- In short
- Diagnosing a flawed A/B comparison means recognising the compound failure of an undersized sample, an uncontrolled input distribution, and post-hoc metric selection. A small sample such as 50 sessions per arm can show a gap within the noise floor that disappears at scale; an uncontrolled distribution where one arm sees easier inputs can produce an apparent win that is really a sampling artifact; and choosing the primary metric after seeing which one moved converts the experiment into outcome-shopping. Any one of the three is sufficient to invalidate a result.
Full concept guide coming soon
We are building the in-depth, exam-aligned guide for this knowledge point. In the meantime, explore the prerequisites and related concepts below, watch the official Anthropic Academy lessons, and start an adaptive study session to master it with Archie.
Watch and learn
Official Anthropic Academy lessons first, then hand-picked walkthroughs. Videos load only when you press play.
No videos curated for this concept yet
We are still curating the best official and community videos for this topic.
References & primary sources
Adaptive study
Master this concept with Archie
Practice it inside an adaptive study session. Archie, your Socratic AI tutor, tracks your mastery with Bayesian Knowledge Tracing and schedules the perfect next review.