Glossary
What is knowledge cutoff?
The date after which a model has no training knowledge.
Every model is trained on a snapshot of text collected up to a fixed date. Anything after that date is unknown unless it is supplied in the conversation or fetched by a tool.
Cutoffs are also uneven: coverage thins out well before the stated date, especially for small projects and recent releases.
Pasting the current page is the simplest way to move a question past the cutoff.
In practice
A model trained before a library's version 3 release will keep writing version 2 code until you show it the new docs.
Common questions
- What does knowledge cutoff mean in one sentence?
- The date after which a model has no training knowledge.
- Why does knowledge cutoff matter when you use Claude or ChatGPT?
- Pasting the current page is the simplest way to move a question past the cutoff.
- Can you give an example of knowledge cutoff?
- A model trained before a library's version 3 release will keep writing version 2 code until you show it the new docs.
Related terms
- HallucinationA confident AI answer that is not supported by any real source.
- GroundingTying an AI answer to specific source material you supplied.
- Retrieval-augmented generationFetching relevant documents and adding them to the prompt before the model answers.
- Glossary indexEvery AI context term, defined in plain language.
Get LocalBridge
One click sends your open tabs into Claude or ChatGPT. One-time licence, no subscription.
See how it works