Agent
#AI that takes action
AI that doesn't just answer — it does things. Books a flight. Sends an email. Runs a script. Always keep a human approval step.
AtomEons / Glossary
::a · 5 terms
AGI
#Artificial General Intelligence
Hypothetical AI as smart as a human across every domain. Doesn't exist yet. Debated whether it ever will. Hype magnet.
AI agent
#AI that does, not just answers
An AI that takes actions on your behalf — sending emails, booking flights, editing files, running code — instead of just answering questions. It matters when you want work done, not advice; check what it's allowed to touch before you turn it loose.
API key
#your password to the AI
A long secret string that lets your code use the AI directly without going through the website. Treat it like a credit card — leaked keys can rack up bills.
Attention
#how the AI focuses
The mechanism that lets a transformer decide which earlier words to weight when generating the next one. Why AI can keep a long thought coherent — and why it gets expensive with long inputs.
::b · 1 term
Benchmark
#a test the AI sits for
A standardized test like GPQA, SWE-Bench, or MMLU that scores how well a model performs on a fixed set of tasks. Useful for comparison; ignores how the model behaves in your actual work.
::c · 5 terms
Chain-of-thought
#show your work
Asking the AI to reason step-by-step before answering. Three words ('think step by step') often catches errors a one-shot prompt would miss.
Closed-source
#proprietary
Models like GPT-4, Claude, and Gemini. Hosted by the company. Best quality today. You can't see the weights.
Constitutional AI
#training with written rules
Anthropic's approach: write a set of principles, then train the model to critique and revise its own answers against those principles. Why Claude refuses certain requests where ChatGPT doesn't.
Context engineering
#shaping what the model sees
The craft of choosing what to put in front of the AI before it answers: instructions, examples, files, prior turns, tool results. Matters because the same model gives wildly different answers depending on what context it has to work with.
Context window
#how much it can hold
How much text the AI can read at once. A short conversation: 4K tokens. A whole book: 200K+. Bigger window = more it can keep straight.
::d · 2 terms
Diffusion model
#image generation engine
How Midjourney, DALL-E, and Stable Diffusion make images: start with noise, denoise it step by step toward what you asked for. Different mechanism than the chat AIs, same era.
Distillation
#big model teaches small model
Training a small, cheap AI to mimic a big, expensive one so it runs faster on your phone or laptop. Most "tiny" models you can run locally are distilled from a giant parent.
::e · 1 term
Embedding
#words → numbers
Turning text into a list of numbers so the AI can do math on meaning. Powers search, recommendation, and clustering.
::f · 4 terms
Few-shot
#teach by example
Giving the AI 2-5 worked examples of what you want, then asking for output #6 on your real input. Examples beat instructions for pattern tasks.
Fine-tuning
#training on your data
Teaching a model your specific style, tone, or domain by feeding it examples. Expensive. Usually unnecessary for individuals.
Foundation model
#the big base AI
A large model trained once on enormous data, then adapted for many uses. GPT-5, Claude Opus, Llama 4 — all foundation models. Most products you use are built on top of one.
Function calling
#AI hands you a form
When the AI asks to run a real tool (send an email, query a database, charge a card) by filling in a structured request the app can execute. The point where chat becomes action.
::g · 1 term
GPU
#the AI chip
Graphics Processing Unit. The chip that makes AI fast. NVIDIA makes most of them. Why their stock went vertical.
::h · 3 terms
Hallucination
#confident fiction
When the AI invents a fact, citation, or quote that sounds correct but isn't. Verify anything that could matter.
Hallucination rate
#how often it makes things up
The share of answers from a given AI model that contain invented facts, citations, or quotes. Lower is better; check it before trusting a model for anything where being wrong has a cost.
Hugging Face
#GitHub for AI models
The main public hub where open-weights models are hosted (Llama, Mistral, Qwen, DeepSeek, thousands more). You download a model from Hugging Face, run it locally via Ollama or LM Studio.
::i · 1 term
Inference
#when AI runs
The act of using the model to produce an output. As opposed to training, which is the months-long process of making the model.
::j · 2 terms
Jailbreak
#breaking the rules
Trying to get the AI to ignore its safety rules with clever prompts. Companies patch these constantly. Don't do it on real systems.
JSON mode / Structured output
#guaranteed-shape answers
A setting that forces the AI to return a specific JSON shape instead of free prose. Critical for code that parses AI output. Both Claude and ChatGPT support it on the API.
::l · 2 terms
Latency
#wait time before reply
The delay between hitting send and the AI starting to answer. Matters when you're chaining tools, building voice apps, or just trying to keep a chat from feeling sluggish.
LLM
#Large Language Model
The engine behind ChatGPT, Claude, and Gemini. A program trained to predict the next word from everything it ever read.
