Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Study: ChatGPT Outperforms Physicians in Quality, Empathetic Answers to Patients. Parent comment
That is definitely happening here.
https://jamanetwork.com/journals/jamainternalmedicine/fullar...
> evaluators did not assess the chatbot responses for accuracy or fabricated information
Yikes. (I do fault the researchers quite a bit for quietly slipping that little detail into a page-long "limitations" section.)
There are no comments on this comment yet.
That is definitely happening here.
https://jamanetwork.com/journals/jamainternalmedicine/fullar...
> evaluators did not assess the chatbot responses for accuracy or fabricated information
Yikes. (I do fault the researchers quite a bit for quietly slipping that little detail into a page-long "limitations" section.)