News for hackers. Stuff that matters.

A comment on Some signs of AI model collapse begin to reveal themselves.

Re:Some signs of AI model collapse begin to reveal themselves by Urahandystar on Tuesday May 27, 2025 @09:28AM (#44106784)
The example in the article seems less like a RAG issue and more like a prompt issue. The fact that LLM's seeming can't disappoint the user and have to assume they are correct is what is leading to the misinformation in articles like this.

That said there is a clear vulnerability in LLM's not being able to judge whether information is true or not especially when pulling from the web.

[ Parent | on HN ]
Re:Some signs of AI model collapse begin to reveal themselves by old_man_cato on Tuesday May 27, 2025 @09:34AM (#44106847)
"Prompt issue" is just the new "user error". Just passes the blame anywhere other than the flawed value of the tool itself.
[ Parent | on HN ]