OOD

Definition

Cases that look different from anything the model saw during training.

Out-of-distribution inputs — examples drawn from a distribution sufficiently different from the training distribution to stress generalization.

Also called: out-of-distribution

Mentioned in 9 episodes

1. 079
   An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
2. 066
   Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
3. 051
   Why Parallel Sampling Plateaus, And What Evidence Graphs Do Instead
4. 047
   When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
5. 040
   Two Frozen Models Learn to Whisper: Coupling Through Hidden States
6. 032
   A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
7. 022
   Training the Model Spec Directly: An Alignment Lever Aimed at the Say-Do Gap
8. 017
   When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
9. 013
   Why Search Keeps Rediscovering the Same Workflow, and What That Means