- In short
- Training-time alignment is the broad safety behaviour baked into Claude before any deployment exists; it reduces general-purpose harm on every request but never saw your partner's data rules, authorization model, or domain policy. Inference-time control is the runtime layer you build - system instructions paired with input screening, output screening, tool authorization, and human review - and it is the only layer that actually enforces deployment-specific rules.
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.