Fundamentals

The building blocks. If you can't explain these, you're not ready for projects, site tours, or client conversations.

Clear filter

Transformers

The dominant architecture behind modern AI, parallelizable, scalable, attention-powered

Attention Mechanisms

How models decide what to focus on, the core of what makes transformers powerful

Tokens

The atomic units of language that AI models actually process

Embeddings

How models represent meaning internally, dense vectors that capture semantic relationships

Pre-training

The massive first stage that teaches a model to predict language

RLHF / Post-training

Turning a raw autocomplete engine into a useful, safe assistant

Reasoning Training / RLVR

How modern models learn to think step-by-step using verifiable rewards

Base Models

Pure autocomplete, powerful but raw and hard to direct

Instruction-tuned Models

The chatbots you know, RLHF-trained to follow instructions reliably

Reasoning Models

The current frontier, models that think before they answer

System Prompts

The instructions that shape how a model behaves before a user says anything

Context Windows

The maximum text a model can see at once, and why it's so hard to extend

Parameters

The learned weights that define a model, and why size matters

Training vs. Inference

Building a model vs. running one, fundamentally different compute profiles

Hallucinations

When LLMs confidently state things that aren't true, and why it's a fundamental problem

Jailbreaking

Bypassing a model's safety training through adversarial prompting

Tool Use

How LLMs interact with external systems to extend their capabilities

Agentic Capabilities

LLMs running in loops with tools to complete multi-step tasks autonomously

Multimodality

AI that can see, hear, and reason across text, images, audio, and more

Major AI Players

Who's building frontier AI and what differentiates each lab

Open Source vs. Open Weights

The important distinction between truly open AI and 'open enough'

What a Wrapper Is

The thin AI product problem, and why it matters for business strategy

Prompt Engineering

The craft of writing inputs that reliably get the outputs you want

API Basics

How to actually call an LLM from code, the mechanics every builder needs

RAG (Retrieval-Augmented Generation)

Grounding AI responses in your data, the go-to pattern for custom knowledge bases