{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2022-03-29-chinchilla/","md":"https://postcutoff.com/e/2022-03-29-chinchilla/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":"2022-03-29-chinchilla","date":"2022-03-29","date_precision":"day","short_title":"DeepMind's Chinchilla revises scaling laws toward more data","deck":null,"takeaway":"Hoffmann et al. found that for compute-optimal training, parameters and training tokens should scale equally (~20 tokens per parameter); 70B Chinchilla outperformed the 280B Gopher.","category":"research","category_label":"Research","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Training Compute-Optimal Large Language Models (arXiv)","url":"https://arxiv.org/abs/2203.15556","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Wikipedia: Chinchilla (language model)","url":"https://en.wikipedia.org/wiki/Chinchilla_(language_model)","type":"discussion","group":"reactions","domain":"en.wikipedia.org"}],"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["DeepMind"],"title":"DeepMind's Chinchilla revises scaling laws toward more data","summary":"Hoffmann et al. found that for compute-optimal training, parameters and training tokens should scale equally (~20 tokens per parameter); 70B Chinchilla outperformed the 280B Gopher.","key_facts":["arXiv 2203.15556 'Training Compute-Optimal Large Language Models'","Chinchilla: 70B parameters trained on 1.4 trillion tokens","Beat Gopher (280B), GPT-3 (175B) and Megatron-Turing NLG (530B) on many benchmarks","Implied most prior LLMs were undertrained"],"key_numbers":[],"tags":["scaling-laws","llm","compute-optimal"],"science":null,"body_md":"## What happened\n\nOver 400 training runs showed earlier scaling laws had over-weighted parameter count relative to data.\n\n## Why it matters\n\nReshaped how every lab trains LLMs, pushing toward far larger datasets and smaller, cheaper-to-serve models (e.g. LLaMA).","disputed":[],"related":[{"id":"2023-02-24-llama","url":"https://postcutoff.com/e/2023-02-24-llama/","date":"2023-02-24","date_precision":"day","short_title":"Meta releases LLaMA, sparking the open-weights LLM wave","deck":null,"takeaway":"Kick-started the open-weights LLM movement that later produced Llama 2/3, Mistral, Qwen and DeepSeek.","category":"open-source","category_label":"Open source","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Meta AI"]},{"id":"2020-01-23-scaling-laws","url":"https://postcutoff.com/e/2020-01-23-scaling-laws/","date":"2020-01-23","date_precision":"day","short_title":"OpenAI publishes 'Scaling Laws for Neural Language Models'","deck":null,"takeaway":"Scaling laws became the strategic basis for the trillion-dollar compute build-out of the 2020s.","category":"research","category_label":"Research","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":1,"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/deepmind-chinchilla-revises"}