Lesson 36 · 2 min
The knowledge cutoff
A model only learned from text up to a certain date, so on its own it does not know what happened after that.
A model is trained on a huge collection of text gathered up to some point. That point is its knowledge cutoff. Anything newer simply was not in its training data.
Ask about last week's news, today's exchange rate or a new phone model, and a chatbot without web access may give an old answer, guess, or say it does not know.
The cutoff is often months before the model is released, and people keep using a model long after that. So the gap between what it knows and today can be a year or more.
Many chatbots can now search the web to fill the gap. When they do, they usually show sources. If there are no sources, assume the answer comes from older training data.
Do it now
Find the edge of its knowledge
- 1. Ask a chatbot the question in the prompt below.
- 2. Then ask about a news event from this month, with web search turned off if you can.
- 3. Notice whether it admits it does not know or tries to guess.
What is the most recent date your training data covers? If I ask about something after that date, how will you tell me you do not know?
Quick check
Keep going
Next →Web search and deep research modesWords from this lesson
- Knowledge cutoff
- The date after which a model learned nothing new. Unless it can search the web, it may not know recent events.
- Training data
- The examples, such as text, images or recordings, that a model learns its patterns from.