LLM Foundations · 60 to 90 minutes
Correct common LLM assumptions
Explain why a context window is not a word count, why a model does not remember earlier chats on its own, and why temperature zero does not make an answer true.
1.5 h
1
Step 1: The question
A teammate says that a 10,000-token context model can read 10,000 words, remember every earlier chat, and become fully accurate at temperature zero. Explain the problems with these assumptions.
2
Step 2: Hints
Optional. Each hint gives a little more away.
3
Step 3: Your answer
Kept in this browser. Saving your score below keeps a copy with it.
0 / 5000
4
Step 4: Reference answer
5
Step 5: Score yourself
Score each dimension 0, 1, or 2, then save the score to your history. Readiness thresholds are editorial estimates.
Grades your written answer against this rubric with your own AI provider key from Settings. It is a second opinion: the score you save is still yours.
0 of 8 · Scored 0 of 4 dimensions
Ready at 6 of 8, with no 0 in Token accuracy or Context and memory explanation
Kept in this browser until you sign up, then it moves to your account.
Complete this level when you can answer the canonical question in two minutes, work the context budget without looking at the answer, and explain how you would catch an invented citation.
Your saved scores
Practice saves and mock interview answers on this question, newest first.
No saved scores yet. Score every dimension, then save.
6
Step 6: Follow-up questions
An interviewer may ask these next.
What is a token?
Does a model remember earlier messages?
Does temperature zero guarantee truth?
How does inference differ from training?
Why can an LLM invent a citation?
7