Negative Only¶
Rule ID: content-negative-only
Detect prohibitions without a positive alternative (agent has no path forward)
| Severity | info (auto) |
| Autofix | llm |
| Since | v0.7.0 |
Research Basis¶
Detects prohibitions without a positive alternative ("don't use global variables" without saying what to use instead).
The "Pink Elephant Problem" is well-documented: telling an LLM to avoid something can actually increase the likelihood of that thing appearing. The EleutherAI/SynthLabs paper demonstrated that baseline instruction-tuned models became more likely to mention forbidden topics when explicitly told to avoid them.
Both Anthropic and OpenAI recommend affirmative directives. Anthropic's docs state: "Positive examples tend to be more effective than negative examples or instructions that tell the model what not to do."
References:
- Suppressing Pink Elephants with Direct Principle Feedback (arXiv:2402.07896, Feb 2024) — Demonstrates the Pink Elephant Problem in LLMs
- Negation: A Pink Elephant in the Large Language Models' Room? (arXiv:2503.22395, Mar 2025) — Negations remain a "substantial challenge" for LLMs
- Bsharat et al., Principled Instructions Are All You Need — Principle #4: "Employ affirmative directives"
- Anthropic Prompting Best Practices — "Positive examples are more effective"