It seems as if this is based on demand. Whenever a new model is released, I'm guessing tens of thousands of us switch over to try the latest and greatest, which overloads the servers, leading to nerfing. It's 100% dishonest, but they realized they would lose users a lot quicker if they were honest and just said "our models are overloaded, come back later".
After Fable launch I switched over to Codex and it was simply amazing, with frequent usage resets that seemed never ending. They clearly had more compute than they knew what to do with. Post Astra, Codex has gotten dumb again across all models, increased usage for no real reason, and no resets.
I'm guessing Opus 5.5 will take the heat off Codex for a bit, leading to better performance. So I guess I stick around here instead of switching again?
If servers/resources are overwhelmed it should result in slower responses not degraded quality, or at least have an option for the user to chose from. I'd almost always prefer to wait than get broken or poor results. Even a warning would help, I'd at least not waste my time.
It's absolutely based on demand: If you increase the number of experiments, you also increase the number of statistically significant-looking results. See also: https://xkcd.com/882/
After Fable launch I switched over to Codex and it was simply amazing, with frequent usage resets that seemed never ending. They clearly had more compute than they knew what to do with. Post Astra, Codex has gotten dumb again across all models, increased usage for no real reason, and no resets.
I'm guessing Opus 5.5 will take the heat off Codex for a bit, leading to better performance. So I guess I stick around here instead of switching again?