TopDev
34 terms · Updated weekly

Quick lookup of AI terms in plain language

Every term: short definition → real example → when to use. No translation-ese, no fluff.

📚
34
Terms
🌱
15/34
Beginner
15/34
Intermediate
🔥
4/34
Advanced

✨ Start here

Foundational terms to read first if you're new to AI.

34 terms

All terms

⚙️
Beginner

What is a Context Window?

The maximum amount of text an LLM can 'remember' in a single pass. It decides how much information you can fit into a prompt.

⚙️ Techniques #context#llm
🤖
Intermediate

What is a Diffusion Model?

A class of AI model that generates images by gradually denoising — the technology behind Midjourney, Stable Diffusion, and DALL-E.

🤖 Models #diffusion#image-gen
🤖
Intermediate

What is a Foundation Model?

A large AI model trained on broad, general-purpose data — used as a base to fine-tune for many different tasks.

🤖 Models #foundation-model#llm
🌱
Beginner

What is a GPU? Why does AI need GPUs?

Graphics cards — hardware that accelerates parallel computation, the backbone of every modern AI model.

🌱 Basics #gpu#phan-cung
🌱
Intermediate

What is a Neural Network?

A computational structure inspired by how neurons in the brain connect — the foundation of modern deep learning.

🌱 Basics #neural-network#deep-learning
⚙️
Beginner

What is a System Prompt?

An instruction block that 'configures' an LLM before the user starts chatting — it sets the AI's persona, format, and limits.

⚙️ Techniques #system-prompt#prompt
⚙️
Beginner

What is a Token (in LLMs)?

The smallest unit an LLM processes — not a word, but a fragment. Tokens determine API cost and context limits.

⚙️ Techniques #token#llm
🤖
Advanced

What is a Transformer?

A neural network architecture introduced in 2017, the foundation behind every modern LLM (GPT, Claude, Gemini).

🤖 Models #transformer#deep-learning
🛠️
Intermediate

What is a Vector Database?

A type of database specialized in storing and quickly searching vector embeddings — the foundation for RAG and semantic search.

🛠️ Tools #vector-db#embedding
🌱
Intermediate

What is AI Alignment?

The research field that works to keep AI acting in line with human intent and values — even as systems grow more powerful.

🌱 Basics #alignment#safety
⚙️
Beginner

What is AI Hallucination?

When an LLM confidently produces information that is factually wrong — fabricated stats, fake citations, made-up events.

⚙️ Techniques #hallucination#llm
🚀
Intermediate

What is an AI Agent?

An AI system that can plan, use tools, and take multi-step actions to complete a goal — not just answer a single question.

🚀 Applications #agent#tool-use
⚙️
Beginner

What is an AI API? How to use LLM APIs

How developers call AI models from code — how the Claude API, OpenAI API, and Gemini API work.

⚙️ Techniques #api#developer
⚙️
Intermediate

What is an Embedding?

A way to represent text, images, or anything else as numerical vectors so machines can compare meaning.

⚙️ Techniques #embedding#vector
🤖
Beginner

What is an LLM?

Large Language Models — AI systems trained on massive text corpora that can understand and generate human-like text. ChatGPT, Claude, and Gemini are all LLMs.

🤖 Models #llm#basics
🌱
Beginner

What is Artificial Intelligence (AI)?

The branch of computer science that builds machines capable of mimicking human reasoning, learning, and decision-making.

🌱 Basics #ai#co-ban
⚙️
Beginner

What is Chain of Thought (CoT)?

A prompting technique that asks an LLM to 'think step by step' before answering — significantly boosts accuracy on hard problems.

⚙️ Techniques #cot#prompt
🌱
Beginner

What is Computer Vision?

The branch of AI that lets machines 'see' and interpret images and video — from face recognition to self-driving cars.

🌱 Basics #computer-vision#vision
🌱
Beginner

What is Deep Learning?

A branch of machine learning that uses many-layered neural networks to learn from complex data like images, audio, and text.

🌱 Basics #deep-learning#neural-network
⚙️
Intermediate

What is Fine-tuning?

The process of further training an existing AI model on your data so it gets better at a specific task or matches a specific style.

⚙️ Techniques #fine-tuning#training
⚙️
Intermediate

What is Function Calling (Tool Use)?

The ability for an LLM to call external functions or APIs to fetch real data — not just generate text from memory.

⚙️ Techniques #function-calling#tool-use
🌱
Beginner

What is Generative AI?

A type of AI that doesn't just classify or predict — it CREATES new content: text, images, video, code, and music.

🌱 Basics #generative-ai#co-ban
⚙️
Intermediate

What is Inference (AI Inference)?

The process of running a trained AI model to serve users — the main driver of cost and latency in any AI product.

⚙️ Techniques #inference#llm
⚙️
Intermediate

What is Jailbreak (AI)?

Techniques that bypass an LLM's safety guardrails to make it do something it would normally refuse.

⚙️ Techniques #jailbreak#safety
⚙️
Advanced

What is LoRA?

Low-Rank Adaptation — a technique for fine-tuning large models that saves 100-1000× the resources of full fine-tuning.

⚙️ Techniques #lora#fine-tuning
🌱
Beginner

What is Machine Learning?

An approach to AI where computers learn patterns from data instead of being programmed step by step.

🌱 Basics #machine-learning#basics
⚙️
Intermediate

What is MCP (Model Context Protocol)?

An open standard from Anthropic that lets LLMs connect to tools, databases, and apps through a single unified protocol.

⚙️ Techniques #mcp#agent
⚙️
Intermediate

What is Multimodal AI?

AI that can handle multiple data types at once — text, images, audio, video — not just text like older LLMs.

⚙️ Techniques #multimodal#llm
🌱
Beginner

What is NLP (Natural Language Processing)?

The branch of AI that helps machines read, understand, and produce human language — from Google Translate to ChatGPT.

🌱 Basics #nlp#language
⚙️
Beginner

What is Prompt Engineering?

The craft of writing instructions that get AI models to produce better, more reliable output.

⚙️ Techniques #prompt#llm
⚙️
Advanced

What is Quantization?

A technique for reducing numeric precision in AI models so they run faster and use less RAM — at the cost of a bit of accuracy.

⚙️ Techniques #quantization#optimization
⚙️
Intermediate

What is RAG (Retrieval-Augmented Generation)?

A technique that lets an LLM look up your documents before answering — reducing hallucinations and grounding answers in real data.

⚙️ Techniques #rag#llm
⚙️
Advanced

What is RLHF?

Reinforcement Learning from Human Feedback — a technique that uses human feedback to teach LLMs to answer in a way that matches human preferences.

⚙️ Techniques #rlhf#training
⚙️
Intermediate

What is Training?

The process of teaching an AI model by showing it millions or billions of examples and adjusting its internal parameters.

⚙️ Techniques #training#llm
💡

Missing a term?

Send a suggestion — we prioritize terms most people ask about.

Suggest a term →