HOW TO Spot AI Trickery in Images

Sunday newspapers once featured fun “spot the difference” puzzles with two similar images. That same careful eye is now essential in the AI era to avoid falling for manipulated images.

Here’s a practical checklist based on a New York Times article to tell if a photo is an AI fake:

1. Check the perspective - Look at lines that should run straight into the distance (like floor tiles or walls). Do they bend, warp, or point in different directions?
2. Watch for prompt keywords - Scan for brand names, place names, or other words from the original prompt that appear in strange or overly prominent places.
3. Zoom in on small text - Big letters may look fine, but smaller writing often turns into gibberish. Also look for odd soft shadows on the characters.
4. Examine how objects connect - Does a strap actually attach to a badge? Do skin tones match between a person and the photo on their ID? AI often fails at real physical relationships.
5. Read the text carefully - Even sharp, pixel-perfect text can be nonsense. Check if slogans or labels actually make sense when you read them closely.
6. Look for missing real-world knowledge - Are there incorrect, made-up, or non-standard symbols, signs, or details that someone with specialized knowledge would notice as wrong?
7. Hunt for quieter logical mistakes - Look for small oddities that don’t add up. These subtler errors are what experts often use to confirm a fake.

A.I. image generators once struggled to replicate human features, haphazardly attaching six- and seven-fingered hands to arms that bent at inhuman angles. Those glaring errors have largely disappeared, making today’s fakes far harder to detect at a glance.

As AI image generators continue to improve, the most obvious giveaways will keep fading. 

Use this checklist regularly, stay curious about the details that don’t quite add up, and remember that no single sign is definitive on its own.