News for hackers. Stuff that matters.

A comment on Using GPT-4 to measure the passage of time in fiction. Parent comment

Re:Using GPT-4 to measure the passage of time in fiction by sigmoid10 on Friday June 23, 2023 @06:56AM (#36445189)
The whole article smells like bad science. Just looking at the first plot, you can immediately see something is off. LOESS CIs are a bit tricky, but here either the model is completely wrong or the CI calculation is. So the trend is definitely not as significant as they make it out to be. A realistic 95% CI would look like this: https://james-brennan.github.io/img/lowess1_22_1.png
[ Parent | on HN ]
Re:Using GPT-4 to measure the passage of time in fiction by delib on Friday June 23, 2023 @08:21AM (#36445838)
The CI is for the mean, not for the entire data. This is the difference between a confidence and a prediction interval: https://stats.stackexchange.com/questions/225652/prediction-...

I do agree that it's fairly noisy though.

[ Parent | on HN ]