The AI Can Be Wrong

Part of the Fundamentals section of Coddy's AI Prompts journey — lesson 5 of 23.

Here's a critical lesson: AI can confidently give you wrong information. This phenomenon is often called a "hallucination."

Remember, AI generates text by predicting what words should come next. It doesn't fact-check itself. It doesn't know what's true—it only knows what sounds plausible.

So when you ask about a historical date, a scientific fact, or a person's biography, the AI might produce something that reads perfectly but is completely made up.

For example, if you ask:

Who wrote the novel "The Winds of Tomorrow"?

The AI might confidently name an author, describe the plot, and even mention the publication year—for a book that doesn't exist. It's not lying; it's generating text that fits the pattern of how such questions are typically answered.

This is why you should never blindly trust AI output, especially for facts, statistics, quotes, or anything you plan to use in important work. Always verify critical information from reliable sources.

Challenge

Ask the AI: "Tell me about the famous scientist Dr. Elmsworth Quigley and his discoveries."

Dr. Elmsworth Quigley doesn't exist. But watch what happens — the AI will confidently tell you all about "him" anyway.

The response must:

Contain the name Quigley (showing the AI played along)
Contain the word discovered or discovery or invented or research (showing it made up achievements)
Not contain the words don't know, doesn't exist, not real, no record, or fictional, (proving the AI didn't catch the trick)

What just happened? The AI didn't lie on purpose. It has no idea what's real or fake. It just generated text that sounds like a plausible answer about a scientist. This is called a hallucination — and it's why you should always verify AI output.

Cheat sheet

AI generates text by predicting what words should come next based on patterns, not by knowing what is true. This means AI can confidently provide incorrect information, a phenomenon called a "hallucination".

AI doesn't fact-check itself—it only produces text that sounds plausible. When asked about facts, dates, people, or events, it may generate completely fabricated information that reads convincingly.

Always verify critical information from reliable sources. Never blindly trust AI output for facts, statistics, quotes, or anything used in important work.