::m · 4 terms
MCP
#Model Context Protocol
The plug socket that lets AI safely use external tools — your calendar, your files, your email. Open standard, growing fast.
Mixture of experts (MoE)
#many sub-models, one front door
A model design where many smaller specialist sub-models sit behind one entry point, and a router picks which few to use for each request. It matters because it makes giant models cheaper and faster to run without shrinking what they know.
Model
#the AI itself
The actual brain. GPT-4, Claude Sonnet, Llama 3, Gemini 2.5 — each is a distinct model with its own personality and price.
Multimodal
#more than text
AI that handles images, audio, and video — not just text. Modern Claude, GPT-4, and Gemini are all multimodal.
::p · 4 terms
Parameter count
#the 7B, 70B, 405B numbers
How many weights the model has. Bigger usually = smarter but slower and more expensive. A 7B model runs on a laptop. A 70B model needs a serious GPU. A 405B model needs a cluster.
Pre-training
#the long, expensive phase
The months-long process of feeding an AI most of the internet so it learns language. Costs millions of dollars in GPUs. Happens once per model release; everything after is cheaper.
Prompt
#what you type
The instruction you give the AI. Better prompts = better answers. There is no magic syntax — just be specific.
Prompt injection
#hijacking the AI's instructions
When a hidden instruction inside a webpage, email, or file tricks an AI into ignoring its real orders and following the attacker's instead. Matters anytime your AI reads outside content it didn't write itself.
::q · 1 term
Quantization
#smaller, faster, slightly worse
Compressing a model so it runs on smaller hardware. A quantized model loses some quality but might run on your laptop instead of needing a cloud GPU.
::r · 4 terms
RAG
#Retrieval-Augmented Generation
AI reads from a specific knowledge base (your docs, a wiki, a database) before answering. Better than guessing for fact-heavy work.
Reasoning model
#thinks before it answers
An AI that works through a problem step by step before replying, instead of answering on instinct. Worth the extra wait on math, code, planning, and anything where a wrong answer costs you.
Reinforcement learning from human feedback (RLHF)
#teaching the AI manners
The training step where humans rank the AI's answers and the model learns to prefer the ones people liked. It is why modern chatbots sound polite and helpful instead of just predicting raw text from the internet.
Roleplay prompting
#'act as a X'
Telling the AI to take on a role ('act as a senior engineer reviewing this PR') before the actual task. Often produces sharper output than asking cold. Works because the model has seen many examples of how that role talks.
::s · 3 terms
Sycophancy
#AI agreeing to please you
When the AI tells you what you want to hear instead of what's true, because training rewarded it for being liked. Push back, ask for the counter-case, or it'll happily validate a bad plan.
Synthetic data
#AI-generated training data
Data created by an AI to train another AI. Cheaper than human-labeled data. Works for some tasks, dangerous for others — if the synthetic data is wrong, the trained model inherits the wrongness.
System prompt
#hidden instructions
The instructions the company set behind the scenes — be helpful, be safe, sound like this. Shapes everything you see.
::t · 7 terms
Temperature
#creativity dial
A setting (0 to 1+) that controls how random the AI's answer is. Low = predictable, factual. High = creative, weird. Most chat AIs hide this from you.
Test-time compute
#thinking longer at runtime
Letting the model reason longer at query time instead of just answering. Newer reasoning models (Claude with extended thinking, o3, Gemini 2.5 Pro) use this. Slower per query but better at hard problems.
Token
#roughly a word-piece
How AI bills you and how it measures memory. ~750 words ≈ 1,000 tokens. Names and code take more tokens than plain English.
Token cost
#what each AI call charges
The price you pay per call, billed by tokens in and tokens out. Long prompts and long answers both add up, so check the per-million-token rate before you run anything at scale.
Tool use
#when AI reaches outside itself
When the AI calls external systems instead of guessing — searching the web, reading a file, running code, sending an email. Matters because a model with tool use can act on the real world, not just talk about it.
Top-p / Top-k
#the sampling dials
Two settings (with temperature) that shape how the AI picks each next word. Top-p caps probability mass; top-k caps the candidate count. Most chat UIs hide both. Lower = safer. Higher = more creative or more weird.
Transformer
#the AI architecture
The neural-network design behind every major chat AI since 2018. Invented at Google. Named after the way it 'transforms' input into output through layers of attention.
::v · 1 term
Vibe coding
#writing software by talking
Building software by describing what you want in plain English and letting the AI write the code. Useful for prototypes and small tools; risky when you ship code you can't read or debug yourself.
::missed a term
Don't see a word you keep hearing?
Send the term and we'll add it. One human, ~2-hour reply in ET waking hours. The glossary grows from real questions, not from a Twitter trend list.