AI
Systems that use learned patterns to predict, classify or generate outputs.
A plain-English glossary and carefully attributed sources to keep close by.
Systems that use learned patterns to predict, classify or generate outputs.
AI that produces text, images, audio or other new outputs from learned patterns.
Adjusting model parameters using examples.
Using a trained model to produce an output.
A chunk of text processed by a model; it can be part of a word.
The limited amount of input and output a model can work with at once.
A generated claim or reference that is unsupported or false.
Connecting an answer to supplied or retrieved evidence. It still needs checking.
Untrusted content that attempts to redirect a system or its tools.
Removing or replacing sensitive information, including identifying context.
A system that can select steps or tools towards a goal within set boundaries.
Designing retries so the same request does not create duplicate effects.
A responsible person checks outputs and approves consequential actions.
A systematic skew that can produce unfair or misleading outputs.
An output following a specified format or schema; accuracy still needs validation.
External resources are optional. Their content, availability and accessibility may change. Our original written lessons cover the learning objectives without third-party videos.
The original publisher 3Blue1Brown is a candidate for supplementary technical explanations. Playback, captions, duration and embedding could not be verified from this environment. No unverified provider IDs are embedded. Editorial review is required before adding a video verified for playback in lessons. Candidate source links and review notes are available beside the relevant written lessons.