News for hackers. Stuff that matters.
Re:"Certainly, here is a possible introduction for your topi... by Supermancho on Friday March 15, 2024 @10:28AM (#39716159)
Chat GPT prompt response? in the start of the second text block.
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by chankstein38 on Friday March 15, 2024 @10:33AM (#39716205)
Sure seems likely! Definitely not natural flow to start a section lol
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by jensenbox on Friday March 15, 2024 @10:31AM (#39716187)
Whoops!
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by JR1427 on Friday March 15, 2024 @10:33AM (#39716203)
Amazing!

Their citations are going to go through the roof!

[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by OJFord on Friday March 15, 2024 @10:42AM (#39716315)
And the rest of it is predictably pretty crap. I'm no subject matter expert, but it doesn't sound like it's written by one (or any academic) either, even to me.
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by elaus on Friday March 15, 2024 @10:43AM (#39716317)
Related Lemmy discussion of a similar incident from this week: https://lemmy.world/post/13128991

The relevant screenshot of the post: https://mander.xyz/pictrs/image/9d46f584-67a3-489d-92a5-c322... [An introduction of a published paper, containing the sentence "I'm very sorry, but I don't have access to real-time information or patient-specific data, as I am an AI language model."]

[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by klysm on Friday March 15, 2024 @10:46AM (#39716354)
The feedback loop has begun, next generation models will be trained on previous models outputs.
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by herodotus on Friday March 15, 2024 @10:48AM (#39716374)
Certainly, here's a comment:

It seems like you inadvertently left in a placeholder or instruction for ChatGPT within your article's introduction. While it's an understandable oversight, it's essential to thoroughly review your text before publishing to ensure such remnants are removed. This helps maintain the professionalism and polish of your work. If you need further assistance or editing help, feel free to ask!

[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by dicroce on Friday March 15, 2024 @10:49AM (#39716385)
It's not even buried in the middle!
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by madcaptenor on Friday March 15, 2024 @10:53AM (#39716431)
I'm unable to see the whole paper (although I can see the first sentence). Do the citations in that section actually cite relevant articles?
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by kloch on Friday March 15, 2024 @11:17AM (#39716702)
Scientific publishing is a total joke these days, especially for theoretical works (vs practical/experimental results).

We need a better way to sift through the mountains of make-work papers to find the stuff that actually works and is useful. Ironically, AI will probably help with that, at least until it outperforms humans at scientific discoveries itself.

[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by nerdponx on Friday March 15, 2024 @12:08PM (#39717338)
I think the really disturbing aspect to me is that no editor or reviewer flagged this. It's literally the first sentence of the paper! Did they just read the abstract and say "meh, good enough"? Were they all using AI to review the paper?
[ Parent | on HN ]
Re:"Certainly, here is a possible introduction for your topi... by yangbo on Saturday March 16, 2024 @01:39PM (#39727856)
The journal editor should run a language model to detect if the paper includes some placeholder or instruction for a language model. Unfortunately they did not.
[ Parent | on HN ]