Copyright 2026 © Nabil Samari
I use AI at work daily. And I've noticed it makes things up to be safe. It claims to know, even when it's just guessing.
This is called hallucination. AI produces text that sounds convincing, is well-reasoned, and grammatically perfect — but wrong. It doesn't lie intentionally. It has no intent. It's just doing its best at what it was trained to do: predict the next word.
In this post, I'll explain what the phenomenon is, why it happens, and how you can reduce it. I've dug into Anthropic's own materials, industry research, and my own experience.
Why Does This Happen?
AI doesn't think like a human. At its core, it's an extremely advanced next-word predictor. It has read billions of pages of text from the internet, books, and documents, and learned which words typically follow each other.
When you ask it something, it doesn't "check a fact database" for the answer. It doesn't open Wikipedia. It looks at its own parameters and guesses the most likely continuation.
This works well when the topic is common and there's plenty of data. But when you ask about a niche subject, a rare name, or an exact statistic, the model has to guess. And because it's been trained to be helpful, it would rather invent an answer than say "I don't know."
How to Spot a Hallucination
AI hallucination is dangerous precisely because it looks like the right answer. It doesn't write "uh, dunno" — it provides a detailed, well-structured explanation. I've noticed that hallucination often only becomes apparent when:
- I ask for source citations. AI might invent research papers that sound credible but don't exist.
- I ask the same question again in a different way. If the answer changes significantly, it's not confident on the topic.
- I ask for overly specific or niche information. AI is generally good at general knowledge but weak on rare specifics.
How to Reduce Hallucination in Practice
I've learned a few concrete methods that work:
Give permission to say "I don't know." If you say in your prompt "If you're not sure, say you don't know," the AI will do so surprisingly often. It removes the pressure to fabricate an answer.
Ask for direct quotes. When working with long documents, first ask it to extract exact quotes, and only then analyze based on them. This forces the AI to stay within the given material.
