chain-of-thought-google-brain-2022
IN premise — entries/2026/06/21/wiki-Prompt_engineering-chunk-1.md
Created 2026-06-21T09:50:10+00:00
Chain-of-thought prompting was proposed by Google Brain in 2022; zero-shot CoT works by appending 'Let's think step-by-step' to the prompt
Summary
This anchors a foundational fact about where chain-of-thought prompting came from and how the simplest version of it works: just telling a model to reason step by step, a technique Google Brain introduced in 2022. It matters because many downstream claims about LLM capabilities, prompt-engineering effectiveness, and the reliability of model "reasoning" are built on this as a starting assumption, so getting the provenance and mechanism right keeps those inferences grounded.
Dependents
These beliefs depend on this one:
- IN google-research-lineage-spans-transformer-to-frontier — Google's research lineage connects the original Transformer (2017), BERT (2018), Chain-of-Thought prompting (2022), and the model evolution through to Gemini — a continuous thread from foundational architecture to frontier capability.