Skip to content

R0053/2026-03-31-02/C002/H1

Research R0053 — Prompt Claims
Run 2026-03-31-02
Claim C002
Hypothesis H1

Statement

The claim is accurate — negative constraints ("must not") are necessary for AI compliance and positive instructions alone are insufficient.

Status

Current: Eliminated

Supporting Evidence

Evidence Summary
SRC02-E01 Instruction hierarchies do fail, suggesting enforcement is needed

Contradicting Evidence

Evidence Summary
SRC01-E01 Negative instructions produce worse output
SRC01-E02 Anthropic recommends positive over negative framing

Reasoning

The evidence directly contradicts the claim's specific mechanism. While enforcement is needed (partial support), the claim's assertion that you "must tell the AI what it is not allowed to do" is shown to be counterproductive in many cases.

Relationship to Other Hypotheses

H1 and H2 agree that enforcement is needed but disagree on mechanism. H1 and H3 are fully contradictory.