News for hackers. Stuff that matters.
Re:When ChatGPT summarises, it does nothing of the kind by sitkack on Sunday July 21, 2024 @06:16PM (#41028733)
Without this detail, the whole body of work is anecdotal.
Re:When ChatGPT summarises, it does nothing of the kind by gctwnl on Sunday July 21, 2024 @06:30PM (#41028862)
Definitely. Otherwise it would have required a lot more than a single blog post. It is an observation, not anything rigorous with a large number of examples, and decent statistics.
Re:When ChatGPT summarises, it does nothing of the kind by sitkack on Monday July 22, 2024 @12:49AM (#41031007)
It doesn’t require a whole more. 1) the full transcript of the llm exchange and 2) version numbers for the llm would go a long way.

It is basically a long winded way of saying in a bug report, “it doesn’t work”.

Re:When ChatGPT summarises, it does nothing of the kind by benreesman on Sunday July 21, 2024 @06:26PM (#41028821)
To be fair, most of the commentary on both sides of the LLM conversation are pretty anecdotal, which is increasingly looking like a structural problem given that any solid evidence goes in the training set in about an hour.