Gen AI Lingo

Your next step

How an answer is made

Why answers vary, and why plausible details can be invented.

Start learning

What you’ll learn

  1. New text is not always a found answer

    Distinguish creating a response from retrieving a document.

    About 4 minutes · Open activity

  2. A language model works with language patterns

    Recognize the role of a language model in text tasks.

    About 4 minutes · Open activity

  3. Text grows a piece at a time

    Use a simplified sequence to explain common language-model generation.

    About 4 minutes · Open activity

  4. The same request can vary

    Expect output variation without assuming one sample defines a tool.

    About 4 minutes · Open activity

  5. Plausible details can be invented

    Recognize fabricated names, quotes or references as possible output errors.

    About 5 minutes · Open activity

  6. Training information can be old

    Distinguish learned information from current retrieved information.

    About 4 minutes · Open activity

  7. Explain a surprising answer

    Identify a generated rather than retrieved answer, flag an invented reference, and choose current evidence for a recent change.

    About 5 minutes · Open activity