{"data":{"slug":"chinchilla-paper","etype":"paper","name":"Training Compute-Optimal LLMs — Chinchilla (2022)","cat":"Scaling","subtitle":"DeepMind's correction: most models were undertrained on data.","summary":"Hoffmann et al. showed compute-optimal training wants ~20 tokens per parameter — far more data than the field was using — so a 70B model trained right beat a 280B one. It reshaped every subsequent training run and made data supply a first-order constraint.","attrs":null,"kf":null,"aliases":["Chinchilla"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/2203.15556","label":"arXiv 2203.15556"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T04:58:07+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}