Metrics for GenAI results · Question 28 of 60

A tester runs a prompt once, finds the result very good and declares the prompt finished. What is problematic about this?

1 answer is correct. Medium Created with AI

Show answer

Answer

  • B A single run is not a reliable basis for non-deterministic models

Explanation

The same model may answer less well next time. Only several runs show how good the prompt is on average and how stable it is.

Certifications & exams

Which exam comes next?

You can already practise for 51 exams, and 16 are up for a vote. See all certifications with their official information, cast your vote or suggest your exam.

See all certifications