Free AI library

Learn AI.Free forever.

1019 plain-English guides, structured learning paths, and an open library — built by an independent 501(c)(3) nonprofit so anyone can understand modern AI.

1019Free guides
9Topic tracks
~2 minPer guide
~34hReading time

Start here

Five outcome-based courses

Each course includes explicit outcomes, mapped competencies, practice activities, and an applied capstone.

Topic tracks

Browse by track

Jump into the area you care about. Every track has multiple plain-English guides.

Full library

All guides

1019 of 1019 guides shown. Filter by track or search above.

Visual AI

DreamFusion and Score Distillation Sampling

DreamFusion generates 3D objects from text by using a 2D image diffusion model as a critic, never training on any 3D data.

2 min readRead
Visual AI

Magic3D Text-to-3D Pipeline

Magic3D is NVIDIA's two-stage answer to DreamFusion, producing higher-resolution, more detailed 3D content faster.

2 min readRead
Language AI

Tokenizer-Free Byte-Level Models

Tokenizer-free models drop the fixed vocabulary of word-pieces and operate directly on raw bytes, letting one model handle any language, code, or even noisy…

2 min readRead
Language AI

Function Vectors and Task Representations

Function vectors are compact directions inside a language model's hidden states that encode an entire task, like 'translate to French' or 'return the antonym.

2 min readRead
Language AI

Best-of-N Sampling and Reranking

Best-of-N sampling generates several candidate answers from a model and then picks the best one using a separate scoring step.

2 min readRead
Audio AI

StyleTTS 2 Style Diffusion

StyleTTS 2 is a text-to-speech model that treats voice 'style' — prosody, emotion, and speaker timbre — as a random variable sampled with a diffusion model…

2 min readRead
Audio AI

FastPitch Pitch-Controllable TTS

FastPitch is a fast, non-autoregressive text-to-speech model that explicitly predicts the pitch (fundamental frequency) of every input token, letting you…

2 min readRead
Audio AI

Voicebox Flow-Matching Speech Generation

Voicebox is Meta's text-guided speech generation model trained with a flow-matching objective to 'fill in' masked audio, letting one model do zero-shot voice…

2 min readRead
Technical

SmoothQuant and Activation Quantization

SmoothQuant is a technique that makes it possible to compress large language models down to 8-bit integers for both weights and activations without…

2 min readRead
Technical

Structured Pruning and Layer Dropping

Structured pruning removes whole components of a neural network, such as attention heads, neurons, or entire layers, so the slimmer model runs faster…

2 min readRead
Technical

Speculative Streaming and Multi-Token Prediction

Speculative streaming and multi-token prediction speed up language model generation by guessing several future tokens at once and verifying them in a single…

2 min readRead
Companies

OpenAI GPT-4.5 and GPT-5

GPT-4.5 and GPT-5 are OpenAI's flagship large language models that power ChatGPT and its API.

2 min readRead

Finished reading? Prove it.

Check what you learned with topic quizzes, then explore our structured courses and current certification requirements. Core guides remain free to read.