Generative AI · Level 3 of 5
Conditioning
Providing information that guides a model's output distribution.
Conditioning influences generation without necessarily guaranteeing compliance.
Example
A caption guides the content of a synthesized image.
Listen to the definition and example
Audio transcript
Conditioning. Providing information that guides a model's output distribution. Conditioning influences generation without necessarily guaranteeing compliance. For example: A caption guides the content of a synthesized image.
Explore this concept
Why it matters
This helps you reason about how content is generated and which limitations to check.
Start with
Quick recall question
Try answering before looking back at the definition.