Testers of a public-radio playlist writer send station briefs and then judge clarity, freshness, and house-rule fit of the produced hour. They never open the weights. Which GenAI test approach is that?
Select an answer to reveal the explanation.
Short Explanation
Send station briefs, then judge clarity, freshness, and house-rule fit of the produced hour, without opening the weights. That is black-box evaluation of generated content. A playlist writer is the SUT, not a CT-GenAI test-generation tool.
Full Explanation
GenAI as the SUT is tested black-box by sending briefs and judging outputs. Weight inspection, Chapter 6 documentation review, and CT-GenAI “AI for testing” are out of this LO.