AI will hand you a confident, well-written answer even when it’s completely made up, and it will never tell you it doesn’t know.

In this lesson, you’ll learn:

• Spot why AI hallucinates: it predicts the next likely word instead of checking facts, and always picks the answer that sounds most believable
• Recognize the three hallucination triggers: auto-predicting when unsure, the cascade effect where one small early error snowballs through a long conversation, and sycophancy where AI agrees with you even when you’re wrong
• Catch red flags in AI answers, like missing or fake citations, outdated details, and responses that flatter instead of giving you a hard truth
• Build safer habits: ask AI to flag data gaps instead of asking “is this correct,” use retrieval tools like NotebookLM and Perplexity for factual work, and request a hand-off document to keep long conversations accurate