How does a model learn?
During training, a model adjusts parameters to reduce errors against a defined objective, using examples. During inference, it applies the learned patterns to a new input. Quality depends on the data, the training objective and the context in which the model is used.
A language model predicts sequences of text units called tokens. Its parameters do not work like a library of verifiable documents. A product may add search or other sources, but that is a specific capability that needs to be confirmed.
Asking a model without search about a recent regulation may produce an outdated answer. Asking for a link does not guarantee that the link exists or supports the claim.
Distinguishing the model from the tools connected to it prevents assumptions about capabilities it does not have.
Try it yourself
Choose three tasks from your day. For each, write down the desired result, the data it needs and whether a simple rule would solve the problem. Explain one task for which you would not use AI.