vibedonaldsvibedonalds.com
Term

Chain of thought

Asking an LLM to spell out intermediate reasoning steps before producing the final answer. Improves accuracy on multi-step problems by ~10-30 percentage points on most reasoning benchmarks.

Background

Chain of thought (CoT) became standard practice after a 2022 paper showed that just adding 'let's think step by step' raised math-word-problem accuracy dramatically. Modern reasoning models (OpenAI o-series, DeepSeek R1, Claude with extended thinking) generate hidden CoT by default. Visible CoT is still used heavily in classical prompts that target non-reasoning models.