Glossary · Term

decision boundary

← all terms

Definition

Plain language

The knife-edge point where a system is nearly tied between two answers and the smallest push tips it either way.

As stated in the literature

The surface in input or representation space where a classifier's predicted class flips; near it, small perturbations produce large changes in the output label while confidence is minimal.

Also called: decision boundaries

Why it matters: Behavior near this edge is where systems are least stable and most easily nudged, which is why both errors and attacks cluster there.

For example, a spam filter that rates one email at 50.1 percent spam and a nearly identical one at 49.9 percent is sitting right on the boundary, where a single extra word flips the verdict.

Heard on the show

“So the correct reading of "Claude went from 0% to 100%" is: on the one question-and-cue combination out of twelve where Claude sat near its decision boundary, stacking cues pushed it decisively.”
Episode 243 — How a Hundred Meaningless Word Choices Add Up to Flip a Model's Answer

Mentioned in 6 episodes

  1. 243
    How a Hundred Meaningless Word Choices Add Up to Flip a Model's Answer
  2. 234
    Two Copies of Gemini Cooperated in a Game Where Betrayal Always Pays
  3. 178
    How an AI Reviewer Learned to Stop Going Easy on AI Writing
  4. 091
    When Better Fine-Tuning Can't Help: A Geometric Impossibility in LLM Causal Reasoning
  5. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
  6. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer

Related terms