Some Basic LLM Etiquette
The article discusses basic etiquette for interacting with large language models (LLMs), suggesting that users should be polite, clear, and respectful in their prompts. It argues that treating AI assistants courteously can improve output quality and foster more productive human-AI interactions.
Background
- LLM stands for Large Language Model — AI systems like ChatGPT, Claude, and Gemini that generate text by predicting the next word.
- This post offers advice on how to talk to these models more effectively, a skill often called "prompt engineering."
- The key insight: LLMs are not thinking beings but next-word predictors; being polite ("please," "thank you") can improve results because the model was trained on polite human text, not because it has feelings.
- Other tips include asking the model to "think step by step" (which reduces errors), giving it a persona ("you are an expert editor"), and breaking complex requests into smaller steps.
- The author frames this as etiquette — not for the AI's benefit, but to train the human to communicate clearly and to leverage how the model's training data works.