2.6 — Bonus rule — Be positive (say what to do, not what to avoid)

🟢 In plain words — saying what to do is more precise than saying what not to do. “Don’t do X” leaves a thousand possibilities; “do Y” leaves only one.

Beginner mistake: telling the AI what it must not do (“don’t use complicated words,” “don’t write long sentences”). A positive instruction is more clear and more reliable.

• ❌ “Don’t use lists.” → ✅ “Write only in flowing paragraphs.”
• ❌ “Don’t be too technical.” → ✅ “Explain it to a beginner, with everyday examples.”

📝 Honest nuance: recent models handle negation better than before. But positive phrasing remains more precise and keeps you in control. Keep the habit.

✅ In short

• Phrase things positively: say what to do, not what to avoid.
• A positive instruction leaves less room for interpretation.
• Recent models handle negation better, but the positive reflex stays more reliable.