The whole article smells like bad science. Just looking at the first plot, you c... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		sigmoid10 on June 23, 2023 \| parent \| context \| favorite \| on: Using GPT-4 to measure the passage of time in fict... 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

delib on June 23, 2023 [–]

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.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact