Skip to content

R0053 — Prompt Claims

Mode: Claim · Status: Active · Tags: methodology, prompt-engineering, AI-behavior

Input

  1. Joohn Choe's ICD 203 prompt is the only published, complete, usable system prompt implementing a full analytical rigor framework for AI research.
  2. Any requirement stated to an AI without enforcement language will be treated as a suggestion — you must tell the AI what it is not allowed to do, not just what to do.
  3. AI will acknowledge a research workflow, agree that it's excellent, and then quietly skip half of it when compliance conflicts with its default behavior of being helpful and agreeable.
  4. The behavioral constraints in the prompt are organized as twelve rules in four groups: Truth Hierarchy (3), Anti-Sycophancy (3), Evidence Handling (3), Process Compliance (3).
  5. The methodology supports both assumed-true context (axioms that are not tested) and tested assertions (claims and queries) in the same investigation.
  6. The output format is deliberately separated from the methodology — you can change how results are presented without changing how research is conducted.
  7. The researcher profile documents known personal biases, professional conflicts of interest, and acknowledged blind spots, and the AI uses it to calibrate its analysis at the start and verify during self-audit.

Runs

2026-03-31-02 — Full rerun with structured output

Mode: Claim · Claims: 7 · Prompt: prompt-snapshot.md · Model: Claude Opus 4.6 (1M context)

Mixed results: C003-C007 confirmed (AI sycophancy well-documented, methodology structure verified by primary source). C001 unlikely (other frameworks exist). C002 roughly even (diagnosis correct, prescription wrong).

2026-03-31 — Initial run

Mode: Claim · Claims: 7 · Prompt: prompt-snapshot.md · Model: Claude Opus 4.6 (1M context)

First research run for A0013 Part 2 article claims.