classifier

A classifier is a machine learning model or algorithm that assigns input data to one of a set of predefined categories.

10 articlesLast mentioned

A classifier is a model or algorithm that assigns input data to one of a set of predefined categories. It is used for tasks whose outcome is a discrete category, such as spam detection, object recognition in images, and sentiment analysis of text. It is distinguished from regression, which predicts continuous values.

In LLM systems, lightweight classifiers are commonly placed before or after a generative model to screen prompts for sensitive information or attacks, route requests to an appropriate model based on their nature, or check whether outputs violate a policy. Because they are far smaller and faster than large generative models, they are often deployed as the first stage of safety and routing pipelines.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • Claude Code Best Practices: Five Jobs to Stop Doing by HandAI in Practice ·

    Approving Confirming every command, or skipping permissions Auto mode and its classifier

    Read article
  • Decision Models: Probabilities, Not Text, for Faster and Cheaper Agent RoutingAI in Practice ·

    In Mastra, an open-source TypeScript framework for building agents that ships with classifier primitives for these models, three question types are available.

    Read article
  • Claude Fable 5.2 Prompting: Set Effort to High, Demand Proof, Drop Old RulesAI in Practice ·

    Anthropic's models now include an automated safety classifier that watches for model distillation attempts, meaning efforts to extract a model's internal reason…

    Read article
  • AI Peer Review Study: Editors Preferred AI Reviews in 87% to 100% of PairsAI News ·

    …design borrows from Claude Code and Claude in Chrome, including auto-mode classifiers and credential protections intended to prevent unauthorized actions such a…

    Read article
  • Coder's Hybrid AI Gateway: Local Models for Bots, Cloud for Developer ChatAI Performance ·

    Lightweight classifiers at the gateway can block sensitive material such as payroll records before any tokens reach a model, and can decide whether a query need…

    Read article
  • Claude Code Limits: Game Clone Ban, Cyber Filters and What $200 a Month BuysAI News ·

    …efense of what it calls a safety margin, openly stating that it tunes its classifiers to fire on prompts that are probably benign in order to keep jailbreaks ou…

    Read article
  • Intelligence Plane: Why Memory and Ontology, Not the Model, Define AI AgentsAI in Practice ·

    …ipelines can use learned models in all ten: a router model, an input guard classifier, a semantic cache validator, an embedder and reranker, a query planner, a…

    Read article
  • AI Agent Guardrails: Citibank's $893.9M Misfire Makes the Case for BrakesAI Security ·

    Auto-mode classifiers: ending approval fatigue

    Read article
  • AI Code Review in Five Layers: How the Claude Code Team Tiers Human ApprovalAI in Practice ·

    An AI classifier assigns each PR its tier, and a second, independent classifier double-checks whether human oversight is needed.

    Read article
  • OpenAI's New Decision Model Picks From a List in 150 ms: Seven Practical BuildsAI in Practice ·

    …rom a distraction-catching focus timer to a rough-cut video editor, it shows clearly where a fast, cheap classifier beats a chat model and where it falls short.

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.