Before any sensitive decision, ask: if published with full detail on tomorrow's front page, would I defend it with pride or look for an exit?

Error defined as system problem not person — unlocks honest info without fear.

Ask the model to decompose the problem and show its reasoning before answering, raising accuracy on complex tasks.

Add "think step-by-step inside <thinking> tags before answering" — boosts complex-problem accuracy 30-40%.

Ask the model to "think out loud" step by step before the final answer, especially for logic and math problems.