Mixture of Experts
Also: MoE
An AI architecture where only part of the model activates for any given request — different specialized 'sub-models' (experts) handle different types of tasks. It lets you build very large, capable models without needing proportionally large computing power for every query, because you're only using a relevant slice of the model at any given time. It's an efficiency technique that makes some of the largest AI models practical to run.
In practice
You send Claude a coding question and a cooking question. Internally, different parts of the model specialize in each domain — only the relevant "expert" activates for your request. Mixture of Experts is the architecture that makes this work, allowing very large, capable models to run efficiently by only using a relevant slice of their capacity per query.
Related concepts