• 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.

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

• articleStealing Reasoning Traces from Proprietary LLM APIssimonwillison.net
• articleHow Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought TrajectoriesHui Wei, Junda Wu, Sheldon Yu, Sizhe Zhou, Yizhu Jiao, Ming Zhong, Bowen Jin, Tong Yu, Shijia Pan, Jiawei Han, Julian McAuley
• articleLanguage Models Don T Always Say What They Think Unfaithful Explanations In Chain Of Thought Prompting 2023 05 07Cohere

Checking sign-in…

Loading comments…