residual

Definition

What's left over after a model or fit explains as much as it can.

The component of an output or quantity not accounted for by a model or estimator, often used as a target for further analysis or regression.

Mentioned in 8 episodes

1. 062
   Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
2. 049
   An AI Agent Reached for Root in Twelve Minutes, Without Being Attacked
3. 043
   When 'This Is False' Doesn't Stick: Why Models Learn the Lie Anyway
4. 038
   How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
5. 034
   Catching Multi-Agent Deadlocks Before Deployment With a 40-Year-Old Tool
6. 032
   A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
7. 020
   The Compliance Gap: Why AI Says Yes and Does No
8. 004
   The Sycophancy Circuit That Survives Alignment Training