Skip to content

training

Chain of Thought

A prompting technique that encourages language models to show their reasoning step by step before arriving at a final answer. Chain-of-thought prompting significantly improves performance on mathematical, logical, and multi-step reasoning tasks.

In practice

Instead of directly answering '17 x 24 = ?', chain of thought prompts the model to compute 17x20=340, 17x4=68, 340+68=408.

Models

Where it comes up