GPT-4o is stuck in a loop and unusable

[lily_of_the_valley]

I have a custom GPT that co-writes a story with me based on my fairly detailed instructions, but for the past two months, something seems to have gone wrong. The style and language of the chatbot remain the same, but there’s something odd with its memory – at least that’s what I think. The chatbot gets stuck in a loop. Only the first few responses in a conversation seem original, and then it starts repeating itself; for instance, the character performs similar actions in different scenes. It’s almost like Groundhog Day. Before, I could create longer conversations without this issue, and every response from ChatGPT was fresh, but now it just doesn’t make sense.

I believe the problem began when Custom GPTs switched to the new GPT-4o model. I don’t understand why, as a ChatGPT Plus user, I can’t choose whether my GPTs use the GPT-4 or GPT-4o model. What’s the point of GPT-4o having a higher message limit when I have to generate more responses before I get one that satisfies me, and even then, I’m often still not happy with it? I rarely hit the message limit with GPT-4, so I don’t see why that model can’t remain available with custom GPTs.

I’m considering cancelling my subscription until the quality of GPT-4o’s responses improves or GPTs have the option to choose the model. Since I can choose the model with regular chat, why can’t I do the same with GPTs if I’m a paying user?

Is anyone else noticing the same problems as I am?

[elazar]

Hi, I’m experiencing the same issues. Try to look at you memory limits

[lachie1]

I have had similar issues with regular chats.

[lily_of_the_valley]

That can’t be right, because I used to have longer conversations and this problem didn’t happen before. GPT-4 has a long contextual memory, and GPT-4o has the same.

[anayjh2412]

Look if that is the concern then let me clarify that there is no ai in this world without this problem though it may look like it does not repeat in loop but thats not the case it may giveany responses without repeating but at a point it always start looping. And this is true for EACH AND EVERY AI MODEL/CHATBOT

[FortuneTeller]

I’m experiencing the similar issue, and GPTs builder didn’t provide any solution or tools to resolve this. Feels bad about it.

[_j]

I just have to search for my own naming of this “stuck in a loop”, which you’ll discern below, where the length of a ChatGPT conversation quickly degrades the (post-devday cheapening) AI, and the model starts referring back incorrecly through its narrow vision to past messages instead of seeing the forest and a progression leading up to the latest input’s needs.

@_j

This friendly agreement over quality I note is also symptomatic in models as they continue to be released and updated by OpenAI. It often becomes a useless parrot, besides other symptoms like getting “hung up” on past inputs.

@_j

The same behavior has hit ChatGPT’s GPT-4 as hit GPT-3.5-turbo around September (so that GPT-3.5 couldn’t code as well as crippled GPT-4?):

Hung up on past inputs.

Repeating the same code back to you with errors it just fixed re-included. Repeatedly. Rewriting the parameters and values of API functions to hallucinations. Rewriting the whole code base with a different encoder library and discarding 50% of the functionality, even against direct instructions not to alter more than instructed the second or third try.

@_j

And guess what I just had in ChatGPT with GPT-4. The same manifestation seen in those later alterations to gpt-3.5 besides the inability to follow system instructions: Hung up on prior inputs, unable to complete a new task but instead parroting back a prior code job, trying to answer my new question in the frame of existing context, and then spitting out the same code again, despite clear instructions that old code is no longer under question. To where the session had to be abandoned.

ChatGPT doesn’t have the “forgets what you said after 3 turns” of chat management any more - but maybe it SHOULD have that option.

Fortunately there’s (until June 2025?) API GPT-4 that hasn’t been hit badly.

o1 models are showing to be far worse in this; might as well just paste into a new session for every question and iteration. An o1-xxx “regenerate” in ChatGPT is generally better than what another model responded at a particular point, but you only get one go at good quality.

Someone needs to make a “long conversation” benchmark, instead of a “can answer one question” benchmark that AI companies compete with and tout…

[mhenrynyc]

It is making me crazy. I am trying to organize a document, actually a friends legal case with text messages that support his case. Every command I give says “include all text messages” and it never sends them all and then apologizes and understands my frustrations. It doesn’t. I switch between my Mac OS app and web version and each the same. It causing major major headaches. It also can’t seem to create a Word document these days. Any advice, explanation or misery anyone can share about the disconnect lately?