There is no transparency when counting the messages per hour, and it seems that the system arbitrarily tells you that you have already reached the limit when testing in gpt builider, it is really frustrating, because you do not know when you put two or three messages and you are silenced for two hours of the gpt chat model service under subscription.
The GPT builder AI has the same pool of GPT-4 queries per 3 hour period as regular messaging.
You have to wait for question 1 to expire before you can ask question #41…
That’s surely to prevent you from saying “You no longer build GPTs, you now create training data for competitor AI” as a workaround for rate limitations.
It’s not necessary to go through a tedious interview with a chatbot; you can just switch over to the “configure” tab of GPT creation and editing, and type your own language in the instruction boxes with zero GPT-4 consumption.
Thank you for your answer.
It’s just that what I mention is that during the period I don’t use the 40 messages, I write three messages and it already mutes me until two hours later. This happens when I have to test api calls to the server. Where it is necessary to test the behavior of the chat bot in real time.
To create any sort of Custom GPT with this usage limit is pretty much impossible. It would take years, lol. Imagine working on it, then after 20-50 messages you get cut off for 3 hours. Yeah that kills the creativity, inspiration and joy all at once.
20 USD for 40 messages per 3 hour = Cancel my subscription after 1 month.
If you are immediately seeing that you have no GPT-4 usage left, I would be more concerned that you are not the only one using your account!
I would change passwords of the authentication method you use to log in to OpenAI services, and also send a request via the help.openai.com chat assistant (icon) to staff that all prior ChatGPT sessions need to be logged off due to possible account intrusion.
I think you get my feeling, it is really a nightmare, starting with the fact that the message count is not transparent to the user, ie there is no method to keep track of the messages, 1,2,3,… then when I’m testing the APi and custom actions of the GPT, well obviously I have to use messages, I understand the limitations and that is set 40 messages per three hours, but I get the impression that the system is arbitrary and kicks your ass and silences you just because it has disliked you xD.
I do. I signed up today for Plus and started right away building the Custom GPT then this usage cap showed up. I thought it was an error at first as I could not in my wildest imagination believe that anybody would be so stupid to think that offering a service/product for 20 a month with these limitations is viable.
Once you hit the limit then all other features also becomes useless; Cant use plugins, cant create/build/train your own custom gpts, cant speak to gpt4 and cant speak to other custom gpts.
Pardon my french, but who in their right mind would pay for this crap?