Since we are testers we tend to spot pattern and issues even when we do not want to 
.
So i was wondering how do you spot a text that is generated by an LLM/AI.
Please do not say I use a scanner.
For me the tells are usually these 3
* Using the prashe "In the world of"
* Using words that one does not usually use in a day to day conversation like delve
* The post is marked with emojis all the way.
What about you?
I totally relate to spotting patterns—it's a tester's instinct! Here are a few additional signs I look for when identifying text generated by an LLM or AI:
Repetitive Structures: AI-generated content often has a tendency to use similar sentence structures or phrases multiple times, which can make it feel less dynamic.
Overly Formal Language: The tone can sometimes be more formal or polished than everyday conversation, lacking the natural quirks and informalities that people usually incorporate.
Generic Examples: AI tends to use broad or generic examples, which may feel less personal or specific compared to anecdotes from human experiences.
What do you think? Have you noticed any other distinctive patterns?
No account yet? Create an account
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.