The game is simple:
Two photos side by side
One’s made by a human, one’s made with AI
Pick the AI one
See if you’re right (plus the source/prompt)
20/20.
The nature shots were harder than shit that had man-made things or people in them. But also, the resolution of each pairing being dramatically different kinda gave a pattern to which one would be which.
78%, not bad. Anything with no people or animals are always harder to spot, especially with how small the pictures are. I want to try one with with bigger pictures and people prominently featured.
Nice try but I’m not doing QA checks for generative AI slop.
It seems like a reply to the wrong point.
I’m not saying most people can tell the difference. If they can now, they won’t soon. My issues with AI are about training on people’s work and then killing their jobs. Also destroying the environment, and other issues.
- Reality Check #1 18/20
- Perfect Streak: 13
I can spot AI images 90% of the time.
fuck that UI. tapping to select and zoom below is odd. I messed up a few and exited.
The swipe to move to the next slide was so similar to the swipe backwards, I exited twice and gave up.
Skill issue /s
Those images are very AI-easy IMO. No crowds or complex images.
Plot twist: they were all AI generated.
That’s what I would do if I would create such a test. But I would add the option “can not decide” to keep it a bit more fair.
🤖 Reality Check #1 19/20 🔥 Perfect Streak: 18
I can spot AI images 95% of the time. 🧠 Can you beat me? realitycheckk.com
The one pic with the pink flower and water bubbles under water really put me off
Yep that got me too. Those lily pads looked very unlikely
This is literally us giving them training data for AI to identify what pictures look like AI…
Which in turn is training data to help AI make better pictures
🤖 Reality Check #1 18/20 🔥 Perfect Streak: 10
I can spot AI images 90% of the time. 🧠 Can you beat me? realitycheckk.com
Am dumb?
🤖 12/20 🔥 Perfect Streak: 4
I can spot AI images 60% of the time. 🧠
Got up to 11 myself before I lost it.
Just me not reading any directions till 3 in, I thought I was picking the real one at first
It looks too perfect and kinda slimy so that’s how I know.
Is this site just going to use the results to train AI to generate better fake imagery?
I don’t think much training can be done on 20 pictures
70%. I noticed that the more I tried to dissect it, the worse I was. I was far more accurate taking a quick glance at both and making a decision after like 5 seconds.
Interesting, I was kinda the opposite. I got 80% looking very carefully at each pair.
Just like multiple choice quizzes, go with your first guess if unsure.
