Anybody else facing issues with inconsistency with openai models? I've been using the sub question query engine and it was supposed to route questions to different tools, but this morning it started routing all queries only to one tool only despite not having changed the prompt or data
they 100% change the underlying model without telling anyone (at least, that's the only way I can explain it, the performance definitely fluctuates over time)
Ok let me try that! Its so frustrating that everytime things change under the hood, we have to make changes to the prompts or descriptions 😡 Sometimes we might not even get back the same level of performance as before 😭
