"Truth doesn't shout. But it leaves clues for those willing to look."
By the end of this Beacon, you'll know when to trust AI — and when to double-check. You'll also learn how to use Perplexity and your favorite chatbot to verify information quickly.
AI tools can state something incorrectly — and sound completely confident while doing it. This is called a hallucination. The AI doesn't know it's wrong. It's not lying — it just fills in gaps with plausible-sounding information.
AI tends to struggle most with: recent events, specific numbers and statistics, quotes and sources, and local or niche information.
With Perplexity: Take any surprising claim and ask: "Is it true that [claim]? Please show me your sources."
With any AI tool: Ask: "How confident are you in this answer?" or "Are there any parts of this you're not sure about?" Many AI tools will flag their own uncertainty when you ask directly.
Step 1 — Get a claim
Pick one that surprises you — or one you're not sure about.
Step 2 — Check it with Perplexity
Look at what Perplexity says about the fact you picked. Did it confirm it, contradict it, or offer a more nuanced version?
Notice that the AI's original answer might have been almost right — correct in general, but off on a specific detail. That's the gap worth watching: AI often gets the big picture right but slips on the fine print.
Think of AI like a very well-read friend. They know a lot. They're helpful and quick. But they're not always right. For anything that affects your health, finances, legal situation, or that you plan to share publicly — always verify with a trusted source.
You now know how to be a critical AI user — not just a passive one.
Up next — Beacon 9: Summarize the World. You'll learn how to take any long document and get the key points in minutes.
No rush. Come back whenever you're ready. 🙂