Hacker News new | ask | show | jobs
by verbify 384 days ago
How do you know it isn't hallucinating? My experience of AI is that it can be very convincing and produce information that "looks right".
1 comments

I mostly use it in fields where its claims are easily verifiable.
So then it's no different from reading a Wikipedia page about a topic? I mean, if you only use it to teach you stuff you can verify, then couldn't you skip one step in this process?
I learned Stochastic Differential Equations this way, for instance. I wasn't going to learn that so quickly from Wikipedia.

https://chatgpt.com/share/6834ed85-4dac-800e-b940-3b9a5f13d6...

It's definitely more involved than the Wikipedia article. How do you confirm what it's saying is true?
I just keep asking it questions until I hit a level of detail I can verify with my own mathematical understanding.
Ah okay, so it's used to summarize data about a topic in a field you understand well