Facing inconsistent responses after yesterday fix made

For a given use-case of mine, I had formulated a prompt which also used function calling in it. This prompt was working perfectly fine until yesterday night. After the fix which was made by OpenAI due to the elevated error rate, I have noticed that the exact same prompt has stopped working. Hallucinations have increased drastically.

Is anyone aware of the reason for this? And is there any other possible solution for this?

I also am facing an issue where previously working prompts are suddenly not working as expected at all. If I send a prompt to generate exactly 1 thing, it’s suddenly generating 5 or 10 things. Also, it was previously giving me unique responses for each request, and now it’s giving me the same response like 80% of the time.