Comment by johnnyApplePRNG
10 hours ago
The average programmer is outraged by OpenAI's methods, too.
I don't care how good Astra or any subsequent models they may release might be... I am never going back to those token reset shenanigans.
10 hours ago
The average programmer is outraged by OpenAI's methods, too.
I don't care how good Astra or any subsequent models they may release might be... I am never going back to those token reset shenanigans.
The reset stuff is incredibly tiresome. We all know that it's all built into an internal number they are tracking (just like e.g. company benefits that are just part of your compensation calculation), and all it does is obscure the value the subscription provides and make planning impossible. It's the poorest service experience I can remember having, ever.
Gotta get a few sparks or an m5ultra and run local
What are the token reset shenanigans?
From what I see, a lot of people were angry at Anthropic's limits with the subscription plan. OpenAI had some issue I can't remember, and they reset people's token usage (for the session or weekly limits). I think they got a lot of good press, now OpenAI seems to just do it at random when they want a PR boost. It makes scheduling your worklife a bit difficult if you are limited by that.
There are a lot of us who just use the AI on projects until the session limit hits, and wait for the usage to reset.
> There are a lot of us who just use the AI on projects until the session limit hits, and wait for the usage to reset.
Do you mean that you can't continue on your own until the reset?
Well, I was happily paying $300 canadian pesos per month to OpenAI for some time... until the tokens just dried up overnight for some reason.
I went from using it non-stop all day every day for months, to running into my weekly limit within 24 hours almost overnight.
They lied about token efficiencies and everything... said they had no idea what the problem was, etc... and then bam, once China starts releasing more powerful models, they start "resetting" our token limits constantly ... sometimes ... maybe ... if we're lucky ...
I am over it.
I don't care WHAT I pay to be perfectly honest. I would have gladly paid $2,000 per month for the service I was receiving.
I just don't like being jerked around like that.
Toodles, OpenAI.