Re:AI fabricates 21 out of 23 citations lawyer sanctioned re...
by amilios on Sunday September 14, 2025 @03:43AM
(#45238231)
Plenty of progress in models that can use tools and search. Would love to see how one of these tool/search-enabled models do at this kind of a task. In my experience, they don't fabricate things anymore, just sometimes occasionally misrepresent the content of citations (put a citation somewhere where it doesn't actually support what is written).
[ Parent
| on HN ]
Re:AI fabricates 21 out of 23 citations lawyer sanctioned re...
by delichon on Sunday September 14, 2025 @05:15AM
(#45238580)
A few days ago I asked GPT 5 for links to news on the Charlotte murder before the story got reported by the mainstream media. It gave me five different links, including AP and Reuters. Every one, five out of five, was a hallucination.
Re:AI fabricates 21 out of 23 citations lawyer sanctioned re...
by splix on Sunday September 14, 2025 @08:54AM
(#45239453)
I'm wondering how did you ask for the links?
It supposed to search for actual documents and then process them (extract content, summarize, giving you the links, and so on).
Re:AI fabricates 21 out of 23 citations lawyer sanctioned re...
by watwut on Sunday September 14, 2025 @09:36AM
(#45239670)
It hallucinated complete documentation to the tech we asked it about just 2 weeks ago. Completely made up documentation with only vague relationship.to how it really works.
Re:AI fabricates 21 out of 23 citations lawyer sanctioned re...
by vinni2 on Sunday September 14, 2025 @11:10AM
(#45240352)
I asked GPT-5 for updated literature survey for a paper I was writing with search enabled and explicit asked to use google scholar arxiv etc and yet most papers were non existent and in some cases even pointed to some GitHub repos which were private.