classifier

Definition

Plain language

A program that sorts things into categories, like 'spam or not spam'.

Also called: classifiers

Why it matters: It turns messy inputs into clean category labels, making it a cheap, fast tool for tasks like flagging suspicious or sensitive content.

For example, an email program uses a classifier to decide whether each incoming message goes to the inbox or the spam folder.

Heard on the show

“One line: off-the-shelf safety classifiers do poorly on these cases, one scored around forty-four percent.”

Mentioned in 24 episodes

1. 202
   How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
2. 196
   AI Agents Reached Opposite Conclusions From the Same Data — and Passed Review
3. 174
   When the AI 'Schemes,' It's Usually Just Lazy or Confused
4. 171
   The Safety Decision a Model Makes Before It Thinks a Word
5. 159
   Can a Coding Agent Run Its Own Robot Experiments Overnight, With No Human Resetting the Scene?
6. 158
   How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
7. 152
   Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
8. 146
   How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
9. 140
   When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
10. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
11. 118
    Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
12. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
13. 104
    How Making a Research Agent Smarter Quietly Makes It Leak Your Secrets
14. 103
    AI Agents Tried to Invent a Post-Human Language, And Reinvented Cherokee
15. 089
    When AI-Written Papers Read Well But the Evidence Underneath Is Broken
16. 088
    Two Levers for Self-Improving AI: When Rewriting Code Isn't Enough
17. 087
    When No Agent Reads the Whole Document: A Universal Cliff in Multi-Agent Review
18. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
19. 073
    When Three LLMs Talk to Each Other, Their Ideas Quietly Stop Moving
20. 064
    When Agent Memory Stops Being a Database and Starts Being a Skill
21. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
22. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
23. 018
    Language Models Compute the Rational Move, Then Override It
24. 002
    An AI Ran a Real Optics Lab for 21 Hours and Found a Transformer-Shaped Pattern in Light

Related concepts