Checked fact 139914 Oct 2026Safety and security

Scaling Laws: the abstract says a language model’s loss scales as a power law with model size, dataset size and the compute used for training.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven orders of magnitude.

What the source said when we opened it, on 13 Oct 2026.

The source

Scaling Laws for Neural Language Models (arXiv 2001.08361)
arXiv · 2020-01-23

Open the source archived copy

Checked

Checked by the notis newsroom on 13 Oct 2026, against the source above.

In the story

Dario Amodei wants outside testers inside frontier AI companies 14 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Scaling Laws: the abstract says a language model’s loss scales as a power law with model size, dataset size and the compute used for training.” ai notis, checked 13 Oct 2026. Source: Scaling Laws for Neural Language Models (arXiv 2001.08361) (arXiv). https://ainotis.com/c/1399

As a reference (APA style)

ai notis. (2026, October 13). Scaling Laws: the abstract says a language model’s loss scales as a power law with model size, dataset size and the compute used for training [Checked claim 1399]. ai notis. https://ainotis.com/c/1399

Anyone may quote this address. It does not change; if we correct the story, this page says so.