Nous Releases Arete-27B and an Open Propaganda Eval
Source
nousresearch.com
Author
Nous Research
Date
Why it matters
About 53M tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → of SFT cut state-aligned answers in a strong open model from 22% to under 1% without capability loss in Nous's tests. Engineers get open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition →, an evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → and data to audit or replicate value tuning.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
