(All images are by the writer unless otherwise noted)
Intro
Prompt Engineering is the practice of designing and refining prompts (text inputs) to boost the behavior of Large Language Models (LLMs). The goal is to get the specified responses from the model by rigorously crafting the instructions. Essentially the most used prompting techniques are:
- Chain-of-Thought: involves generating a step-by-step reasoning process to achieve a conclusion. The model is pushed to “think out loud” by explicitly laying out the logical steps that result in the ultimate answer.
- ReAct (Reason+Act): combines reasoning with motion. The model not only thinks through an issue but in addition takes actions based on its reasoning. So it’s more interactive because the model alternates between reasoning steps and actions, refining its approach iteratively. Mainly, it’s a loop of “thought”, “motion”, “commentary”.
Let’s make an example: imagine asking an AI to “find one of the best laptop under $1000”.
– Normal Answer: “Lenovo Thinkpad”.
– Chain-of-Thought Answer: “I would like to contemplate aspects like performance, battery life, and…
