logoalt Hacker News

jeltzlast Sunday at 11:53 AM2 repliesview on HN

Yes, I have. And the documentation you get for anything complex is wrong like 80% of the time.


Replies

embedding-shapelast Sunday at 2:54 PM

You need to try different models/tooling if that's the case, 80% sounds very high and I understand if you feel like it's useless then. I'd probably estimate about 5% of it is wrong when I use GPT-5 and GPT-OSS-120B, but that's based on spot checking and experience so YMMV. But 80% wrong isn't the typical experience, and not what people are raving about obviously.

NewsaHackOlast Sunday at 4:31 PM

80% of the time? Are you sure you aren't hallucinating?