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.

Companies

Salesforce Einstein

Salesforce Einstein is the AI layer built into Salesforce's customer relationship management (CRM) platform, adding predictions, recommendations…

2 min readRead
Technical

FP8 and Low-Precision Formats

FP8 is an 8-bit floating-point number format that lets AI models store weights and run math using a quarter of the memory of standard 32-bit numbers.

2 min readRead
Technical

PagedAttention and vLLM

PagedAttention is a memory-management technique that stores a language model's attention cache in small reusable blocks instead of one big contiguous chunk.

2 min readRead
Technical

Continuous Batching

Continuous batching is a serving technique that adds and removes requests from a running batch token-by-token, instead of waiting for a whole fixed batch…

2 min readRead
Audio AI

Neural Vocoders

A neural vocoder is a model that turns a compact acoustic representation, usually a mel-spectrogram, into an actual audible waveform.

2 min readRead
Audio AI

Neural Audio Codecs

Neural audio codecs use deep learning to compress sound into tiny streams of discrete tokens and reconstruct it with high fidelity.

2 min readRead
Audio AI

VALL-E and Codec Language Models

VALL-E reframed text-to-speech as a language modeling problem over audio codec tokens, enabling voice cloning from just three seconds of a sample.

2 min readRead
Language AI

FlashAttention

FlashAttention is a memory-efficient algorithm that computes the exact same attention as standard transformers but without ever writing the giant attention…

2 min readRead
Language AI

Grouped-Query Attention

Grouped-Query Attention (GQA) is a way to shrink the memory needed during text generation by letting several query heads share the same key and value heads.

2 min readRead
Language AI

Rotary Position Embeddings

Rotary Position Embeddings (RoPE) encode where each token sits in a sequence by rotating its query and key vectors by an angle proportional to position.

2 min readRead
Companies

Hume AI

Hume AI is a research lab and startup building 'emotionally intelligent' voice AI that reads the tone, rhythm, and prosody of human speech, not just…

2 min readRead
Companies

OpenAI Sora

Sora is OpenAI's text-to-video model that generates realistic, minute-long video clips from written prompts.

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.