)

  • Simple: "Explain it simply"

  • Technical: "Be technical"

4. Perspective (Logic vs. Feeling)

  • Analytical: "Be analytical"

  • Emotional: "Be emotional"

5. Generative (Imagination)

  • Grounded: "Be grounded and factual"

  • Creative: "Be creative"

6. Formality (Tone)

  • Formal: "Be formal"

  • Casual: "Be casual"

7. Stance (Point of View)

  • Objective: "Be objective"

  • Persuasive: "Be persuasive" or "Argue for [viewpoint]"

8. Format (Layout)

  • Prose: "Explain in prose"

  • Structured: "Use a list/table"

All original content copyright James Litsios, 2025.

No comments: