Free AI library

Language AI guidesFree forever.

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

155Free guides
1Topic tracks
~2 minPer guide
~5hReading 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

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

Language AI

Minimum Bayes Risk Decoding

Minimum Bayes Risk (MBR) decoding picks the output that is most similar to many other likely outputs, rather than the single highest-probability one.

2 min readRead
Language AI

Typical Sampling

Typical sampling is a text-generation method that picks the next word from tokens whose information content sits close to the model's expected surprise…

2 min readRead
Language AI

Mirostat Perplexity Control

Mirostat is a decoding algorithm that actively steers a language model's output toward a target perplexity (a set level of surprise) using a feedback loop.

2 min readRead
Language AI

Sycophancy in Language Models

Sycophancy is the tendency of AI language models to tell users what they want to hear, agreeing with stated opinions or caving to pushback even…

2 min readRead
Language AI

Speculative Sampling Verification

Speculative sampling speeds up large language model generation by letting a small 'draft' model guess several tokens ahead, then having the big model verify…

2 min readRead
Language AI

Entropy-Based Sampling

Entropy-based sampling adapts how an LLM picks its next token based on how uncertain the model is at that moment.

2 min readRead
Language AI

ELECTRA Pretraining

ELECTRA is a more efficient way to pretrain language models by teaching them to spot fake words instead of guessing hidden ones.

2 min readRead
Language AI

RoBERTa Training Recipe

RoBERTa showed that BERT was significantly undertrained: by tuning the recipe rather than the architecture, it set new benchmark records.

2 min readRead
Language AI

XLNet Permutation Modeling

XLNet blends the bidirectional context of BERT with the autoregressive prediction of GPT by training over random word orderings.

2 min readRead
Language AI

Tree of Thoughts

Tree of Thoughts (ToT) is a prompting framework that lets a language model explore multiple reasoning paths in parallel, like branches of a tree, instead…

2 min readRead
Language AI

Self-Consistency Decoding

Self-consistency is a decoding strategy that samples many different reasoning paths from a language model and then picks the answer most of them agree on.

2 min readRead
Language AI

Odds Ratio Preference Optimization

Odds Ratio Preference Optimization (ORPO) is a fine-tuning method that teaches a language model good behavior and human preferences in a single training pass.

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.