logoalt Hacker News

MrBuddyCasinoyesterday at 6:44 PM1 replyview on HN

Yes you have to continuously tune the prompts ever so subtly. 3.5 is a lot better than than 3.1 tho.

Important to remember that json schema instructions take precedence over the normal prompt, so move as much into property descriptions as possible.


Replies

ComputerGuruyesterday at 7:35 PM

This was 3.5 flash lite, actually, and after prompt tuning. It was very clearly an issue that correlated with input (JSON array) size, the more elements in the batch, the higher the error rate.

3.0 flash (not lite) handled it like a champ though, fwiw.