AWS Certified AI Practitioner (AIF-C01)

Which description best defines prompt engineering?

1. APhysically upgrading the servers on which the model runs
2. BManually relabeling the model's entire training dataset
3. CDesigning and refining the input instructions to a model to get better outputsCorrect
4. DRewriting the model's internal source code in order to change its neural architecture

Why: Prompt engineering is the practice of crafting and refining prompts, wording, context, examples, and structure, to guide a model toward higher-quality outputs, without altering the model's weights or code.

What most clearly distinguishes generative AI from traditional discriminative machine learning?

1. AGenerative AI is always faster and cheaper to run than every other type of machine learning model
2. BGenerative AI creates new content such as text or images, not just labels for existing dataCorrect
3. CGenerative AI needs no training data whatsoever and can function from nothing but a short prompt
4. DGenerative AI is able only to sort each of its inputs into a set of predefined fixed categories

Why: Generative models produce new artifacts (text, images, audio, code) that resemble their training data. Discriminative models instead label or score existing inputs. Generative AI still needs training data and is often compute-intensive.