AI · Reference
AI vocabulary
Core terms for talking to and about AI. Models, tokens, prompting, behavior, RAG, agents, controls, safety, image generation. The vocabulary that turns hand-waving into instructions a model can act on.
The foundations. Get these and the rest of the vocabulary clicks into place.
Description
The foundations. Get these and the rest of the vocabulary clicks into place.
Terms
token, very well
A model trained on vast text that generates language by predicting the next token. Claude, GPT, Gemini are LLMs.
The chunks a model reads/writes, roughly ¾ of a word. Pricing and limits are counted in tokens.
learned numbers
The learned numbers that store what a model "knows." More isn't always better.
Layers of interconnected "neurons" that transform inputs to outputs, the underlying structure.
architecture (2017)
The architecture behind modern LLMs; its "attention" lets it weigh relationships across text.
Training = learning from data (slow, expensive, one-time); inference = using it to answer (each request).
specialized
Pre-training builds broad ability; fine-tuning adapts a model to a specific domain or style.
fixed date
The date past which the model has no built-in knowledge, needs search for newer facts.
How you talk to a model. Small wording changes produce big quality changes.
Description
How you talk to a model. Small wording changes produce big quality changes.
Terms
The text you send the model, instruction, question, and any context.
A behind-the-scenes instruction setting the model's role, rules, and persona for the whole chat.
Zero-shot = no examples; few-shot = a few examples to show the pattern you want.
Asking the model to reason in steps before answering, improves hard/logic problems.
tax lawyer…"
Telling the model who to be, which shifts its vocabulary, depth, and defaults.
How much text (prompt + history + output) the model can consider at once. Overflow gets dropped.
Asking for a specific machine-readable shape (JSON, table, XML) so output is parseable.
A reusable prompt with variable slots filled in per request.
What models can do, and the quirks to watch for.
Description
What models can do, and the quirks to watch for.
Terms
made-up answer
When a model states false information fluently and confidently. Always verify facts.
Tying answers to provided/retrieved evidence so they're factual, not invented.
working it out
A model working through a problem internally before answering, better on complex tasks.
Handling more than text, images, audio, video, as input and/or output.
honest, harmless
Shaping a model to behave according to human intentions and values.
only at scale
Capabilities that show up in big models but not small ones, not explicitly programmed.
varied answers
The same prompt can give different outputs each time (unless temperature is 0).
tokens per second
How fast a model responds and how many tokens it streams per second.
How models get information beyond their training, the basis of most real AI apps.
Description
How models get information beyond their training, the basis of most real AI apps.
Terms
Fetching relevant documents and feeding them to the model so answers use your data.
A list of numbers representing text's meaning, so similar ideas sit close together.
finds nearest
A store optimized to find the embeddings closest to a query (Pinecone, pgvector, Weaviate).
not keywords
Finding results by meaning rather than exact words, "car" matches "automobile."
Splitting long documents into smaller pieces that fit the context and retrieve precisely.
sessions
Storing facts/preferences so the AI recalls them in future conversations.
in the window
Deliberately assembling the right instructions, examples, and data into the prompt.
A second pass that re-scores retrieved results so the most relevant reach the model.
When a model doesn't just talk, but acts, calling tools and taking steps toward a goal.
Description
When a model doesn't just talk, but acts, calling tools and taking steps toward a goal.
Terms
↻ until done
An AI that loops, plans, takes actions, checks results, to complete a multi-step goal autonomously.
Letting a model call external functions/APIs, search, code, databases, to do real work.
An open standard for connecting AI to tools and data sources (Slack, GitHub, files) in a uniform way.
tools & models
Coordinating multiple steps, tools, or sub-agents into a reliable workflow.
a helper agent
A separate agent spun up to handle a focused subtask (research, verification) in parallel.
How much an agent does alone vs pausing for human approval at key steps.
model decides steps
A workflow follows predefined steps; an agent decides its own steps dynamically.
it can do
Constraints (allowed tools, scopes, checks) that keep an agent safe and on-task.
The knobs that tune how a model generates. Naming these gives you fine control.
Description
The knobs that tune how a model generates. Naming these gives you fine control.
Terms
Randomness. Low = focused/repeatable; high = varied/creative.
Limits choices to the most probable tokens summing to p, another diversity control.
A ceiling on how long the response can be.
Text that, when generated, halts the output, useful for clean formatting.
they're generated ▋
Sending the response token-by-token as it's produced, so the user sees it type out.
A fixed starting value that makes random generation repeatable.
Measuring whether AI works, and keeping it from misbehaving.
Description
Measuring whether AI works, and keeping it from misbehaving.
Terms
Tests that measure model quality on a task. Build your own to know if changes help.
training data
Systematic skew inherited from training data that can produce unfair outputs.
hijacks instructions
Hidden instructions in input data that trick a model into ignoring its real task.
safety rules
Crafted prompts that try to bypass a model's safety guidelines.
to find flaws
Deliberately probing a system for failures and harms before users find them.
& output
Checks that block unsafe inputs/outputs around the model.
→ model improves
Training a model using human ratings of its responses to align behavior.
Whether a model's stated certainty matches how often it's actually right.
The vocabulary for generating images, audio, and video.
Description
The vocabulary for generating images, audio, and video.
Terms
Generates images by starting from noise and progressively refining (Stable Diffusion, Midjourney, DALL·E).
Creating an image from a text description (the prompt).
Emphasizing or de-emphasizing parts of an image prompt with weights.
Telling the model what to avoid in the image.
Fixes the starting randomness so you can reproduce or vary an image consistently.
extend beyond image
Regenerating a masked region (inpaint) or extending the canvas (outpaint).
Increasing an image's resolution while adding plausible detail.
pose / edge / depth map
Steering generation with an extra input, a sketch, pose, or depth map, for precise control.