Chapter 03

Sampling and Uncertainty

Estimate behavior from samples without pretending the sample is the truth. Report confidence intervals and sample counts next to scores. Prefer paired comparisons when the same cases run through competing versions. Separate model-reported confidence from measured statistical…

Apply this chapter

  • Estimate behavior from samples without pretending the sample is the truth.
  • Report confidence intervals and sample counts next to scores.
  • Prefer paired comparisons when the same cases run through competing versions.
  • Separate model-reported confidence from measured statistical confidence.

Continue the conversation

Apply this to your context.

Save your product context once, then open a focused conversation that combines it with this concept.

5 focused briefs

Concepts in this chapter

  1. 015
    Sampling: One Run Tells You Almost NothingFor unpredictable systems, a single output is an anecdote. A sample is the beginning of evidence.
  2. 016
    How Many Samples Are Enough?Sample size is a risk decision. The higher the stakes and the rarer the failure, the more evidence builders need.
  3. 017
    Basic Stats Every AI Builder Should KnowA few practical statistics can help developers explain non-deterministic quality without pretending the data is more precise than it is.
  4. 018
    Confidence Intervals: Saying "About" Like a ProfessionalConfidence intervals help Confidence Engineers report estimates as ranges instead of pretending sample results are exact truth.
  5. 019
    AI-Reported Confidence vs. Statistical ConfidenceAn LLM saying it is confident is not the same as a confidence interval calculated from sample data.

Shared across the Knowledge Edition

Adapt every concept to your world.

Describe your product, role, users, risks, constraints, or current quality problem. This stays in this browser until you choose to send it to ChatGPT.

Saved only in this browser.0 / 2400