Intel / article

theinformation.com

Source: theinformation.com
Author: Stephanie Palazzolo
Date: Indexed Sep 3, 2026

Why it matters

If frontier models reason in latent loops rather than visible , monitoring and any safety tooling built on readable traces stop seeing the actual computation.

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.
chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.

Read the source theinformation.com