News for hackers. Stuff that matters.
Re:Detect ChatGPT Generated Content by krisoft on Saturday January 28, 2023 @08:26AM (#34557400)
This is useless. I have tried it with 4 different samples and it made mistakes with each.

- it thinks AI wrote parts of my handwritten texts

- King James Genesis 29 is appearantely fully AI written

- a wall of text copied straight from chatgpt? Only partially AI written.

- second chapter of Harry Potter? AI written parts

In fact I could not find a sample yet which was not AI written at least partially according to this.

Re:Detect ChatGPT Generated Content by krisoft on Saturday January 28, 2023 @08:35AM (#34557451)
The GNU preamble is entirely AI written. According to this tool. To be honest I always suspected Stallman. :)
Re:Detect ChatGPT Generated Content by _just7_ on Saturday January 28, 2023 @08:30AM (#34557427)
The only way I could get it to say something was completely written by a human, was by adding spelling mistakes
Re:Detect ChatGPT Generated Content by bhickey on Saturday January 28, 2023 @09:07AM (#34557640)
Agreed. This is useless. I asked GPT-3 to write a HN post decrying GPTZero:

> GPTZero is absolute trash! It can't even detect plagarism correctly. It's a complete joke and waste of time! Don't bother with it! You'd be better off just manually checking for plagiarism. It's so unreliable it's not even worth mentioning. Just save yourself the time and money and don't bother with GPTZero. Worst AI tool ever!

GPTZero classified it as fully human written. This is a cat and mouse game where the mouse is always going to lose.

Re:Detect ChatGPT Generated Content by programmarchy on Saturday January 28, 2023 @09:14AM (#34557682)
Agree with you, but! In a Tom and Jerry episode, Tom Cat would be GPTZero and Jerry Mouse would be GPT3 ;)
Re:Detect ChatGPT Generated Content by hutzlibu on Saturday January 28, 2023 @09:58AM (#34558014)
It is hilarious comedy, though.

The sad part is, that real people will likely suffer, when people with power take salespersons serious and use stuff like that to "detect" and punish frauds.

Re:Detect ChatGPT Generated Content by dvngnt_ on Saturday January 28, 2023 @09:36AM (#34557826)
how mad would you be if someone accused you of using AI to write something but you actually did write it
Re:Detect ChatGPT Generated Content by kcplate on Saturday January 28, 2023 @10:32AM (#34558359)
Same, ran a few samples and it was wrong every time. My hope is that teachers will run some tests before just willy-nilly trusting the scores it gives and start accusing students, but sadly I know a lot of teachers and I bet within that group few will run their own tests and will just accept it as authority.
Re:Detect ChatGPT Generated Content by ren_engineer on Saturday January 28, 2023 @10:39AM (#34558414)
it's a toy project built by a CS undergrad student over their winter break that went viral because journalists desperately want something that can expose AI writing. It's built on streamlit and a few glued together libraries, not really surprising the results aren't good. It's not some state of the art custom tool but they are marketing themselves as the solution to solving academic plagiarism