All terms
Foundations
Knowledge Cutoff
The date where a model's training data ends, beyond which it has no built-in knowledge.
Definition
A knowledge cutoff is the point in time where a model's training data stops, so it has no built-in knowledge of events after that date. To answer questions about newer information, the model must be given external tools such as web search or retrieval. The cutoff is a property of the training run, not a hard limit on what the system can ever know.