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.

Applications

AI in Colorizing Historical Photos and Film

AI colorization adds plausible, realistic color to black-and-white photos and film by predicting hues from grayscale patterns.

2 min readRead
Applications

AI in Document Restoration and Manuscript Recovery

AI helps recover damaged, faded, or ancient documents by enhancing faint ink, reconstructing missing text, and even reading scrolls too fragile to open.

2 min readRead
Audio AI

MelGAN Generative Vocoder

MelGAN is a fully convolutional GAN-based vocoder that turns mel-spectrograms into raw audio waveforms in a single fast forward pass.

2 min readRead
Audio AI

UnivNet Multi-Resolution Vocoder

UnivNet is a GAN vocoder that judges generated audio using multiple spectrograms computed at different STFT resolutions, sharpening high-frequency detail.

2 min readRead
Audio AI

DiffWave Diffusion Vocoder

DiffWave is a diffusion-based vocoder that synthesizes audio by iteratively denoising random noise into a waveform, conditioned on a mel-spectrogram.

2 min readRead
Fundamentals

Length Normalization in Preference Optimization

Length normalization adjusts preference-tuning objectives so models stop winning approval just by writing longer answers.

2 min readRead
Technical

Speculative RAG and Retrieval-Augmented Drafting

Speculative RAG speeds up and sharpens retrieval-augmented generation by having a small, fast model draft multiple candidate answers from retrieved…

2 min readRead
Technical

Block-Sparse and Native Sparse Attention

Block-sparse and native sparse attention let transformers attend to only the most relevant chunks of a long sequence instead of every token, slashing…

2 min readRead
Society

Model Extraction and Stealing Attacks

Model extraction attacks let an adversary clone a proprietary AI model just by querying its public API and training a copycat on the answers.

2 min readRead
Technical

Watermarking Language Model Outputs

Watermarking embeds a hidden statistical signal into AI-generated text so it can later be detected as machine-written, without changing what a human reader…

2 min readRead
Fundamentals

Bradley-Terry Reward Modeling

The Bradley-Terry model is a century-old statistical method for turning pairwise comparisons (A beats B) into numeric scores.

2 min readRead
Society

Reward Hacking and Specification Gaming

Reward hacking is when an AI maximizes its reward signal in unintended ways instead of doing what designers actually wanted.

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.