logoalt Hacker News

Tiberiumyesterday at 12:59 PM4 repliesview on HN

You can easily do this with normal GPT 5.2 in ChatGPT, just turn on thinking (better if extended) and web search, point a Wikipedia page to the model and tell it to check the claims for errors. I've tried it before and surprisingly it finds errors very often, sometimes small, sometimes medium. The less popular the page you linked is, the more likely it'll have errors.

This works because GPT 5.x actually properly use web search.


Replies

nottorpyesterday at 1:09 PM

Have you verified those errors?

show 1 reply
mort96yesterday at 5:53 PM

Can you describe some of the errors you have found this way?

show 1 reply
sgcyesterday at 3:59 PM

I am sure that could be useful with proper post-request research.

As a technique though, never ask an LLM to find errors. Ask it to either find errors or verify that there are no errors. That way it can answer without hallucinating more easily.

show 1 reply
multjoyyesterday at 2:14 PM

It says it finds errors.

show 1 reply