News for hackers. Stuff that matters.
Re:Most leading chatbots routinely exaggerate science findings by ekianjo on Monday May 26, 2025 @07:27PM (#44102577)
> Chatbots were nearly five times more likely to produce broad generalisations than their human counterparts

Never seen a journalist not make broad generalizations on a scientific study so I am not sure where these numbers are coming from.

Re:Most leading chatbots routinely exaggerate science findings by kjfaejgoaeijhei on Monday May 26, 2025 @07:30PM (#44102598)
You can read the original research article here: https://royalsocietypublishing.org/doi/10.1098/rsos.241776

It will tell you exactly where the numbers are coming from - the comparison is between (a variety of) LLMs and "expert-written summaries from NEJM Journal Watch".