---
title: "Jordan Hoffmann"
type: "entity"
entity_kind: "person"
status: "hub"
canonical_name: "Jordan Hoffmann"
aliases: []
first_seen: "2026-08-22T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["compute-optimal training","Chinchilla","neural scaling laws","Jared Kaplan","DeepMind"]
seek_code_commit: "17d9798"
---


First/co-lead author of "Training Compute-Optimal Large Language Models"
(arXiv:2203.15556, 2022), the DeepMind paper — popularly known by its
70-billion-parameter model, "Chinchilla" — that corrected the field's
prevailing recipe for splitting a fixed compute budget between model size
and training data.

Matters to this vault as the figure whose paper directly rebuts
[[entity-jared-kaplan|Jared Kaplan]]'s 2020 scaling-law exponents: where
Kaplan's own reported allocation ratio implied growing parameters 5.5x for
every 1.8x growth in training tokens, Hoffmann et al. found the two should
grow equally, and backed the correction with a 70B model that beat four
larger, differently-trained contemporaries on the same compute budget.

## References
- [[claim-hoffmann-2022-compute-optimal-scaling-splits-equally-between-parameters-and-data]]
- [[claim-hoffmann-2022-chinchilla-70b-outperforms-larger-undertrained-contemporaries]]
- [[claim-hoffmann-2022-loss-decay-exponents-are-3x-larger-than-kaplans]]