{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2022-01-28-chain-of-thought/","md":"https://postcutoff.com/e/2022-01-28-chain-of-thought/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2022-01-28-chain-of-thought","date":"2022-01-28","date_precision":"day","short_title":"Chain-of-thought prompting elicits reasoning in LLMs","deck":null,"takeaway":"Wei et al. showed that prompting large models to write out intermediate reasoning steps dramatically improves performance on math and logic tasks — an ability that emerges with scale.","category":"research","category_label":"Research","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (arXiv)","url":"https://arxiv.org/abs/2201.11903","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Language Models Perform Reasoning via Chain of Thought (Google Research blog)","url":"https://research.google/blog/language-models-perform-reasoning-via-chain-of-thought/","type":"official","group":"primary","domain":"research.google"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google Research"],"title":"Chain-of-thought prompting elicits reasoning in LLMs","summary":"Wei et al. showed that prompting large models to write out intermediate reasoning steps dramatically improves performance on math and logic tasks — an ability that emerges with scale.","key_facts":["arXiv 2201.11903 (January 2022); NeurIPS 2022","PaLM 540B with chain-of-thought reached state of the art on GSM8K math word problems at the time","Follow-up: 'Let's think step by step' zero-shot CoT (Kojima et al., 2022)","Precursor to trained reasoning models like OpenAI o1"],"key_numbers":[],"tags":["reasoning","prompting","llm"],"science":null,"body_md":"## What happened\n\nAdding worked examples with step-by-step reasoning in the prompt caused large models to reason explicitly before answering.\n\n## Why it matters\n\nMade 'thinking out loud' central to LLM capability; RL-trained reasoning models (o1, R1, Claude extended thinking) are its descendants.","disputed":[],"related":[{"id":"2024-09-12-openai-o1","url":"https://postcutoff.com/e/2024-09-12-openai-o1/","date":"2024-09-12","date_precision":"day","short_title":"OpenAI o1: reasoning models trained with reinforcement learning","deck":null,"takeaway":"Opened the 'reasoning model' era and a new scaling axis (test-time compute); every major lab followed within months.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["OpenAI"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/chain-of-thought-prompting"}