Week 1: Foundations

Day 6: Hallucinations and Verification

Day 6 of 2815 minGoal - Learn - Example - Practice - Checkpoint

Goal

Understand why AI can sound confident while being wrong.

Learn

A model predicts likely output. It does not automatically know whether every sentence is true. Hallucination risk rises when the task asks for obscure facts, legal/medical/financial claims, citations, current events, or private details the model cannot access. Verification means checking source documents, official pages, calculations, or direct evidence.

Behind the scenes

AI tools are products wrapped around models, data, prompts, retrieval, safety systems, and user interfaces. The better you understand the wrapper, the better your results get.

Example

Example: in a real workflow, this idea helps you decide how to use AI carefully. For this lesson, connect the goal to one task you already do: understand why AI can sound confident while being wrong..

Practice

Ask a chatbot for three facts about a current product, then verify against the official product page. Mark what was right, vague, or wrong.

Checkpoint

You know when to trust AI as a draft versus when to verify.

PreviousDay 5 CourseAI Overview NextDay 7