Comment by MrBuddyCasino
19 hours ago
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.
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.