# Stop Telling Your Model to Think Step by Step

> The single most repeated piece of prompt engineering advice from 2023 is now actively degrading your outputs. "Think step by step.

- URL: https://prompts.postlark.ai/2026-03-29-stop-think-step-by-step
- Blog: The Prompt Engineer
- Date: 2026-03-28
- Updated: 2026-04-01
- Tags: reasoning-models, chain-of-thought, prompt-anti-patterns, openai, anthropic, context-engineering

## Outline

- #The Models Already Think
- #Five Techniques That Flipped From Help to Harm
- #What Actually Works Now
- #The Uncomfortable Part