This whole article about who can and can't detect AI writing is fascinating!
The average person essentially does no better than chance, but a panel of 5 people who use AI for writing every day got only 1 in 300 wrong.
The screenshot describes how they look at the […] https://zirk.us/@grammargirl/114495485010114243
The average person essentially does no better than chance, but a panel of 5 people who use AI for writing every day got only 1 in 300 wrong.
The screenshot describes how they look at the […] https://zirk.us/@grammargirl/114495485010114243
Comments
Researchers could get a lot more attention if they made a fun test for people to try— although such a test would quickly be outdated.
I don’t feel confident in spotting AI I just know its weaknesses I think a bit more than most people. A little.
i noticed several websites - one which dealt exclusively with science news - which were AI-generated, because the headlines often didn't match the expectations of the content. also, the AI-generated websites were very often quite redundant - presented the same […]
I want to do a test so bad!
Thank you for posting!
So the conclusion is that if you want to spot AI generated text you need to use and be familiar with AI generated text.
As a parent of teenagers I can attest to this. Since the advent of LLMs I have encouraged them to explore and understand them. After all, according to the local […]
TLDR; You can tell the text is written by #AI because it's written better than a human generated text.
Humans: The source of inaccurate data since Sumer civilisation 6000 years ago.
This really doesn't make much sense to me. You can always tell AI because it doesn't convey much, if any, factual information, but simply blabbers.
Why are they comparing a panel of 5 experts to individual non-experts; that's not fair.
I think someone who does no better than […]