The last few days to maybe a week, I’ve been noticing a steady degradation of the responses from gpt-4. Today, for the first time using chatGPT using either 3.5 or 4, I’ve been getting spelling and grammatical errors.
I’m using the engine to write rpg campaign world material and it has started losing context, tense, and perspective regularly. I tend to use the same prompts over and over again, so I can rebuild the base campaign setting, so I really notice good days for gpt and bad days.
Outside of the objective hard errors I’ve been getting, the last couple of weeks has been especially bad on the subjective side as well. The creativity and liveliness seems to have been squashed.
I’m unsure what’s going on, but wanted to report the downtrend. It can be frustrating to use many of our 25 messages per 3 hours correcting the output. Thanks.