← All questions
MediumCodingSystem design

Implement temperature, top-k, and top-p sampling

1Give yourself 5 minutes
2Answer out loud, not in your head
3Then compare with the answer below

Reference answer

Then expect these follow-ups

  • What does temperature → 0 converge to?

  • (Greedy argmax.) Why does top-p adapt better than top-k across confident vs uncertain distributions?

  • Why is generation non-deterministic even at temperature 0 on real serving stacks?

Free to read · better with Enzo

Practice this out loud with Enzo

Enzo runs it as a mock interview, pushes back with follow-ups, and grades you on the rubric.

Next question