Unless the update is splitting cells. > Turns out, a simple table from Wikipedia... | Hacker News

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

melenaboija on Sept 3, 2024 | parent | context | favorite | on: Web scraping with GPT-4o: powerful but expensive

Unless the update is splitting cells.

> Turns out, a simple table from Wikipedia (Human development index) breaks the model because rows with repeated values are merged

sebstefan on Sept 3, 2024 [–]

Nah, still correct :-) that would break the regular scraping as well

>The LLM is resistant to website updates that would break normal scraping

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