AI Foundations
Understand what AI is, how systems learn, where they fail, and how to judge claims without hype.
Free AI library
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.
Start her
Each course includes explicit outcomes, mapped competencies, practice activities, and an applied capstone.
Understand what AI is, how systems learn, where they fail, and how to judge claims without hype.
Use AI productively while protecting privacy, checking outputs, and preserving human accountability.
Evaluate workplace use cases, run safe pilots, measure value, and communicate changes responsibly.
Analyze AI systems through rights, equity, governance, safety, and public-interest outcomes.
Understand language models, retrieval, agents, evaluation, cost, and deployment safeguards through practical system design.
Topic tracks
Jump into the area you care about. Every track has multiple plain-English guides.
Full library
155 av 1019 guides shown. Filter by track or search above.
LLM evaluation measures a language model or application against defined tasks and failure conditions.
Språk AIModel Context Protocol, or MCP, defines a common interface through which an AI host can connect to servers offering tools, resources, and prompts.
Språk AITool calling lets a model request an operation through a defined interface.
Språk AIAI summarization creates a shorter representation of source material.
Språk AIRetrieval quality measures whether a search system returns useful evidence for a query and places it where a reader or downstream model can use it.
Språk AIStructured outputs organize model responses into a defined shape, such as a JSON object validated against a schema.
Språk AIA multilingual language model works with more than one language using shared learned representations.
Språk AIReverseringsforbannelsen er en overraskende feilmodus der en språkmodell som lærer 'A er B' ikke kan svare pålitelig 'B er A.
Språk AI"Tapt i midten"-effekten er språkmodellers tendens til å bruke informasjon best når den vises i starten eller slutten av en lang inndata...
Språk AIEmergent evner er ferdigheter som plutselig dukker opp i store språkmodeller når de passerer en viss skala, selv om mindre modeller ikke viste noen tegn til dem.
Språk AIKontrastiv dekoding genererer tekst av høyere kvalitet ved å trekke tendensene til en liten, svak språkmodell fra tendensene til en stor, sterk.
Språk AIBegrenset strålesøk tvinger utdataene til en språkmodell til å tilfredsstille harde krav, som å inkludere spesifikke ord eller matche en grammatikk, samtidig som...
Check what you learned with topic quizzes, then explore our structured courses and current certification requirements. Core guides remain free to read.