Knowledge Cutoff

The date after which a model's training data ends — everything later is invisible to it.

A model knows nothing about the world after its cutoff unless it is given search or documents at inference time. This is why models confidently describe superseded versions of software and miss recent events. Retrieval and web tools are the fix; the cutoff itself never moves without retraining.

In practice: Asking a model for ’the latest’ anything is unreliable unless it can search.