Grokking LLM Evals
Vote

0% completed

​

Chapter Assessment: What an Eval Is

This review covers the first chapter: what an eval is, why LLM features need one, the job ticket assistant's promises, the kinds of eval, and the development loop. The bank holds 20 questions, and each attempt draws ten, so a second attempt gives you different coverage. Most questions describe a situation with the job ticket assistant and ask what a team should do or conclude, rather than asking for a definition. Have three things ready: the four parts of an eval, the difference between a capability eval and a regression eval, and the order of the five steps in the loop. A few questions ask for a simple pass rate. When you get a question wrong, treat it as a pointer to the lesson worth rereading, and read the explanation on every option, including the ones you did not choose.

General
Test Your Knowledge
Check your understanding and reinforce the key concepts covered in this section with a short, targeted assessment.
10 Questions
~15 mins
Your progress is saved automatically

Reading Progress

0%


Vote for new content