Inference
Inference is the act of running a model to produce an answer, as opposed to training it in the first place.
In a little more detail
Training happens once and costs a fortune. Inference happens every time somebody asks a question, which is why answer quality, speed and cost are all discussed in terms of it.
Related terms
- LLM: An LLM, or large language model, is the program underneath AI search: software trained on an enormous amount of text that predicts what words should come next.
- Training data: Training data is the enormous body of text AI search learned from before it was released, which is fixed, often months or years old, and cannot be edited by you.
See it on your own site
The scan reads your site the way AI search does and reports where you stand on this and sixteen other checks.