The most-looked-up terms in the AI Dictionary this week, ranked by real page views.
Trending this week — most-looked-up terms, ranked by real page views.
meatproxy
A meat proxy is a person who forwards AI-generated text, code, or other output without reading, understanding, or validating it, acting only as a relay to the recipient.
Claude-ese · Opus-ese · token vomit
Claudish is the dense, jargon-heavy register Claude and similar coding agents default to — compressed metaphors, invented compound nouns, and objects doing action verbs.
Claude is Anthropic's family of large language models, built with an emphasis on helpfulness, harmlessness, and honesty as core training objectives.
GEV · WorldView globe · gods-eye-view
God's Eye View is an MIT-licensed browser globe by Bilawal Sidhu that fuses public aircraft, ship, satellite, and camera feeds with an optional OpenAI Realtime voice agent.
Open Bot · CopilotKit OpenBot
OpenBot is CopilotKit's open-source, self-hosted platform for AI coworkers: each Bot gets its own computer, and a gateway decides and records every action before it runs.
Diarization · Speaker Attribution
Speaker diarization is the step in a transcription pipeline that answers "who spoke when", splitting audio into segments and labelling each one with a distinct speaker identity.
MHS
The Model Hardware Standard (MHS) is Anthropic's open specification letting AI agents safely discover and operate physical lab and manufacturing equipment through a standardized driver layer.
AI Model · Machine Learning Model
A model is the trained set of parameters and computations that maps inputs to outputs after learning from data.
Load-Bearing Comment · Load-Bearing Hack
Load-bearing describes a piece of code, comment, prompt, or workaround that looks disposable but is actually critical to the system working.
agent skill · capability
A reusable, self-contained capability that an agent can invoke — such as "search the web," "write code," or "analyze an image" — typically defined as a tool, prompt template, or sub-workflow.
MCP
Model Context Protocol is a protocol for connecting AI applications to external tools, prompts, and contextual resources through a consistent interface.
AI
Artificial intelligence is the field of building computer systems that perform tasks associated with perception, reasoning, learning, language, or decision-making.
throttling
A cap on how many API requests a client can make in a time window, protecting servers and enforcing plan tiers.
code mode · tools as code
Code-mode exposes agent tools as shell commands so a model can batch many actions into one script instead of making one tool call per model turn.
open-source intelligence · open source intelligence · OSINT client
OSINT is intelligence gathered from publicly available sources — broadcasts, published APIs, and open datasets — rather than classified or covert collection.
PPE · PPE Earth AI · Google PPE
The Planetary Prediction Engine is Google Research's experimental Earth AI agent that turns a geospatial natural-language query into data discovery, multimodal fusion, AutoML, and a written report.
pay-to-reset · quota reset
A usage reset is a paid or free add-on that instantly refills a subscriber's hit AI usage quota instead of making them wait for the plan's normal reset window.
proof assistant · machine-checked proof
Formal verification is checking that a claim follows from stated rules by a mechanical proof, not by reading a plausible argument.
Mermaid-slop · Diagram Slop · AI Diagram Slop · Flowchart Slop
Mermaid slop is the generic, auto-layout, brand-mismatched diagram AI coding agents default to producing for every request, regardless of what the content actually needs to show.
Agent · Agents · AI agents · AI agent
An AI agent is a system that observes context, chooses actions, and uses their results to pursue a goal.
A test set is held-out data reserved for estimating final performance after development choices are complete.
agent graphs · agentic graphs · org graph
Graph engineering is designing a multi-agent organization as a programmable graph: which agents exist, what each owns, and how work flows between them.
Tool Calling
Tool use lets a model request an external operation instead of trying to produce every result from its internal parameters.
Vibecoding
Vibe coding is writing software by describing what you want to an AI model and accepting its output with little manual review of the underlying code.
Git is a distributed version-control system that tracks snapshots of a repository as linked commits.
explainx.ai Melo · Melo learning copilot · Blog Melo
Melo is explainx.ai's AI learning copilot — a tutor with Quiz, Practice, and Explain Back modes, grounded in pathways, articles, and the skills registry.
Gauntlet Loops
A Gauntlet Loop is a named multi-agent prompt pattern — coined by Matt Shumer — that decomposes a goal into pieces, gives each piece its own builder and a separate fresh-context critic agent, and keeps looping builder-fixes-gap until the critic's blind comparison says the output beats a concrete real-world quality bar.
Glorified autocomplete is a dismissive description of large language models as simple next-word predictors with no real understanding, scaled up and dressed in a chat interface.
Slop
AI slop is low-quality, mass-produced generative AI content published without meaningful human review or a genuine audience need.
τ³-bench · tau3 bench · tau-bench 3
Tau3-Bench (τ³-bench) is an agent evaluation suite in the τ-bench family, measuring multi-step tool use with official graders on domain scenarios such as banking.
